From Corpus to Cockpit: Generating Emergency Lexical Bundles in Aviation Context

preprint OA: closed CC-BY-4.0
📄 Open PDF Full text JSON View at publisher

Abstract

Abstract This study examines how AI-driven concordance analysis can identify syntactic patterns in aviation emergency communication, with the goal of informing ICAO-aligned training materials. Routine aviation exchanges follow standard phraseology, but emergencies demand flexible, context-specific language. Miscommunication in such situations can compromise safety. Corpus linguistics and speech act theory provide complementary frameworks for understanding how pilots and air traffic controllers use language in crises. A specialized 14,000-word corpus of 83 authentic transcripts of related emergencies was compiled. #LancsBox V6.0 retrieved concordance lines, and ChatGPT generated lexical bundles, which were compared with manual extractions using the Jaccard Similarity Index. Lexical bundles were analyzed for syntactic patterns and communicative functions using Austin’s and Searle’s speech act models. The AI and manually generated bundle lists showed 91.7% similarity, confirming high reliability of AI assisted corpus analysis. Key syntactic features included imperatives, modal verbs, elliptical forms, and technical noun phrases, serving functions such as alerting, requesting, and instructing. Speech act analysis highlighted their operational significance. AI assisted corpus analysis effectively uncovers authentic linguistic patterns in aviation emergencies, enabling the design of scenario-based, ICAO-aligned training. Future work should expand to other emergency types, integrate multimodal data, and pilot-test materials to validate pedagogical impact.
Full text 198,218 characters · extracted from preprint-html · click to expand
From Corpus to Cockpit: Generating Emergency Lexical Bundles in Aviation Context | Research Square window.SnipcartSettings = { analytics: { enabled: false } }; (function() { var accessVector = localStorage.getItem('access_vector') || ''; window.dataLayer = window.dataLayer || []; if (accessVector) { window.dataLayer.push({ user: { profile: { profileInfo: { snid: accessVector } } } }); } })(); (function(w,d,s,l,i){w[l]=w[l]||[];w[l].push({'gtm.start':new Date().getTime(),event:'gtm.js'});var f=d.getElementsByTagName(s)[0],j=d.createElement(s),dl=l!='dataLayer'?'&l='+l:'';j.async=true;j.src='https://www.googletagmanager.com/gtm.js?id='+i+dl;f.parentNode.insertBefore(j,f);})(window,document,'script','dataLayer','GTM-K279D39R'); Browse Preprints In Review Journals COVID-19 Preprints AJE Video Bytes Research Tools Research Promotion AJE Professional Editing AJE Rubriq About Preprint Platform In Review Editorial Policies Our Team Advisory Board Help Center Sign In Submit a Preprint Cite Share Download PDF Research Article From Corpus to Cockpit: Generating Emergency Lexical Bundles in Aviation Context Deni Sapta Nugraha, Eneng Uswatun Hasanah, Ratna Dewanti, Ifan Iskandar This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-8373980/v1 This work is licensed under a CC BY 4.0 License Status: Published Journal Publication published 17 Mar, 2026 Read the published version in Corpus Pragmatics → Version 1 posted You are reading this latest preprint version Abstract This study examines how AI-driven concordance analysis can identify syntactic patterns in aviation emergency communication, with the goal of informing ICAO-aligned training materials. Routine aviation exchanges follow standard phraseology, but emergencies demand flexible, context-specific language. Miscommunication in such situations can compromise safety. Corpus linguistics and speech act theory provide complementary frameworks for understanding how pilots and air traffic controllers use language in crises. A specialized 14,000-word corpus of 83 authentic transcripts of related emergencies was compiled. #LancsBox V6.0 retrieved concordance lines, and ChatGPT generated lexical bundles, which were compared with manual extractions using the Jaccard Similarity Index. Lexical bundles were analyzed for syntactic patterns and communicative functions using Austin’s and Searle’s speech act models. The AI and manually generated bundle lists showed 91.7% similarity, confirming high reliability of AI assisted corpus analysis. Key syntactic features included imperatives, modal verbs, elliptical forms, and technical noun phrases, serving functions such as alerting, requesting, and instructing. Speech act analysis highlighted their operational significance. AI assisted corpus analysis effectively uncovers authentic linguistic patterns in aviation emergencies, enabling the design of scenario-based, ICAO-aligned training. Future work should expand to other emergency types, integrate multimodal data, and pilot-test materials to validate pedagogical impact. Aviation English ChatGPT Corpus Lexical Bundles Speech act Figures Figure 1 Figure 2 Figure 3 Introduction Communication is central to human interaction, and in aviation—where lives depend on clarity, accuracy, and efficiency—it becomes a critical operational tool. In this high-stakes industry (Friginal & Roberts, 2020 ; Thorpe et al., 2022 ; Yang et al., 2023 ) effective communication minimizes ambiguity and ensures immediate comprehension, directly influencing safety outcomes. This research draws on speech act theory and pragmatics (Austin, 1962 ; Searle, 1969 ) which view language as performative—issuing commands, enacting procedures, and coordinating responses. In emergencies, excessive politeness can hinder clarity (Bonnefon et al., 2011 ), while decision-making under time pressure demands precision (Haddington & Stokoe, 2023 ). Evidence from healthcare (Yamada & Halamek, 2014 ) and cabin crew performance (Murphy, 2001 ) highlights the need for standardized, context-appropriate protocols in crisis communication. Crisis management depends on using language as a tool for swift, decisive action (Kale et al., 2021 ; Kim, 2018 ). Corpus linguistics offers a data-driven approach to studying authentic interactions (Curry & McEnery, 2025 ; McEnery & Hardie, 2012 ), revealing real-world patterns, phrases, and structures. Such insights can inform curriculum design and foster learner engagement with authentic data (Friginal & Cox, 2025 ). Corpus-based research has shaped professional communication training across disciplines. Examples include personalized lexical and keyword lists for legal English (Alasmary, 2024 ), pronunciation-focused nurse-patient materials (Staples, 2019 ), and register analysis for military contexts (Noguera-Díaz & Pérez-Paredes, 2019 )). These studies demonstrate how authentic pattern analysis can guide the creation of precise, discipline-specific materials—principles equally applicable to aviation. In aviation, where clarity, conciseness, and authority are vital, corpus-informed research reveals distinct features of Aviation English (Zhao, 2023 , 2024 ) and supports the design of authentic, context-specific training tasks (Nugraha et al., 2023 ; Pacheco et al., 2023 ; Tosqui-Lucks et al., 2024 ). Communication failures have been linked to accidents (Estival & Molesworth, 2020 ; Molesworth & Estival, 2015 ; Tarnavska et al., 2021 ), with misinterpretations heightened by accent differences (Wu et al., 2019 ). While ICAO phraseology ensures standardization (Alderson, 2009 ; Doc 9835, 2010 ), it often falls short in non-routine scenarios requiring adaptive language use. Emergencies demand more than vocabulary, they require syntactic patterns that convey urgency, instructions, or distress. Advances in AI and tools like #LancsBox enable large-scale analysis of such patterns (Brezina, 2025 ; Kwakye et al., 2024 ). While ChatGPT shows promise for needs analysis (Assassi, 2025 ), limitations remain in diagnosing language deficiencies. This study addresses these gaps by applying AI-driven concordance to a specialized corpus of fuel-related emergencies, aiming to identify recurrent syntactic patterns and inform ICAO-aligned training that reflects the urgency and complexity of real-world aviation crises. Theoretical Framework Speech Acts, Pragmatics, and Corpus: Insights from Aviation Emergencies Speech Act Theory, introduced by Austin ( 1962 ) and refined by Searle ( 1969 ), provides a foundational lens for understanding language as action. Austin’s triad—locutionary (saying), illocutionary (intention), and perlocutionary (effect)—highlights the performative potential of utterances, especially in high-stakes contexts like aviation. Searle’s classification of illocutionary acts—assertives, directives, commissives, expressives, and declarations—offers a practical tool for categorizing communicative intentions in operational settings. In aviation emergencies, speech act theory clarifies how communication affects decision-making and safety. For example, “We are declaring a fuel emergency” functions as a declaration that alters operational status, while “Requesting immediate priority landing” is a directive prompting urgent action. Such utterances directly impact coordination and risk management, illustrating the real-world relevance of illocutionary acts. Empirical studies reinforce this approach. Sassen ( 2005 ) analyzed crisis communication to identify breakdowns threatening safety, while Kale et al. ( 2021 ) highlighted pragmatic failures arising from cross-cultural misinterpretations in global aviation. Garcia ( 2016 ) observed shifts from standard phraseology to conversational forms during emergencies, improving coordination under stress. Speech act categorization also informs assessment and pedagogy. Neuro-pragmatic research links speech acts to specific brain activation patterns (Boux et al., 2021 ; Egorova et al., 2016 ), offering measurable criteria for diagnostics. Pedagogical studies emphasize explicit instruction of speech acts in language teaching (Marcet, 2024 ; Meihami & Khanlarzadeh, 2015 ) while research on communicative success underscores the value of assessing recognition and interpretation abilities (Holtgraves, 2024 ). Corpus linguistics complements these insights by uncovering authentic patterns in aviation discourse. Tools like KWIC and concordance analysis (Brezina, 2025 ) reveal the frequency, syntactic realization, and pragmatic functions of speech acts in large datasets. Studies show that corpus-informed materials improve training authenticity and align with real-world communication demands (Pacheco et al., 2023 ; Tosqui-Lucks & Silva, 2020 ; Zhao, 2024 ). Integrating speech act theory with corpus linguistics provides a comprehensive framework for analyzing aviation communication. This approach addresses linguistic form, pragmatic function, and operational efficiency, offering a robust foundation for pedagogical interventions, ICAO language assessment, and safety-focused communication training. AI Meets Corpus Linguistics: Enhancing Language Learning in High-Stakes Context The convergence of corpus linguistics and artificial intelligence (AI) has transformed the analysis of syntactic and lexico-grammatical patterns in specialized domains such as English for Specific Purposes (ESP) (Anthony, 2024 ; Kalaš, 2025 ) AI-driven concordance tools enable large-scale, precise investigations of recurrent structures previously constrained by manual analysis (H. Liu et al., 2023 ). Grounded in empirical realism, these tools allow researchers to observe and model language use in authentic contexts, enhancing accuracy, scalability, and ecological validity (Biber & Reppen, 2015 ; McEnery & Hardie, 2012 ). Epistemologically, AI concordance systems adopt an inductive, data-driven approach, aligning with Stubbs’ ( 2001 ) “linguistics of evidence” and usage-based models of language acquisition (Ellis & Wulff, 2020 ; Tyler, 2010 ). Patterns such as will be + V-ed or noun + be + adjective reveal how language encodes certainty, commands, or evaluations in domain-specific communication. These insights inform both theoretical understanding and practical instruction. AI-powered tools—including AntConc, #LancsBox, English-Corpora, and NLP platforms—use deep learning to detect patterns beyond human capacity (X. J. Liu et al., 2025 ; Thara & Poornachandran, 2022 )). They enable rapid analysis of large datasets, monitor evolving language trends, and provide real-time feedback in assessments. However, human interpretation remains essential for context, cultural nuance, and ethical considerations, emphasizing a complementary AI-human approach. In aviation English, precise linguistic patterns support safety and operational efficiency. Communication breakdowns often arise from ambiguous phrasing or deviations from expected structures (Barshi & Farris, 2016 ; Wu et al., 2019 ). AI-driven corpus analysis identifies authentic patterns—e.g., “we are losing power” or “request immediate descent”—which can be explicitly taught, equipping learners with ready-to-use linguistic templates in high-stakes situations. Pedagogically, corpus-informed materials shift instruction from prescriptive grammar to data-driven, task-based learning (Bui, 2025 ). Concordance lines can underpin awareness-raising, pattern recognition, syntactic transformation, and spoken rehearsal activities that align with learners’ professional objectives. Moreover, AI supports performance-based assessment, as advocated by ICAO Doc 9835 ( 2010 ), enabling evaluation of grammatical accuracy, pragmatic appropriateness, discourse coherence, and responsiveness under pressure (Fleckenstein et al., 2024 ; Topping et al., 2025 ). From a constructivist perspective, learners actively engage with authentic data, constructing knowledge through exploratory tasks and pattern recognition (Bayaga, 2025 ; Lin, 2021 ). AI-driven concordance integrates empirical, inductive, and constructivist principles, allowing applied linguists to design targeted activities, improve communication training, and support syllabus development, materials creation, and needs analysis. In high-risk domains like aviation, this approach ensures learners develop accurate, efficient, and contextually appropriate communicative competence. Method Research Design This study uses AI-driven concordance analysis to explore how syntactic patterns, especially lexical bundles, function in aviation emergency communication. The analysis is based on real-world data and aims to inform language training protocols that meet ICAO standards. We used #LancsBox for AI-driven concordance analysis because it can process large datasets (Brezina, 2025). To compare the lexical bundles generated by AI and those identified manually, we used the Jaccard Similarity Index to measure the overlap between two data samples (Kryszkiewicz, 2024; Verma & Aggarwal, 2020). Research Question The following primary research question and sub-questions are designed to structure the inquiry and clarify the focus of the study: 1. How can AI-driven concordance analysis be effectively incorporated using #LancsBox Version 6.0 to identify and interpret lexical bundles in aviation emergency communication? 2. How does AI concordance analysis generate (or mine) lexical bundles from concordance lines retrieved using #LancsBox Version 6.0? 3. What syntactic patterns commonly occur in aviation emergency interactions? 4. How can lexical bundles lists be analysed using Speech Act Theory? Data Collecting Procedure To answer the research questions, especially how AI concordance analysis in #LancsBox Version 6.0 can create lexical bundles from aviation emergency communication, the following procedures will be used: 1. Corpus Compilation: 1) Selecting Source Materials: Authentic cockpit voice recorder (CVR) transcripts, ATC–pilot interaction reports, and incident documentation from publicly accessible databases. 2) Setting Criteria: Texts involving emergency, non-routine, or high-stress aviation scenarios with clear speaker identification and context. 3) Volume: Approximately 14.000 words to ensure sufficient frequency data for identifying lexical bundles of “fuel “related emergency discourse. 4) Format: Transcripts were directed, retrieved through a URL address, and stored in #Lanscbox. Eighty-three transcripts were successfully collected and stored in #Lancsbox. 2. Preprocessing a specialized corpus by utilizing #LancsBox. The #Lanscbox will process the specialized corpus automatically. Transformed the transcript into plain text formats, ensuring compatibility with #LancsBox or Copy-paste the public URL address of the transcript data. Data Analysis Procedure The data analysis was conducted using the #LancsBox Version 6.0 software, employing a structured and replicable workflow to comprehensively address all research sub-questions. 1. Concordance Retrieval: This phase involves extracting target linguistic structures using the KWIC (Key Word in Context. Concordance lines will be retrieved based on the headword "Fuel" associated with emergency discourse. 2. Lexical Bundle Mining: This phase involves extracting 3- to 5-word lexical bundles from concordance lines generated in Procedure 1. ChatGPT is employed to generate these lexical bundles. 3. The Jaccard Similarity Index assessed the lexical overlap between AI-generated and manually curated KWIC word lists. It provides a robust metric for quantifying set-based similarity in binary classification scenarios. 4. Functional Categorization: This phase analyses the communicative functions of bundles, such as issuing commands, expressing problems, and requesting assistance. 5. Interpretation and Pedagogical Mapping: This phase involves interpreting patterns using concordance line context and collocation network. Subsequently, findings are translated into pedagogical recommendations, including simulation scripting, ICAO-aligned training tasks, and assessment indicators. Research Protocol Protocols are designed to extract, interpret, and validate recurring lexical and grammatical patterns within a specialized corpus of authentic ATC–pilot emergency interactions. The following table outlines the key tools, functions, and data sources utilized throughout the research process. Table 1 . Research protocol Protocols Function Data Source 1. Specialized corpus (#Lancsbox v.6.0) Collection of authentic ATC–pilot emergency interactions Public transcripts 2. #LancsBox V6.0 – KWIC Tool Retrieves concordance lines for specific lexical and syntactic queries Specialize corpus 3. ChatGPT Identifies lexical bundles Concordance lines 4. Manual concordance Analysis #LAncsBox 6.0 Identifies lexical bundles Concordance lines 5. Functional Coding Scheme manually Categories lexical bundles by Speech Act theory (e.g., request, command) Lexical bundles list 6. Literature Benchmarking Validates findings against existing lexical/phraseological studies Academic and regulatory studies in aviation and applied linguistics Results This section presents research findings addressing questions from the background section, using AI-assisted concordance analysis and manual coding of an aviation emergency communication corpus. Lexical Bundles Mining Before data mining, the initial step involves constructing a specialized corpus for aviation communication. This corpus is sourced from publicly available websites that provide communication transcripts between pilots and air traffic controllers in non-routine contexts. The collected data is stored in the #Lancsbox application version 6.0. Adhere to the provided instructions to construct a corpus online. Subsequently, #Lancsbox automatically processes the text into the specialized corpus format. Once your corpus is prepared, select one of the themes related to the emergency in KWIC. Please refer to the following Procedures: 1. Type a lemma fuel in KWIC 2. Enter the lemma, the following concordance lines will be seen: 3. Copy the concordance text from the window and paste it into the ChatGPT. 4. Compose the Prompt in the ChatGPT, for instance: Please analyze the lexical bundles that illustrate an emergency with the head word fuel based on the concordance text attached .” 5. The lexical bundles list will be displayed on ChatGPT, as evidenced in Table 2 column 2. Table 2 . Lexical Bundles Illustrating Emergency Situations with lemma Fuel Category Lexical Generator Tools Lexical Occurrences* * 1 = available 0 = Not available AI (Artificial Intelligence) Manual concordance lines analysis #Lancsbox (Line Number) AI-Words List KWIC_Words List Fuel Loss or Depletion running out of fuel 55,56 1 1 we're running out of fuel 60,62 1 1 ran out of fuel 33, 57 1 1 don't have fuel 61 1 1 zero fuel weight 21,22, 23 1 1 no fuel flow 49, 51 1 1 losing fuel like mad 52 1 1 low fuel state 35 1 1 criticality of the fuel state 36 1 1 Fuel Leak or Damage leaking fuel ignited 5 1 1 damaging a fuel tank 4 1 1 fuel tank to explode 67 1 1 fuel tank resulting from ignition 75 1 1 Leaking fuel 4, 5 1 1 uncovered on fuel during the go around 58 1 1 Fuel Dumping or Management dumping fuel is in progress (fuel dumping) 19 1 1 you dumping fuel? 18, 24, 25 1 1 start dumping fuel 24, 46 1 1 verify number two fuel (Fire) 17 1 1 ready to dump fuel 72 1 1 fuel dump on that track 85,86 1 1 can we dump fuel? Not Available 1 0 commence your fuel dump 85 1 1 Fuel Checks, Valves, and Pressure fuel pumps failed 71 1 1 fuel pressure 38, 39 1 1 fuel shut off 70 1 1 turn off all fuel valves 43, 44 1 1 fuel valves secured NOT available 1 0 open the cross feeds 37 1 1 fuel balance check 53 1 1 fuel transfer off Not Available 1 0 Fuel Status Reporting fuel on board 12, 13, 78,79,80, 82 1 0 fuel weight of 22, 23, 30 1 1 what was the fuel weight 26 1 1 tell me your fuel on board 78 1 1 number of souls on board and your fuel 79 1 1 Based on the lexical occurrences listed in Table 2. We compared two lexical bundle extraction methods—an AI-driven concordance tool and a manual KWIC-based analysis using #LancsBox—to evaluate their consistency in identifying fuel-related syntactic patterns in aviation emergency discourse. The comparison was conducted using a Jaccard Similarity Index, as can be seen in the following formula: The analysis yielded the Jaccard Similarity Index of 0.917 (See Verma & Aggarwal, 2020 for detailed computational steps). This score indicated that 91.7% of the lexical bundles identified by one method were also identified by the other (Kryszkiewicz, 2024; Verma & Aggarwal, 2020). The analysis demonstrated a high degree of similarity between the AI-generated and KWIC-generated lexical bundle lists, confirming that the AI method reliably replicates the manual extraction process in this context. This supports the validity of AI tools for applications in English for Specific Purposes (ESP), especially in aviation communication emergency context. In addition, Figure 2. illustrates the lexical overlap between the AI-generated and manually extracted (KWIC-based) lists of lexical bundles using a Venn-like diagram. The blue circle represents lexical bundles identified exclusively by the AI-based method, totalling 3 items, while the orange circle corresponds to the manually derived KWIC list, which did not yield any unique lexical bundles. The overlapping region contains 33 lexical bundles that were identified by both methods, representing a substantial convergence in output. This overlap corresponds to a Jaccard Similarity Index of 0.917, indicating a very high degree of similarity between the two extraction methods. The visualization underscores the AI tool’s reliability in reproducing results comparable to expert-guided manual concordance. The analysis of lexical bundle distribution in fuel-related aviation discourse reveals a predominance of uniform scoring patterns, with most bundles receiving a score of 2, indicating their frequent occurrence and communicative significance in abnormal situations (See Figure 3.). These bundles, such as running out of fuel , leaking fuel state , and start dumping fuel? consistently reflect critical themes like fuel exhaustion, leakage, dumping procedures , and system failures , which are essential in pilot–ATC communication. A few bundles scored lower (score = 1), such as fuel pumps failed and fuel balance check , suggesting their relatively infrequent use or specialized application in operational contexts. This distribution highlights a core set of high-utility expressions that are likely to occur in non-routine scenarios, reinforcing the importance of familiarizing aviation personnel with standardized lexical patterns that support clarity, accuracy, and quick decision-making under pressure. 1.1. Syntactic Patterns in Aviation Emergency To generate syntactic pattern, write on ChatGPT the following prompt: What types of syntactic patterns and grammatical constructions commonly occur in aviation emergency interactions referring to lexical bundles above ? ChatGPT generate the following result: This document analyses the common syntactic patterns and grammatical constructions that occur in aviation emergency interactions, based on lexical bundles related to 'fuel' emergencies. These structures reflect how language is used functionally under pressure, enabling efficient, unambiguous communication between flight crews and ATC. Table 3 . Verb Phrase Construction (VP) Pattern Example Function be + V-ing we're running out of fuel Describing ongoing events have + V-ed we have lost fuel pressure Reporting completed actions want/need + to + Verb need to dump fuel Expressing intention or urgency modal + Verb can we dump fuel? Seeking permission or showing necessity Table 4 . Noun Phrase Constructions (NP) Pattern Example Function adjective + noun low fuel state Quantification and condition reporting noun + prepositional phrase fuel on board Specificity and information transfer compound nouns fuel pressure Technical terminology Table 5 . Imperative Constructions Pattern Example Function Verb (base form) start dumping fuel Commanding or instructing Verb + NP turn off fuel valves Immediate corrective actions Table 6 . Interrogative Instructions Pattern Example Function Wh- questions What was the fuel weight? Information requests Yes/No questions You dumping fuel? Confirmation or permission-seeking Table 7 . Elliptical/ Fragmented Speech Pattern Example Function Fragmented clause Dumping fuel in progress Speed and efficiency in communication Reduced questions You dumping fuel? Rapid coordination 1.1. Austin’s Speech Act Theory Analysis Austin’s Speech Act Theory suggests that communication has three layers: the literal meaning of the utterance (locutionary act), the speaker’s communicative intent (illocutionary act), and the listener’s response or the effect of the utterance (perlocutionary act). This framework is useful in aviation training and safety communication research, helping to assess speech form, intent, and effectiveness during emergencies. Table 8. shows the analysis that contributes to developing comprehensive materials by elucidating the intricate layers of communication. Table 8 . Sample Austin's Speech Act Theory Analysis Lexical Bundle Locutionary Act (Literal) Illocutionary Act (Speaker’s Intention) Perlocutionary Act (Effect on Listener) running out of fuel Stating current fuel status Warning / alert ATC prioritizes emergency response or issues immediate clearance you dumping fuel? Asking about current action Request for confirmation Listener confirms or updates status start dumping fuel Command to begin dumping Directive / order Fuel dump procedure initiated by crew fuel on board Reporting available fuel Informational update ATC assesses situation, possibly requests more info zero fuel weight Reporting weight without fuel Technical briefing / status report Used to calculate landing configuration leaking fuel ignited Describing cause of fire Incident explanation Triggers emergency response, informs investigation turn off all fuel valves Instruction to shut fuel flow Directive for safety Listener complies, preventing escalation can we dump fuel? Asking for permission Polite request ATC approves or denies clearance losing fuel like mad Reporting rapid fuel loss Alarm / emergency alert Listener initiates troubleshooting or priority actions number of souls on board and your fuel Requesting critical passenger/fuel data Emergency coordination Supports planning for evacuation, emergency landing, or rescue Searle’s Speech Act Analysis Searle’s theory of speech acts categorises communicative functions into five distinct roles. Assertives express beliefs through verbs like state or claim, conveying information or describing conditions. Directives influence behaviour with verbs like request or command, common in instructions or appeals. Commissives commit speakers to future actions with verbs like promise or volunteer, indicating intention or obligation. Expressive reflects psychological states or emotional reactions with verbs like thank or congratulate. Declarations change the external world with verbs like resign or declare emergency. In high-stakes domains like aviation, understanding these categories ensures clear intentions and accurate communication. Table 9. shows a sample of Searle’s model pragmatic analysis that can contribute to Aviation English material design. Table 9 . Sample Searle’s Speech Act Analysis Lexical Bundle Speech Act Type Communicative Function / Explanation running out of fuel Assertive States a fact about fuel status; alerts listener to the developing critical condition. you dumping fuel? Directive Seeks confirmation of an ongoing or planned action; checks alignment or coordination. start dumping fuel Directive A command given under time pressure initiates an immediate safety-related action. fuel on board Assertive Reports a factual measurement; typically used for operational decisions. zero fuel weight Assertive Provides calculated aircraft data used for load or landing calculations. leaking fuel ignited Assertive Describes a factual event in the incident sequence; often post-event reporting. turn off all fuel valves Directive Directs safety-critical action to prevent escalation (fire/explosion). can we dump fuel? Directive A polite request seeking ATC clearance to take a procedural action. losing fuel like mad Assertive A more urgent, emotionally charged assertion of fuel loss to escalate response. number of souls on board and your fuel Directive Requesting critical information for emergency coordination (e.g., rescue planning). Discussion This study examined how AI-driven concordance tools can identify syntactic patterns in specialized aviation discourse, focusing on emergency communications involving fuel-related scenarios, and how these patterns can inform ICAO-compliant training materials. Analysis revealed that real-world aviation emergency communication is characterized by specific, functionally significant syntactic features: modal verbs for necessity and permission, imperatives for urgent directives, elliptical forms for speed and conciseness, repetition to ensure clarity, and technical noun phrases conveying precise operational meaning. Each pattern reflects the cognitive and procedural demands of high-stakes exchanges. The use of AI-driven tools—validated by a Jaccard Similarity Index of 0.917 between AI-generated and manually extracted bundles—demonstrated methodological reliability. This aligns with corpus-based ESP research (e.g., Pacheco et al., 2023 ; Friginal & Cox, 2025 ) showing that AI-enhanced tools such as #LancsBox integrated with ChatGPT can uncover linguistic patterns with precision and scalability. Beyond replication of manual work, AI amplifies analysis by revealing form–function mappings that are often overlooked, consistent with usage-based and constructivist views of language learning (Pérez-Paredes & Boulton, 2025 ). This provides a scalable pathway for generating pedagogically relevant content rooted in authentic communication. Drawing on Biber’s register analysis and usage-based linguistic theories (Ellis & Wulff, 2020 ; Pemberton, 2024 ; Tyler, 2010 ), the study reinforces that language use is patterned according to context and purpose. Imperatives and modals embody the need for unambiguous authority in cockpit–controller exchanges, while ellipsis and lexical compression facilitate rapid yet precise communication. These are not stylistic choices but operational necessities for safety and efficiency. By integrating Austin’s ( 1962 ) and Searle’s ( 1969 , 1976) speech act theories, the study moves beyond structural description to explain communicative functions. For example, the lexical bundle start dumping fuel acts as a directive with immediate illocutionary force and perlocutionary effect, prompting procedural action. This discourse–pragmatic approach bridges structural form and operational significance, offering a more complete understanding of how syntax functions in crisis communication. Embedding corpus-derived syntactic bundles into training materials can create realistic, context-sensitive resources that mirror actual cockpit and ATC exchanges. This goes beyond rote phrase memorization, helping learners develop pragmatic flexibility and situational awareness for non-routine scenarios. Speech act analysis strengthens this approach by focusing training on intentional language use, aligning with ICAO descriptors for Interaction and Structure. Corpus findings also provide a foundation for performance-based assessments, ensuring that evaluation criteria reflect operational demands. Equally noteworthy is a contribution of the study to operational safety. The potential to incorporate syntactic pattern or lexical bundles recognition into similar models, such as the civil aviation safety risk intelligent early warning model developed by Hou et al. ( 2023 ) is significant. AI-assisted communication monitoring systems represent a novel application of corpus linguistics in aviation risk management. These systems can identify anomalous deviations from normative patterns, thereby alerting crews or controllers to developing communication disruptions. This aligns with the current trend toward data-driven predictive safety frameworks, which prioritize prevention over reactive measures (Sun & Tang, 2021 ). Ultimately, the discussion emphasizes that syntactic choices in aviation emergencies are not arbitrary but are shaped by functional, procedural, and safety considerations. By illuminating these patterns through a combined lens of corpus analysis and speech act theory, the study underscores the value of linguistically informed, domain-specific training approaches in high-stakes communication domains. Implication of Syntactic Pattern Analysis The recurrent structures identified—imperatives, modals, urgent interrogatives—mirror authentic emergency speech. For example, We’re running out of fuel reports status, while Start dumping fuel issues a time-critical instruction. Integrating such data into scenario-based training prepares learners for the urgency and clarity required under stress. Exposure to authentic elliptical and repetitive structures builds awareness of how meaning is maintained despite compressed syntax. Tools like #LancsBox facilitate comparison between authentic and textbook language, enabling grammar-awareness tasks that support ICAO level calibration. Realistic assessment tasks can measure the ability to use appropriate syntactic forms under operational pressure. Table 10 . in the original text outlines how training and assessment can target functional language practice, grammar awareness, communication strategies, and data-driven language insights. Table 10 Training and Assessment Framework Area of Application Key Syntactic Features Application in Training Materials Assessment Alignment Targeted Functional Language Practice Imperatives (Start dumping fuel), Modals (Can we dump fuel?), Questions (Do we have enough fuel?) Scenario-based dialogues and simulated ATC exchanges focusing on specific communicative functions in fuel emergencies. Assess learners’ ability to use appropriate syntactic forms for different communicative functions in emergency scenarios. ICAO Level Calibration through Grammar Awareness Modal verbs (necessity, possibility), Ellipsis (information omission), Imperatives (ATC commands) Activities distinguishing between ICAO Level 3 and Level 4 + usage, practicing controlled and free production of appropriate structures. Evaluate learners’ grammatical accuracy and appropriateness in using modal verbs, ellipsis, and imperatives according to ICAO standards. Communication Strategy Training Repetition (Fuel dump. Now.), Fragmentation (Fuel…low) Exercises teaching discourse management strategies for clarity and intelligibility in emergency communication. Assess learners’ ability to use communication strategies effectively while maintaining clarity and intelligibility in emergency situations. Data-Driven Language Awareness High-frequency collocations (fuel flow), Syntactic variation (you dumping fuel?) Concordance line analysis and pattern-matching exercises raising awareness of real-world syntactic patterns. Evaluate learners’ awareness and use of high-frequency collocations and syntactic variation in emergency communication. Assessment & Remediation Alignment All syntactic features extracted from the corpus Rubric-aligned assessment prompts targeting the production and comprehension of specific syntactic features. Provide feedback referencing specific grammar categories related to the use of syntactic features in emergency communication. From a training perspective, such integration aligns with task-based and case-based learning (Bui, 2025 ; Ellis, 2017 ; Golaghaie et al., 2019 ). Trainees gain sensitivity to pragmatic norms and cues in degraded communication environments. For assessment, these patterns can serve as empirical benchmarks for fluency, coherence, and clarity, moving language testing toward performance-based validity (Douglas, 2014 ). Implication of Austin’s Speech Act Analysis Incorporating Austin’s model into aviation English design shifts the focus from form alone to communicative intent. Learners should practice recognizing illocutionary force—whether an utterance is a request , directive , or report —and anticipate perlocutionary effects on listeners. Authentic corpus samples, such as Can we dump fuel? can be classified by function, helping learners connect form to purpose. Role-plays and scenario tasks grounded in real ATC–cockpit transcripts train learners to produce language that achieves desired operational outcomes. Practicing frequent lexical bundles ( running out of fuel , we need priority ) in context enhances automaticity. Material design must also account for context-dependent multifunctionality, where the same phrase can perform different speech acts. This approach supports ICAO descriptors for Structure and Interactions, ensuring that communicative competence includes accuracy, clarity, and operational effectiveness. Implication of Searle’s Speech Act Analysis Applying Searle’s categories— assertives, directives, commissives, expressives, declarations —further refines training by emphasizing functional language use aligned with ICAO LPRs. In emergencies, directives (e.g., Start dumping fuel ), assertives (e.g., reporting fuel status), and declarations (e.g., Mayday ) are operationally critical. Scenario-based simulations can target each category: directives in time-critical instruction drills, assertives in factual reporting under pressure, and declarations in decision-making exercises. Searle’s framework also bridges standard ICAO phraseology and real-life variation. While fixed phrases promote clarity, authentic emergencies require pragmatic flexibility. Contrasting standardized and naturally occurring utterances helps learners decide when adaptation is necessary. This dual awareness reinforces ICAO descriptors for Function, Structure, Vocabulary, and Interactions. Table 11 . illustrates a material design framework based on Searle’s Speech act theory. Table 11 Framework of Aviation English Material Design Based on Searle’s Speech Act Theory Focus Area Implication for Material Design Suggested Activity / Design Idea Function-Focused Communication Training Emphasize communicative functions by teaching learners to identify and use assertives, directives, commissives, expressives, and declarations. Include classification tasks where learners identify the speech act category of given utterances. Realistic Scenario-Based Learning Use each speech act category in realistic scenarios that simulate ATC or cockpit environments to enhance functional language use. Develop scripted role-plays and branching dialogues based on speech act functions. Prioritizing High-Stakes Speech Acts Highlight directives, assertives, and declarations due to their critical role in aviation emergencies and operational clarity. Build targeted drills using lexical bundles from incident corpora to practice warning, alerting, and instructing. Developing Perlocutionary Awareness Help learners anticipate how their words will be interpreted and what actions will result, increasing communicative effectiveness. Use “What will happen next?” prediction tasks based on ATC or cockpit dialogues. Bridging Standard Phraseology and Natural Speech Teach students when to use ICAO phraseology and when natural speech is appropriate, especially in non-routine situations. Contrast ICAO-standard phrases with corpus-derived utterances to foster pragmatic flexibility. Aligning with ICAO Descriptors Map speech act functions to ICAO descriptors like Function, Structure, Vocabulary, and Interactions for focused skills development. Create ICAO assessment-style tasks requiring appropriate speech act use in simulated non-routine situations. Conclusion This study provides a comprehensive analysis of syntactic patterns in aviation emergency communication by employing AI-driven concordance techniques on a specialized corpus of pilot-ATC exchanges. Drawing on corpus linguistics and speech act theory, the research successfully identified and categorized recurrent lexical bundles—including imperatives, modals, interrogatives, elliptical forms, and noun phrases—that are functionally critical during high-stakes fuel-related emergencies. These patterns were systematically mapped to language functions such as status reporting, alerting, instructing, and requesting, and were subsequently interpreted through the perspectives of Austin's and Searle's speech act models. The findings demonstrate that in real-world crises, syntactic form is closely associated with communicative intent and operational effectiveness. By translating these syntactic insights into pedagogical strategies—such as task-based drills, ICAO-aligned assessments, and scenario-based learning—the study illustrates the potential of corpus-informed design to enhance the communicative readiness of aviation personnel. Despite its practical significance, the research acknowledges several limitations. First, while the corpus was specialized and authentic, it was limited in size and scope, focusing primarily on fuel-related emergencies. This potentially narrows the generalizability of findings to other types of emergency discourse, such as medical, weather, or technical failures. Furthermore, the reliance on a pre-compiled, static corpus may not fully capture the dynamic and evolving nature of real-time pilot-ATC communication across various contexts, regions, or aircraft types. Second, although AI tools like #LancsBox facilitated efficient pattern mining, full semantic and pragmatic interpretation still required human expertise, posing a challenge for full automation. Additionally, the study relied on existing transcript data, which may lack prosodic or multimodal cues present in live communication. These limitations suggest the need for broader and multimodal corpora, as well as a deeper integration of AI with expert-validated annotations. The study did not include empirical validation through classroom implementation or pilot testing of instructional materials based on the extracted patterns. As such, the pedagogical effectiveness of using these patterns in real-world training or assessment contexts remains unverified and warrants further applied research. Nonetheless, from the perspective of air traffic controllers and pilot instructors, the potential pedagogical value derived from the data set is commendable Future research should expand beyond a single emergency theme and incorporate a wider variety of scenarios—such as medical diversions, engine failure, or weather-related incidents—to build a more holistic model of emergency discourse. Moreover, the potential of real-time AI monitoring tools should be explored for in-flight communication analysis and predictive safety interventions. Further validation of syntactic features through pilot studies and learner assessments can also strengthen the pedagogical impact of corpus-driven materials. Lastly, interdisciplinary collaboration across aviation linguists, AI developers, and safety experts will be essential to translate linguistic insights into scalable, adaptive, and operationally meaningful training and assessment systems. Declarations Author Contribution DSN was responsible for the conceptualisation of the study, the development of the research methodology, the use of software tools for data analysis, and the writing of the original draft of the manuscript.EUH contributed to the proofreading of the manuscript and participated in the critical review of its content to improve clarity and coherence.RD was involved in the validation of the research findings and provided scholarly review to ensure the rigor and accuracy of the study.II supervised the research process and offered academic guidance throughout the development of the study. Acknowledgement In the preparation of this manuscript, we utilised ChatGPT (GPT-3.5 and 4) to enhance the clarity and coherence of the language, ensuring its adherence to the standards expected in scholarly publications. While ChatGPT contributed to the refinement of the language, it did not generate any original ideas. The authors alone are responsible for any inaccuracies present in the manuscript Data Availability Data Sharing Statement. Transcripts were obtained from publicly available resources https://www.planecrashinfo.com/lastwords.htm Ethical Standard. The authors assert that all procedures contributing to this work comply with the ethical standards of the relevant national and institutional committees on human experimentation and with the Helsinki Declaration of 1975, as revised in 2008. References Alasmary, A. (2024). Sustaining vocabulary knowledge growth through corpus-generated lists of lexical bundles and keywords in the law of contracts. Heliyon , 10 (9), e29944. https://doi.org/10.1016/J.HELIYON.2024.E29944 Alderson, J. C. (2009). Air Safety, Language Assessment Policy, and Policy Implementation: The Case of Aviation English . Annual Review of Applied Linguistics , 29 , 168–187. https://doi.org/10.1017/S0267190509090138 Anthony, L. (2024). An introduction to corpus building, corpus analysis, and AI-supported language pattern discovery (12761885). Art. 12761885. https://doi.org/none Assassi, T. (2025). ESP practitioners’ perspectives on the efficiency of using artificial intelligence ‘ChatGPT’ in needs analysis. Computer Assisted Language Learning , 1–32. https://doi.org/10.1080/09588221.2024.2428943 Austin, J. L. (1962). How to Do Things with Words (J. O. Urmson & M. Sbisa, Eds.; 2nd ed.). Harvard University Press. Barshi, I., & Farris, C. (2016). Misunderstandings in ATC Communication: Language, Cognition, and Experimental Methodology . Routledge. https://doi.org/https://doi.org/10.4324/9781315595641 Bayaga, A. (2025). Leveraging AI-enhanced and emerging technologies for pedagogical innovations in higher education. Education and Information Technologies , 30 (1), 1045–1072. https://doi.org/10.1007/s10639-024-13122-y Biber, D., & Reppen, R. (2015). The Cambridge handbook of English corpus linguistics. In The Cambridge Handbook of English Corpus Linguistics . Cambridge University Press. https://doi.org/10.1007/9781139764377 Bonnefon, J.-F., Feeney, A., & De Neys, W. (2011). The Risk of Polite Misunderstandings. Current Directions in Psychological Science , 20 (5), 321–324. https://doi.org/10.1177/0963721411418472 Boux, I., Tomasello, R., Grisoni, L., & Pulvermüller, F. (2021). Brain signatures predict communicative function of speech production in interaction. Cortex , 135 , 127–145. https://doi.org/10.1016/J.CORTEX.2020.11.008 Brezina, V. (2025). Corpus linguistics and AI: #LancsBox X in the context of emerging technologies. International Journal of Language Studies , 19 (2), 75–90. Bui, G. (2025). Task-Based Language Teaching. In Reference Module in Social Sciences . Elsevier. https://doi.org/10.1016/B978-0-323-95504-1.00434-8 Curry, N., & McEnery, T. (2025). Corpus linguistics for language teaching and learning: A research agenda. Language Teaching , 1–20. https://doi.org/10.1017/S0261444824000430 Doc 9835, Pub. L. No. Doc 9835 Manual on the Implementation of ICAO Language Proficiency Requirements, Manual (2010). https://skybrary.aero/sites/default/files/bookshelf/2497.pdf Douglas, D. (2014). Nobody seems to speak English here today: Enhancing assessment and training in aviation English. Iranian Journal of Language Teaching Research , 2 (2), 1–12. https://doi.org/10.30466/ijltr.2014.20410 Egorova, N., Shtyrov, Y., & Pulvermüller, F. (2016). Brain basis of communicative actions in language. NeuroImage , 125 , 857–867. https://doi.org/10.1016/j.neuroimage.2015.10.055 Ellis, R. (2017). Task-Based Language Teaching. In S. Loewen & M. Sato (Eds.), The Routledge Handbook of Instructed Second Language Acquisition (pp. 108–126). Routledge Taylor & Francis Group. https://doi.org/https://doi.org/10.4324/9781315676968 Ellis, & Wulff, S. (2020). Usage-Based Approaches to L2 Acquisition. In B. VanPatten, G. D. Keating, & S. Wulff (Eds.), Theories in Second Language Acquisition (pp. 63–82). Routledge. https://doi.org/https://doi.org/10.4324/9780429503986 Estival, D., & Molesworth, B. R. C. (2020). Errors in air-ground pilot communication: an experimental study. The ESPecialist , 41 (3). https://doi.org/10.23925/2318-7115.2020v41i3a5 Fleckenstein, J., Meyer, J., Jansen, T., Keller, S. D., Köller, O., & Möller, J. (2024). Do teachers spot AI? Evaluating the detectability of AI-generated texts among student essays. Computers and Education: Artificial Intelligence , 6 , 100209. https://doi.org/10.1016/j.caeai.2024.100209 Friginal, E., & Cox, A. (2025). Corpus Linguistics and English for Specific Purposes. Reference Module in Social Sciences . https://doi.org/10.1016/B978-0-323-95504-1.00481-6 Friginal, E., & Roberts, J. (2020). English in Global Aviation. English in Global Aviation . https://doi.org/10.5040/9781350059344 Garcia, A. C. (2016). Air traffic communications in routine and emergency contexts: A case study of Flight 1549 ‘miracle on the Hudson.’ Journal of Pragmatics , 106 , 57–71. https://doi.org/10.1016/j.pragma.2016.10.005 Golaghaie, F., Asgari, S., Khosravi, S., Ebrahimimonfared, M., Mohtarami, A., & Rafiei, F. (2019). Integrating case-based learning with collective reflection: outcomes of inter-professional continuing education. Reflective Practice , 20 (1), 42–55. https://doi.org/10.1080/14623943.2018.1539660 Haddington, P., & Stokoe, E. (2023). Social interaction in high stakes crisis communication. Journal of Pragmatics , 208 , 91–98. https://doi.org/10.1016/j.pragma.2023.02.014 Holtgraves, T. (2024). Emoji, Speech Acts, and Perceived Communicative Success. Journal of Language and Social Psychology , 43 (1), 83–103. https://doi.org/https://doi.org/10.1177/0261927X231200450 Hou, Z., Xiong, M., Wang, H., Lv, S., & Chen, L. (2023). Civil aviation safety risk intelligent early warning model based on text mining and multi-model fusion. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering , 237 (10), 2402–2427. https://doi.org/10.1177/09544100231153298;CTYPE:STRING:JOURNAL Kalaš, F. (2025). Bridging Tradition and Innovation: Analysing Language Data with Chatgpt-4 in Corpus Linguistics . https://doi.org/10.2139/SSRN.5126316 Kale, U., Herrera, M., & Nagy, A. (2021). Examining pragmatic failure and other language-related risks in global aviation. Aircraft Engineering and Aerospace Technology , 93 (8), 1313–1322. https://doi.org/10.1108/AEAT-03-2021-0081 Kim, H. (2018). What constitutes professional communication in aviation: Is language proficiency enough for testing purposes? Language Testing , 35 (3), 403–426. Kryszkiewicz, M. (2024). A New Approach to Deriving Jaccard Similarity and Jaccard Distance Properties with and without Considering Feature Weights. Communications in Computer and Information Science , 2145 CCIS , 341–349. https://doi.org/10.1007/978-981-97-5934-7_29 Kwakye, A. D., Jennions, I. K., & Ezhilarasu, C. M. (2024). Platform health management for aircraft maintenance – a review. Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering , 238 (3), 267–283. Lin, M. H. (2021). Effects of Data-Driven Learning on College Students of Different Grammar Proficiencies: A Preliminary Empirical Assessment in EFL Classes. SAGE Open , 11 (3), 1–15. https://doi.org/10.1177/21582440211029936 Liu, H., Macwhinney, B., Fromm, D., & Lanzi, A. (2023). Automation of Language Sample Analysis. Journal of Speech, Language, and Hearing Research , 66 (7), 2421–2433. https://doi.org/10.1044/2023_JSLHR-22-00642, Liu, X. J., Wang, J., & Zou, B. (2025). Evaluating an AI speaking assessment tool: Score accuracy, perceived validity, and oral peer feedback as feedback enhancement. Journal of English for Academic Purposes , 75 , 101505. https://doi.org/10.1016/j.jeap.2025.101505 Marcet, E. (2024). Teaching pragmatics to instructors of L2 Japanese: A relevance-theoretic approach. System , 126 , 103472. https://doi.org/10.1016/J.SYSTEM.2024.103472 McEnery, T., & Hardie, A. (2012). Corpus linguistics: Method, theory and practice. In Corpus Linguistics: Method, Theory and Practice . Cambridge University Press. https://doi.org/10.1017/CBO9780511981395 Meihami, H., & Khanlarzadeh, M. (2015). Pragmatic Content in Global and Local ELT Textbooks. Sage Open , 5 (4). https://doi.org/10.1177/2158244015615168 Molesworth, B. R. C., & Estival, D. (2015). Miscommunication in general aviation: The influence of external factors on communication errors. Safety Science , 73 , 73–79. https://doi.org/10.1016/j.ssci.2014.11.004 Murphy, A. (2001). The flight attendant dilemma: an analysis of communication and sensemaking during in-flight emergencies. Journal of Applied Communication Research , 29 (1), 30–53. https://doi.org/10.1080/00909880128100 Noguera-Díaz, Y., & Pérez-Paredes, P. (2019). Register analysis and ESP pedagogy: Noun-phrase modification in a corpus of English for military navy submariners. English for Specific Purposes , 53 , 118–130. https://doi.org/10.1016/J.ESP.2018.06.002 Nugraha, D. S., Mayuni, I., & Anwar, M. (2023). Creating aviation English lesson: a corpus-informed material design. Journal of Teaching English for Specific and Academic Purposes , 11 (1), 23–40. https://doi.org/DOI:10.22190/TESAP230131004N Pacheco, A., Garcia, A. C. de M., Monteiro, A. L. T., Prado, M. C. de A., & Tosqui-Lucks, P. (2023). Using corpus linguistics to create tasks for teaching and assessing Aeronautical English. Applied Corpus Linguistics , 3 (3), 100075. https://doi.org/10.1016/J.ACORP.2023.100075 Pemberton, I. (2024). Usage-Based Second Language Instruction . Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-53414-0 Pérez-Paredes, P., & Boulton, A. (2025). Data-driven Learning in and out of the Language Classroom . Cambridge University Press. https://doi.org/10.1017/9781009511384 Sassen, C. (2005). Linguistic Dimensions of Crisis Talk . John Benjamins Publishing Company. Searle, J. R. (1969). Speech Acts . Cambridge University Press. https://doi.org/10.1017/CBO9781139173438 Staples, S. (2019). Using corpus-based discourse analysis for curriculum development: Creating and evaluating a pronunciation course for internationally educated nurses. English for Specific Purposes , 53 , 13–29. https://doi.org/10.1016/J.ESP.2018.08.005 Stubbs, M. (2001). On inference theories and code theories: Corpus evidence for semantic schemas. Text - Interdisciplinary Journal for the Study of Discourse , 21 (3). https://doi.org/10.1515/text.2001.007 Sun, Z., & Tang, P. (2021). Automatic Communication Error Detection Using Speech Recognition and Linguistic Analysis for Proactive Control of Loss of Separation. Transportation Research Record , 2675 (5), 1–12. https://doi.org/10.1177/0361198120983004 Tarnavska, T., Baranovska, L., Glushanytsia, N., & Yahodzinskyi, S. (2021). The impact of psychological factor on the aircraft operation safety. E3S Web of Conferences , 258 , 02029. https://doi.org/10.1051/e3sconf/202125802029 Thara, S., & Poornachandran, P. (2022). Social media text analytics of Malayalam–English code-mixed using deep learning. Journal of Big Data , 9 (1), 1–25. https://doi.org/10.1186/S40537-022-00594-3/TABLES/12 Thorpe, A., Estival, D., Molesworth, B., & Eidels, A. (2022). Pilot errors: Communication comes last. Safety Science , 149 , 105686. https://doi.org/10.1016/j.ssci.2022.105686 Topping, K. J., Gehringer, E., Khosravi, H., Gudipati, S., Jadhav, K., & Susarla, S. (2025). Enhancing peer assessment with artificial intelligence. International Journal of Educational Technology in Higher Education , 22 (1), 3. https://doi.org/10.1186/s41239-024-00501-1 Tosqui-Lucks, P., Prado, M. C. de A., Pacheco, A., Garcia, A. C. de M., & Monteiro, A. L. T. (2024). Challenges and possibilities in compiling Aeronautical English corpora: The case of the Aerocorpus. Research Methods in Applied Linguistics , 3 (3), 100135. https://doi.org/10.1016/J.RMAL.2024.100135 Tosqui-Lucks, P., & Silva, A. L. B. de C. e. (2020). Aeronautical English: Investigating the nature of this specific language in search of new heights. The ESPecialist , 41 (3). https://doi.org/10.23925/2318-7115.2020v41i3a2 Tyler, A. (2010). Usage-Based Approaches to Language and Their Applications to Second Language Learning. Annual Review of Applied Linguistics , 30 , 270–291. https://doi.org/10.1017/S0267190510000140 Verma, V., & Aggarwal, R. K. (2020). A comparative analysis of similarity measures akin to the Jaccard index in collaborative recommendations: empirical and theoretical perspective. Social Network Analysis and Mining , 10 (1), 1–16. https://doi.org/10.1007/S13278-020-00660-9/METRICS Wu, Q., Molesworth, B. R. C., & Estival, D. (2019). An Investigation into the Factors that Affect Miscommunication between Pilots and Air Traffic Controllers in Commercial Aviation. International Journal of Aerospace Psychology , 29 (1–2), 53–63. https://doi.org/10.1080/24721840.2019.1604138 Yamada, N. K., & Halamek, L. P. (2014). Communication during resuscitation: Time for a change? Resuscitation , 85 (12), e191–e192. https://doi.org/10.1016/j.resuscitation.2014.08.034 Yang, H.-H., Chang, Y.-H., & Chou, Y.-H. (2023). Subjective measures of communication errors between pilots and air traffic controllers. Journal of Air Transport Management , 112 , 102461. https://doi.org/10.1016/j.jairtraman.2023.102461 Zhao, W. (2023). A corpus-based study on aviation English from the perspective of systemic functional linguistics. Discourse & Communication , 17 (5), 630–661. https://doi.org/10.1177/17504813231171644 Zhao, W. (2024). A corpus-based multi-dimensional analysis of the linguistic features of Aviation English. English for Specific Purposes , 76 , 57–73. https://doi.org/10.1016/j.esp.2024.05.004 Additional Declarations No competing interests reported. Cite Share Download PDF Status: Published Journal Publication published 17 Mar, 2026 Read the published version in Corpus Pragmatics → Version 1 posted You are reading this latest preprint version Research Square lets you share your work early, gain feedback from the community, and start making changes to your manuscript prior to peer review in a journal. As a division of Research Square Company, we’re committed to making research communication faster, fairer, and more useful. We do this by developing innovative software and high quality services for the global research community. Our growing team is made up of researchers and industry professionals working together to solve the most critical problems facing scientific publishing. Also discoverable on Platform About Our Team In Review Editorial Policies Advisory Board Help Center Resources Author Services Accessibility API Access RSS feed Manage Cookie Preferences © Research Square 2026 | ISSN 2693-5015 (online) Privacy Policy Terms of Service Do Not Sell My Personal Information {"props":{"pageProps":{"initialData":{"identity":"rs-8373980","acceptedTermsAndConditions":true,"allowDirectSubmit":true,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":562421497,"identity":"1d66262e-5ccf-4feb-b195-c824e701bb1b","order_by":0,"name":"Deni Sapta Nugraha","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAABBklEQVRIiWNgGAWjYDCCA2AEAsxA2gAhwQMTx6mFh4EtgXgtUBU8Bjik0ADf8d6DBxj+2OXZs5/59rigwC5x+4z0Cww/ahhk+HBokTxzLuEAY1tyMQ9P7nbjGQbJiXNu5BQw9hxj4JHEocXgRo7BAcYG5sQehtxt0jwGBxJnSOQkMPA2AN2JS8v9N0CpP/WJPfxvnsG1MP7Fp+UGSIrtcGKPRA4bVEv6AWZ8tkieATosse14Mc+NZ+YgvxjP4HnDcFjmmAROv/AdP2P84cOf6jz2/uRnjwv+2MnOYE9/+PBNjY09rhADgwQwYmBjhnDBTpLAox6uC66F/QFB5aNgFIyCUTCiAABxDV+moDdG3AAAAABJRU5ErkJggg==","orcid":"","institution":"Politeknik Penerbangan Indonesia Curug","correspondingAuthor":true,"prefix":"","firstName":"Deni","middleName":"Sapta","lastName":"Nugraha","suffix":""},{"id":562421498,"identity":"968b898a-afe9-4f04-9067-aeb6ecc29252","order_by":1,"name":"Eneng Uswatun Hasanah","email":"","orcid":"","institution":"MAN Insan Cendekia Serpong","correspondingAuthor":false,"prefix":"","firstName":"Eneng","middleName":"Uswatun","lastName":"Hasanah","suffix":""},{"id":562421499,"identity":"a950d7e9-4b58-4440-af0a-fa54d07f03ca","order_by":2,"name":"Ratna Dewanti","email":"","orcid":"","institution":"State University of Jakarta","correspondingAuthor":false,"prefix":"","firstName":"Ratna","middleName":"","lastName":"Dewanti","suffix":""},{"id":562421500,"identity":"de430956-e1d8-4005-b910-c9c055dd448a","order_by":3,"name":"Ifan Iskandar","email":"","orcid":"","institution":"State University of Jakarta","correspondingAuthor":false,"prefix":"","firstName":"Ifan","middleName":"","lastName":"Iskandar","suffix":""}],"badges":[],"createdAt":"2025-12-16 09:08:56","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-8373980/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-8373980/v1","draftVersion":[],"editorialEvents":[{"content":"https://doi.org/10.1007/s41701-026-00234-8","type":"published","date":"2026-03-17T15:59:33+00:00"}],"editorialNote":"","failedWorkflow":false,"files":[{"id":98804138,"identity":"4a64051a-76e2-42eb-aa6a-d75735d7e3ba","added_by":"auto","created_at":"2025-12-22 14:21:00","extension":"docx","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":793581,"visible":true,"origin":"","legend":"","description":"","filename":"Anonymous.docx","url":"https://assets-eu.researchsquare.com/files/rs-8373980/v1/bedebd31410286edd3c75b1a.docx"},{"id":98804065,"identity":"1f22e18c-b6b8-4130-85bf-bd9529ee80f6","added_by":"auto","created_at":"2025-12-22 14:20:59","extension":"json","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6615,"visible":true,"origin":"","legend":"","description":"","filename":"77b46ac151144a78be17cbfbe1d8d56b.json","url":"https://assets-eu.researchsquare.com/files/rs-8373980/v1/67169a401d315c222f8675eb.json"},{"id":98803635,"identity":"feb6af59-2014-4a32-aeff-035b3ed0baa1","added_by":"auto","created_at":"2025-12-22 14:20:43","extension":"xml","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":173476,"visible":true,"origin":"","legend":"","description":"","filename":"77b46ac151144a78be17cbfbe1d8d56b1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-8373980/v1/d52cd3e2a0270c53c21a5b29.xml"},{"id":98803645,"identity":"71851cc1-200b-405c-8c0e-5937c5cfe30b","added_by":"auto","created_at":"2025-12-22 14:20:44","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":354359,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8373980/v1/2f05c1430d47b7350076c9d7.png"},{"id":98804359,"identity":"e94d7ab3-8860-466b-8a99-d0683c36d30f","added_by":"auto","created_at":"2025-12-22 14:21:07","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":87790,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8373980/v1/41639fb6fdc330d93589b239.png"},{"id":98803682,"identity":"f820b49a-a8dd-4342-a65b-f3d64238eb94","added_by":"auto","created_at":"2025-12-22 14:20:52","extension":"png","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":155713,"visible":true,"origin":"","legend":"","description":"","filename":"floatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8373980/v1/f5a5a7beb59fdc3a10622575.png"},{"id":98804140,"identity":"acf96ecb-71d7-459c-b886-b9b936e10cef","added_by":"auto","created_at":"2025-12-22 14:21:01","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":88030,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage1.png","url":"https://assets-eu.researchsquare.com/files/rs-8373980/v1/b7d8ac1220ad7a7cf06500e8.png"},{"id":98803660,"identity":"cb56c720-dee7-441a-b378-f93949cdaf34","added_by":"auto","created_at":"2025-12-22 14:20:47","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":23296,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage2.png","url":"https://assets-eu.researchsquare.com/files/rs-8373980/v1/fdb3e14087ff875688a89e33.png"},{"id":98803657,"identity":"e958e1a6-07bb-4e60-878c-1eecb413f969","added_by":"auto","created_at":"2025-12-22 14:20:46","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":43895,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinefloatimage3.png","url":"https://assets-eu.researchsquare.com/files/rs-8373980/v1/1f292c2292499e4bd0b4ecc2.png"},{"id":98803643,"identity":"7cfe03ab-beab-42f0-8f54-c9cd2681684c","added_by":"auto","created_at":"2025-12-22 14:20:43","extension":"xml","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":170119,"visible":true,"origin":"","legend":"","description":"","filename":"77b46ac151144a78be17cbfbe1d8d56b1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-8373980/v1/480cacf498cb842bcb1bb6e6.xml"},{"id":98803877,"identity":"6e622d17-e054-40a8-a10e-56981b3b2d91","added_by":"auto","created_at":"2025-12-22 14:20:54","extension":"html","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":188009,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-8373980/v1/be3fa35ff23be9c3b4884198.html"},{"id":98803656,"identity":"70b98850-7103-4342-a369-2cee16bcd462","added_by":"auto","created_at":"2025-12-22 14:20:46","extension":"png","order_by":1,"title":"Figure 1","display":"","copyAsset":false,"role":"figure","size":314253,"visible":true,"origin":"","legend":"\u003cp\u003eConcordance List from Lancsbox Ver.6.0\u003c/p\u003e","description":"","filename":"1.png","url":"https://assets-eu.researchsquare.com/files/rs-8373980/v1/42747779bbbd5845d8b48b1a.png"},{"id":98804413,"identity":"76bb14ba-4d9f-473b-beec-34388ad95137","added_by":"auto","created_at":"2025-12-22 14:21:13","extension":"png","order_by":2,"title":"Figure 2","display":"","copyAsset":false,"role":"figure","size":38017,"visible":true,"origin":"","legend":"\u003cp\u003eJaccard Similarity Diagram\u003c/p\u003e","description":"","filename":"2.png","url":"https://assets-eu.researchsquare.com/files/rs-8373980/v1/12e10ed8ae9df7bb8948daf6.png"},{"id":98803658,"identity":"44d6e2dd-eca9-45be-a4b9-a7ecb0b44235","added_by":"auto","created_at":"2025-12-22 14:20:46","extension":"png","order_by":3,"title":"Figure 3","display":"","copyAsset":false,"role":"figure","size":110273,"visible":true,"origin":"","legend":"\u003cp\u003eScore distribution for different lexical bundles\u003c/p\u003e","description":"","filename":"3.png","url":"https://assets-eu.researchsquare.com/files/rs-8373980/v1/1f3e689b8e2445fe07724874.png"},{"id":105223748,"identity":"a879167b-8dce-44c4-92a1-a7720fc53dc3","added_by":"auto","created_at":"2026-03-23 16:09:49","extension":"pdf","order_by":0,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1689921,"visible":true,"origin":"","legend":"","description":"","filename":"manuscript.pdf","url":"https://assets-eu.researchsquare.com/files/rs-8373980/v1/f899061f-8d89-4bd7-acc5-20742a6ef1c6.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"From Corpus to Cockpit: Generating Emergency Lexical Bundles in Aviation Context ","fulltext":[{"header":"Introduction","content":"\u003cp\u003eCommunication is central to human interaction, and in aviation\u0026mdash;where lives depend on clarity, accuracy, and efficiency\u0026mdash;it becomes a critical operational tool. In this high-stakes industry (Friginal \u0026amp; Roberts, \u003cspan citationid=\"CR22\" class=\"CitationRef\"\u003e2020\u003c/span\u003e; Thorpe et al., \u003cspan citationid=\"CR53\" class=\"CitationRef\"\u003e2022\u003c/span\u003e; Yang et al., \u003cspan citationid=\"CR61\" class=\"CitationRef\"\u003e2023\u003c/span\u003e) effective communication minimizes ambiguity and ensures immediate comprehension, directly influencing safety outcomes. This research draws on speech act theory and pragmatics (Austin, \u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e1962\u003c/span\u003e; Searle, \u003cspan citationid=\"CR47\" class=\"CitationRef\"\u003e1969\u003c/span\u003e) which view language as performative\u0026mdash;issuing commands, enacting procedures, and coordinating responses. In emergencies, excessive politeness can hinder clarity (Bonnefon et al., \u003cspan citationid=\"CR9\" class=\"CitationRef\"\u003e2011\u003c/span\u003e), while decision-making under time pressure demands precision (Haddington \u0026amp; Stokoe, \u003cspan citationid=\"CR25\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). Evidence from healthcare (Yamada \u0026amp; Halamek, \u003cspan citationid=\"CR60\" class=\"CitationRef\"\u003e2014\u003c/span\u003e) and cabin crew performance (Murphy, \u003cspan citationid=\"CR40\" class=\"CitationRef\"\u003e2001\u003c/span\u003e) highlights the need for standardized, context-appropriate protocols in crisis communication.\u003c/p\u003e \u003cp\u003eCrisis management depends on using language as a tool for swift, decisive action (Kale et al., \u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e2021\u003c/span\u003e; Kim, \u003cspan citationid=\"CR30\" class=\"CitationRef\"\u003e2018\u003c/span\u003e). Corpus linguistics offers a data-driven approach to studying authentic interactions (Curry \u0026amp; McEnery, \u003cspan citationid=\"CR13\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; McEnery \u0026amp; Hardie, \u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e2012\u003c/span\u003e), revealing real-world patterns, phrases, and structures. Such insights can inform curriculum design and foster learner engagement with authentic data (Friginal \u0026amp; Cox, \u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e2025\u003c/span\u003e). Corpus-based research has shaped professional communication training across disciplines. Examples include personalized lexical and keyword lists for legal English (Alasmary, \u003cspan citationid=\"CR1\" class=\"CitationRef\"\u003e2024\u003c/span\u003e), pronunciation-focused nurse-patient materials (Staples, \u003cspan citationid=\"CR48\" class=\"CitationRef\"\u003e2019\u003c/span\u003e), and register analysis for military contexts (Noguera-D\u0026iacute;az \u0026amp; P\u0026eacute;rez-Paredes, \u003cspan citationid=\"CR41\" class=\"CitationRef\"\u003e2019\u003c/span\u003e)). These studies demonstrate how authentic pattern analysis can guide the creation of precise, discipline-specific materials\u0026mdash;principles equally applicable to aviation.\u003c/p\u003e \u003cp\u003eIn aviation, where clarity, conciseness, and authority are vital, corpus-informed research reveals distinct features of Aviation English (Zhao, \u003cspan citationid=\"CR62\" class=\"CitationRef\"\u003e2023\u003c/span\u003e, \u003cspan citationid=\"CR63\" class=\"CitationRef\"\u003e2024\u003c/span\u003e) and supports the design of authentic, context-specific training tasks (Nugraha et al., \u003cspan citationid=\"CR42\" class=\"CitationRef\"\u003e2023\u003c/span\u003e; Pacheco et al., \u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e2023\u003c/span\u003e; Tosqui-Lucks et al., \u003cspan citationid=\"CR55\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). Communication failures have been linked to accidents (Estival \u0026amp; Molesworth, \u003cspan citationid=\"CR19\" class=\"CitationRef\"\u003e2020\u003c/span\u003e; Molesworth \u0026amp; Estival, \u003cspan citationid=\"CR39\" class=\"CitationRef\"\u003e2015\u003c/span\u003e; Tarnavska et al., \u003cspan citationid=\"CR51\" class=\"CitationRef\"\u003e2021\u003c/span\u003e), with misinterpretations heightened by accent differences (Wu et al., \u003cspan citationid=\"CR59\" class=\"CitationRef\"\u003e2019\u003c/span\u003e). While ICAO phraseology ensures standardization (Alderson, \u003cspan citationid=\"CR2\" class=\"CitationRef\"\u003e2009\u003c/span\u003e; Doc 9835, \u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e2010\u003c/span\u003e), it often falls short in non-routine scenarios requiring adaptive language use.\u003c/p\u003e \u003cp\u003eEmergencies demand more than vocabulary, they require syntactic patterns that convey urgency, instructions, or distress. Advances in AI and tools like #LancsBox enable large-scale analysis of such patterns (Brezina, \u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Kwakye et al., \u003cspan citationid=\"CR32\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). While ChatGPT shows promise for needs analysis (Assassi, \u003cspan citationid=\"CR4\" class=\"CitationRef\"\u003e2025\u003c/span\u003e), limitations remain in diagnosing language deficiencies. This study addresses these gaps by applying AI-driven concordance to a specialized corpus of fuel-related emergencies, aiming to identify recurrent syntactic patterns and inform ICAO-aligned training that reflects the urgency and complexity of real-world aviation crises.\u003c/p\u003e"},{"header":"Theoretical Framework","content":"\u003cdiv id=\"Sec3\" class=\"Section2\"\u003e \u003ch2\u003eSpeech Acts, Pragmatics, and Corpus: Insights from Aviation Emergencies\u003c/h2\u003e \u003cp\u003eSpeech Act Theory, introduced by Austin (\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e1962\u003c/span\u003e) and refined by Searle (\u003cspan citationid=\"CR47\" class=\"CitationRef\"\u003e1969\u003c/span\u003e), provides a foundational lens for understanding language as action. Austin\u0026rsquo;s triad\u0026mdash;locutionary (saying), illocutionary (intention), and perlocutionary (effect)\u0026mdash;highlights the performative potential of utterances, especially in high-stakes contexts like aviation. Searle\u0026rsquo;s classification of illocutionary acts\u0026mdash;assertives, directives, commissives, expressives, and declarations\u0026mdash;offers a practical tool for categorizing communicative intentions in operational settings.\u003c/p\u003e \u003cp\u003eIn aviation emergencies, speech act theory clarifies how communication affects decision-making and safety. For example, \u0026ldquo;We are declaring a fuel emergency\u0026rdquo; functions as a declaration that alters operational status, while \u0026ldquo;Requesting immediate priority landing\u0026rdquo; is a directive prompting urgent action. Such utterances directly impact coordination and risk management, illustrating the real-world relevance of illocutionary acts. Empirical studies reinforce this approach. Sassen (\u003cspan citationid=\"CR46\" class=\"CitationRef\"\u003e2005\u003c/span\u003e) analyzed crisis communication to identify breakdowns threatening safety, while Kale et al. (\u003cspan citationid=\"CR29\" class=\"CitationRef\"\u003e2021\u003c/span\u003e) highlighted pragmatic failures arising from cross-cultural misinterpretations in global aviation. Garcia (\u003cspan citationid=\"CR23\" class=\"CitationRef\"\u003e2016\u003c/span\u003e) observed shifts from standard phraseology to conversational forms during emergencies, improving coordination under stress.\u003c/p\u003e \u003cp\u003eSpeech act categorization also informs assessment and pedagogy. Neuro-pragmatic research links speech acts to specific brain activation patterns (Boux et al., \u003cspan citationid=\"CR10\" class=\"CitationRef\"\u003e2021\u003c/span\u003e; Egorova et al., \u003cspan citationid=\"CR16\" class=\"CitationRef\"\u003e2016\u003c/span\u003e), offering measurable criteria for diagnostics. Pedagogical studies emphasize explicit instruction of speech acts in language teaching (Marcet, \u003cspan citationid=\"CR36\" class=\"CitationRef\"\u003e2024\u003c/span\u003e; Meihami \u0026amp; Khanlarzadeh, \u003cspan citationid=\"CR38\" class=\"CitationRef\"\u003e2015\u003c/span\u003e) while research on communicative success underscores the value of assessing recognition and interpretation abilities (Holtgraves, \u003cspan citationid=\"CR26\" class=\"CitationRef\"\u003e2024\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eCorpus linguistics complements these insights by uncovering authentic patterns in aviation discourse. Tools like KWIC and concordance analysis (Brezina, \u003cspan citationid=\"CR11\" class=\"CitationRef\"\u003e2025\u003c/span\u003e) reveal the frequency, syntactic realization, and pragmatic functions of speech acts in large datasets. Studies show that corpus-informed materials improve training authenticity and align with real-world communication demands (Pacheco et al., \u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e2023\u003c/span\u003e; Tosqui-Lucks \u0026amp; Silva, \u003cspan citationid=\"CR56\" class=\"CitationRef\"\u003e2020\u003c/span\u003e; Zhao, \u003cspan citationid=\"CR63\" class=\"CitationRef\"\u003e2024\u003c/span\u003e). Integrating speech act theory with corpus linguistics provides a comprehensive framework for analyzing aviation communication. This approach addresses linguistic form, pragmatic function, and operational efficiency, offering a robust foundation for pedagogical interventions, ICAO language assessment, and safety-focused communication training.\u003c/p\u003e \u003c/div\u003e\n\u003ch3\u003eAI Meets Corpus Linguistics: Enhancing Language Learning in High-Stakes Context\u003c/h3\u003e\n\u003cp\u003eThe convergence of corpus linguistics and artificial intelligence (AI) has transformed the analysis of syntactic and lexico-grammatical patterns in specialized domains such as English for Specific Purposes (ESP) (Anthony, \u003cspan citationid=\"CR3\" class=\"CitationRef\"\u003e2024\u003c/span\u003e; Kalaš, \u003cspan citationid=\"CR28\" class=\"CitationRef\"\u003e2025\u003c/span\u003e) AI-driven concordance tools enable large-scale, precise investigations of recurrent structures previously constrained by manual analysis (H. Liu et al., \u003cspan citationid=\"CR34\" class=\"CitationRef\"\u003e2023\u003c/span\u003e). Grounded in empirical realism, these tools allow researchers to observe and model language use in authentic contexts, enhancing accuracy, scalability, and ecological validity (Biber \u0026amp; Reppen, \u003cspan citationid=\"CR8\" class=\"CitationRef\"\u003e2015\u003c/span\u003e; McEnery \u0026amp; Hardie, \u003cspan citationid=\"CR37\" class=\"CitationRef\"\u003e2012\u003c/span\u003e).\u003c/p\u003e \u003cp\u003eEpistemologically, AI concordance systems adopt an inductive, data-driven approach, aligning with Stubbs\u0026rsquo; (\u003cspan citationid=\"CR49\" class=\"CitationRef\"\u003e2001\u003c/span\u003e) \u0026ldquo;linguistics of evidence\u0026rdquo; and usage-based models of language acquisition (Ellis \u0026amp; Wulff, \u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e2020\u003c/span\u003e; Tyler, \u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e2010\u003c/span\u003e). Patterns such as \u003cem\u003ewill be +\u0026thinsp;V-ed\u003c/em\u003e or \u003cem\u003enoun\u0026thinsp;+\u0026thinsp;be +\u0026thinsp;adjective\u003c/em\u003e reveal how language encodes certainty, commands, or evaluations in domain-specific communication. These insights inform both theoretical understanding and practical instruction. AI-powered tools\u0026mdash;including AntConc, #LancsBox, English-Corpora, and NLP platforms\u0026mdash;use deep learning to detect patterns beyond human capacity (X. J. Liu et al., \u003cspan citationid=\"CR35\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Thara \u0026amp; Poornachandran, \u003cspan citationid=\"CR52\" class=\"CitationRef\"\u003e2022\u003c/span\u003e)). They enable rapid analysis of large datasets, monitor evolving language trends, and provide real-time feedback in assessments. However, human interpretation remains essential for context, cultural nuance, and ethical considerations, emphasizing a complementary AI-human approach.\u003c/p\u003e \u003cp\u003eIn aviation English, precise linguistic patterns support safety and operational efficiency. Communication breakdowns often arise from ambiguous phrasing or deviations from expected structures (Barshi \u0026amp; Farris, \u003cspan citationid=\"CR6\" class=\"CitationRef\"\u003e2016\u003c/span\u003e; Wu et al., \u003cspan citationid=\"CR59\" class=\"CitationRef\"\u003e2019\u003c/span\u003e). AI-driven corpus analysis identifies authentic patterns\u0026mdash;e.g., \u0026ldquo;we are losing power\u0026rdquo; or \u0026ldquo;request immediate descent\u0026rdquo;\u0026mdash;which can be explicitly taught, equipping learners with ready-to-use linguistic templates in high-stakes situations. Pedagogically, corpus-informed materials shift instruction from prescriptive grammar to data-driven, task-based learning (Bui, \u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e2025\u003c/span\u003e). Concordance lines can underpin awareness-raising, pattern recognition, syntactic transformation, and spoken rehearsal activities that align with learners\u0026rsquo; professional objectives. Moreover, AI supports performance-based assessment, as advocated by ICAO Doc 9835 (\u003cspan citationid=\"CR14\" class=\"CitationRef\"\u003e2010\u003c/span\u003e), enabling evaluation of grammatical accuracy, pragmatic appropriateness, discourse coherence, and responsiveness under pressure (Fleckenstein et al., \u003cspan citationid=\"CR20\" class=\"CitationRef\"\u003e2024\u003c/span\u003e; Topping et al., \u003cspan citationid=\"CR54\" class=\"CitationRef\"\u003e2025\u003c/span\u003e). From a constructivist perspective, learners actively engage with authentic data, constructing knowledge through exploratory tasks and pattern recognition (Bayaga, \u003cspan citationid=\"CR7\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Lin, \u003cspan citationid=\"CR33\" class=\"CitationRef\"\u003e2021\u003c/span\u003e). AI-driven concordance integrates empirical, inductive, and constructivist principles, allowing applied linguists to design targeted activities, improve communication training, and support syllabus development, materials creation, and needs analysis. In high-risk domains like aviation, this approach ensures learners develop accurate, efficient, and contextually appropriate communicative competence.\u003c/p\u003e"},{"header":"Method","content":"\u003cp\u003e\u003cstrong\u003eResearch Design\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThis study uses AI-driven concordance analysis to explore how syntactic patterns, especially lexical bundles, function in aviation emergency communication. The analysis is based on real-world data and aims to inform language training protocols that meet ICAO standards. We used #LancsBox for AI-driven concordance analysis because it can process large datasets (Brezina, 2025). To compare the lexical bundles generated by AI and those identified manually, we used the Jaccard Similarity Index to measure the overlap between two data samples (Kryszkiewicz, 2024; Verma \u0026amp; Aggarwal, 2020).\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResearch Question\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe following primary research question and sub-questions are designed to structure the inquiry and clarify the focus of the study:\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e1.\u0026nbsp; \u0026nbsp;How can AI-driven concordance analysis be effectively incorporated using #LancsBox Version 6.0 to identify and interpret lexical bundles in aviation emergency communication?\u003c/p\u003e\n\u003cp\u003e2.\u0026nbsp; \u0026nbsp;How does AI concordance analysis generate (or mine) lexical bundles from concordance lines retrieved using #LancsBox Version 6.0?\u003c/p\u003e\n\u003cp\u003e3. \u0026nbsp; What syntactic patterns commonly occur in aviation emergency interactions?\u003c/p\u003e\n\u003cp\u003e4. \u0026nbsp; How can lexical bundles lists be analysed using Speech Act Theory?\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData Collecting Procedure\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eTo answer the research questions, especially how AI concordance analysis in #LancsBox Version 6.0 can create lexical bundles from aviation emergency communication, the following procedures will be used:\u003c/p\u003e\n\u003cp\u003e1.\u0026nbsp;\u0026nbsp;Corpus Compilation:\u003c/p\u003e\n\u003cp\u003e1)\u0026nbsp; \u0026nbsp;Selecting Source Materials: Authentic cockpit voice recorder (CVR) transcripts, ATC\u0026ndash;pilot interaction reports, and incident documentation from publicly accessible databases.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e2)\u0026nbsp; \u0026nbsp;Setting Criteria: Texts involving emergency, non-routine, or high-stress aviation scenarios with clear speaker identification and context.\u003c/p\u003e\n\u003cp\u003e3)\u0026nbsp; \u0026nbsp;Volume: Approximately 14.000 words to ensure sufficient frequency data for identifying lexical bundles of \u0026ldquo;fuel \u0026ldquo;related emergency discourse.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e4) \u0026nbsp; Format: Transcripts were directed, retrieved through a URL address, and stored in #Lanscbox. Eighty-three transcripts were successfully collected and stored in #Lancsbox.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e2. \u0026nbsp;Preprocessing a specialized corpus by utilizing #LancsBox. The #Lanscbox will process the specialized corpus automatically. Transformed the transcript into plain text formats, ensuring compatibility with #LancsBox or Copy-paste the public URL address of the transcript data.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eData Analysis Procedure\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eThe data analysis was conducted using the #LancsBox Version 6.0 software, employing a structured and replicable workflow to comprehensively address all research sub-questions.\u003c/p\u003e\n\u003cp\u003e1.\u0026nbsp; \u0026nbsp;Concordance Retrieval: This phase involves extracting target linguistic structures using the KWIC (Key Word in Context. Concordance lines will be retrieved based on the headword \u0026quot;Fuel\u0026quot; associated with emergency discourse.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e2.\u0026nbsp; \u0026nbsp;Lexical Bundle Mining: This phase involves extracting 3- to 5-word lexical bundles from concordance lines generated in Procedure 1. ChatGPT is employed to generate these lexical bundles.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e3.\u0026nbsp; \u0026nbsp;The Jaccard Similarity Index assessed the lexical overlap between AI-generated and manually curated KWIC word lists. It provides a robust metric for quantifying set-based similarity in binary classification scenarios.\u003c/p\u003e\n\u003cp\u003e4. \u0026nbsp; Functional Categorization: This phase analyses the communicative functions of bundles, such as issuing commands, expressing problems, and requesting assistance.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e5. \u0026nbsp; Interpretation and Pedagogical Mapping: This phase involves interpreting patterns using concordance line context and collocation network. Subsequently, findings are translated into pedagogical recommendations, including simulation scripting, ICAO-aligned training tasks, and assessment indicators.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eResearch Protocol\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eProtocols are designed to extract, interpret, and validate recurring lexical and grammatical patterns within a specialized corpus of authentic ATC\u0026ndash;pilot emergency interactions. The following table outlines the key tools, functions, and data sources utilized throughout the research process.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 1\u003c/strong\u003e\u003cstrong\u003e.\u003c/strong\u003e Research protocol\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" width=\"624\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eProtocols\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 274px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eFunction\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 170px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eData Source\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e1. \u0026nbsp; \u0026nbsp; Specialized corpus (#Lancsbox v.6.0)\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 274px;\"\u003e\n \u003cp\u003eCollection of authentic ATC\u0026ndash;pilot emergency interactions\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 170px;\"\u003e\n \u003cp\u003ePublic transcripts\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e2. \u0026nbsp; \u0026nbsp; #LancsBox V6.0 \u0026ndash; KWIC Tool\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 274px;\"\u003e\n \u003cp\u003eRetrieves concordance lines for specific lexical and syntactic queries\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 170px;\"\u003e\n \u003cp\u003eSpecialize corpus\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e3. \u0026nbsp; \u0026nbsp; ChatGPT\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 274px;\"\u003e\n \u003cp\u003eIdentifies lexical bundles\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 170px;\"\u003e\n \u003cp\u003eConcordance lines\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e4. \u0026nbsp; \u0026nbsp; Manual concordance Analysis #LAncsBox 6.0\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 274px;\"\u003e\n \u003cp\u003eIdentifies lexical bundles\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 170px;\"\u003e\n \u003cp\u003eConcordance lines\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e5. \u0026nbsp; \u0026nbsp; Functional Coding Scheme manually\u003c/p\u003e\n \u003cp\u003e\u0026nbsp;\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 274px;\"\u003e\n \u003cp\u003eCategories lexical bundles by Speech Act theory (e.g., request, command)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 170px;\"\u003e\n \u003cp\u003eLexical bundles list\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e6. \u0026nbsp; \u0026nbsp; Literature Benchmarking\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 274px;\"\u003e\n \u003cp\u003eValidates findings against existing lexical/phraseological studies\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 170px;\"\u003e\n \u003cp\u003eAcademic and regulatory studies in aviation and applied linguistics\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e"},{"header":"Results","content":"\u003cp\u003eThis section presents research findings addressing questions from the background section, using AI-assisted concordance analysis and manual coding of an aviation emergency communication corpus.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eLexical Bundles Mining\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eBefore data mining, the initial step involves constructing a specialized corpus for aviation communication. This corpus is sourced from publicly available websites that provide communication transcripts between pilots and air traffic controllers in non-routine contexts. The collected data is stored in the #Lancsbox application version 6.0. Adhere to the provided instructions to construct a corpus online. Subsequently, #Lancsbox automatically processes the text into the specialized corpus format. Once your corpus is prepared, select one of the themes related to the emergency in KWIC. Please refer to the following Procedures:\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e1. \u0026nbsp; Type a lemma \u003cem\u003efuel\u003c/em\u003e in KWIC\u003c/p\u003e\n\u003cp\u003e2. Enter the lemma, the following concordance lines will be seen:\u003c/p\u003e\n\u003cp\u003e3.\u0026nbsp; \u0026nbsp;Copy the concordance text from the window and paste it into the ChatGPT.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e4. \u0026nbsp; Compose the Prompt in the ChatGPT, for instance: \u003cem\u003ePlease analyze the lexical bundles that illustrate an emergency with the head word \u003cstrong\u003efuel\u003c/strong\u003e based on the concordance text attached\u003c/em\u003e.\u0026rdquo;\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e5. \u0026nbsp; The lexical bundles list will be displayed on ChatGPT, as evidenced in Table 2 column 2.\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 2\u003c/strong\u003e\u003cstrong\u003e.\u003c/strong\u003e Lexical Bundles Illustrating Emergency Situations with lemma Fuel\u0026nbsp;\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"2\" style=\"width: 95px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eCategory\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\" style=\"width: 337px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eLexical Generator Tools\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd colspan=\"2\" valign=\"top\" style=\"width: 170px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eLexical Occurrences*\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e* 1 = available\u003c/p\u003e\n \u003cp\u003e\u0026nbsp; \u0026nbsp;0 = Not available\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eAI (Artificial Intelligence)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eManual concordance lines analysis #Lancsbox\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n \u003cp\u003e\u003cstrong\u003e(Line Number)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eAI-Words List\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eKWIC_Words List\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"9\" valign=\"top\" style=\"width: 95px;\"\u003e\n \u003cp\u003eFuel Loss or Depletion\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003erunning out of fuel\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e55,56\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003ewe\u0026apos;re running out of fuel\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e60,62\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003eran out of fuel\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e33, 57\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003edon\u0026apos;t have fuel\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e61\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003ezero fuel weight\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e21,22, 23\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003eno fuel flow\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e49, 51\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003elosing fuel like mad\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e52\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003elow fuel state\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e35\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003ecriticality of the fuel state\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e36\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"6\" valign=\"top\" style=\"width: 95px;\"\u003e\n \u003cp\u003eFuel Leak or Damage\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003eleaking fuel ignited\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003edamaging a fuel tank\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e4\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003efuel tank to explode\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e67\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003efuel tank resulting from ignition\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e75\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003eLeaking fuel\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e4, 5\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003euncovered on fuel during the go around\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e58\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"8\" valign=\"top\" style=\"width: 95px;\"\u003e\n \u003cp\u003eFuel Dumping or Management\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003edumping fuel is in progress (fuel dumping)\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e19\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003eyou dumping fuel?\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e18, 24, 25\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003estart dumping fuel\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e24, 46\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003everify number two fuel (Fire)\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e17\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003eready to dump fuel\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e72\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003efuel dump on that track\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e85,86\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u003cem\u003ecan we dump fuel?\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eNot Available\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003ecommence your fuel dump\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e85\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"8\" valign=\"top\" style=\"width: 95px;\"\u003e\n \u003cp\u003eFuel Checks, Valves, and Pressure\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003efuel pumps failed\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e71\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003efuel pressure\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e38, 39\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003efuel shut off\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e70\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003eturn off all fuel valves\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e43, 44\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u003cem\u003efuel valves secured\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eNOT available\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003eopen the cross feeds\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e37\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003efuel balance check\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e53\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cstrong\u003e\u003cem\u003efuel transfer off\u003c/em\u003e\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eNot Available\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd rowspan=\"5\" valign=\"top\" style=\"width: 95px;\"\u003e\n \u003cp\u003eFuel Status Reporting\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003efuel on board\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e12, 13, 78,79,80, 82\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e0\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003efuel weight of\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e22, 23, 30\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003ewhat was the fuel weight\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e26\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003etell me your fuel on board\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e78\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 180px;\"\u003e\n \u003cp\u003e\u003cem\u003enumber of souls on board and your fuel\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 157px;\"\u003e\n \u003cp\u003e79\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 72px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd style=\"width: 98px;\"\u003e\n \u003cp\u003e1\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003eBased on the lexical occurrences listed in Table 2. We compared two lexical bundle extraction methods\u0026mdash;an AI-driven concordance tool and a manual KWIC-based analysis using #LancsBox\u0026mdash;to evaluate their consistency in identifying fuel-related syntactic patterns in aviation emergency discourse. The comparison was conducted using a Jaccard Similarity Index, as can be seen in the following formula:\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cimg src=\"data:image/png;base64,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\"\u003e\u003c/p\u003e\n\u003cp\u003eThe analysis yielded the \u003cem\u003eJaccard Similarity Index\u003c/em\u003e of 0.917 (See Verma \u0026amp; Aggarwal, 2020 for detailed computational steps). This score indicated that 91.7% of the lexical bundles identified by one method were also identified by the other (Kryszkiewicz, 2024; Verma \u0026amp; Aggarwal, 2020). The analysis demonstrated a high degree of similarity between the AI-generated and KWIC-generated lexical bundle lists, confirming that the AI method reliably replicates the manual extraction process in this context. This supports the validity of AI tools for applications in \u003cem\u003eEnglish for Specific Purposes\u003c/em\u003e (ESP), especially in aviation communication emergency context.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003eIn addition, \u003cstrong\u003eFigure 2.\u003c/strong\u003e illustrates the lexical overlap between the AI-generated and manually extracted (KWIC-based) lists of lexical bundles using a Venn-like diagram. The blue circle represents lexical bundles identified exclusively by the AI-based method, totalling 3 items, while the orange circle corresponds to the manually derived KWIC list, which did not yield any unique lexical bundles. The overlapping region contains 33 lexical bundles that were identified by both methods, representing a substantial convergence in output. This overlap corresponds to a Jaccard Similarity Index of 0.917, indicating a very high degree of similarity between the two extraction methods. The visualization underscores the AI tool\u0026rsquo;s reliability in reproducing results comparable to expert-guided manual concordance.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u0026nbsp;The analysis of lexical bundle distribution in fuel-related aviation discourse reveals a predominance of uniform scoring patterns, with most bundles receiving a score of 2, indicating their frequent occurrence and communicative significance in abnormal situations (See Figure 3.). These bundles, such as \u003cem\u003erunning out of fuel\u003c/em\u003e, \u003cem\u003eleaking fuel state\u003c/em\u003e, and \u003cem\u003estart dumping fuel?\u003c/em\u003e consistently reflect critical themes like \u003cem\u003efuel exhaustion, leakage, dumping procedures\u003c/em\u003e, and \u003cem\u003esystem failures\u003c/em\u003e, which are essential in pilot\u0026ndash;ATC communication. A few bundles scored lower (score = 1), such as \u003cem\u003efuel pumps failed\u003c/em\u003e and \u003cem\u003efuel balance check\u003c/em\u003e, suggesting their relatively infrequent use or specialized application in operational contexts. This distribution highlights a core set of high-utility expressions that are likely to occur in non-routine scenarios, reinforcing the importance of familiarizing aviation personnel with standardized lexical patterns that support clarity, accuracy, and quick decision-making under pressure.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003e1.1. \u0026nbsp;\u003c/strong\u003e\u003cstrong\u003eSyntactic Patterns in Aviation Emergency\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eTo generate syntactic pattern, write on ChatGPT the following prompt: \u003cem\u003eWhat types of syntactic patterns and grammatical constructions commonly occur in aviation emergency interactions referring to lexical bundles above\u003c/em\u003e? ChatGPT generate the following result:\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cem\u003eThis document analyses the common syntactic patterns and grammatical constructions that occur in aviation emergency interactions, based on lexical bundles related to \u0026apos;fuel\u0026apos; emergencies. These structures reflect how language is used functionally under pressure, enabling efficient, unambiguous communication between flight crews and ATC.\u003c/em\u003e\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 3\u003c/strong\u003e\u003cstrong\u003e.\u003c/strong\u003e Verb Phrase Construction (VP)\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePattern\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eExample\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eFunction\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003ebe + V-ing\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cem\u003ewe\u0026apos;re running out of fuel\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003eDescribing ongoing events\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003ehave + V-ed\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cem\u003ewe have lost fuel pressure\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003eReporting completed actions\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003ewant/need + to + Verb\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cem\u003eneed to dump fuel\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003eExpressing intention or urgency\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003emodal + Verb\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cem\u003ecan we dump fuel?\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003eSeeking permission or showing necessity\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cstrong\u003eTable 4\u003c/strong\u003e\u003cstrong\u003e.\u0026nbsp;\u003c/strong\u003eNoun Phrase Constructions (NP)\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePattern\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eExample\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eFunction\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003eadjective + noun\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cem\u003elow fuel state\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003eQuantification and condition reporting\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003enoun + prepositional phrase\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cem\u003efuel on board\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003eSpecificity and information transfer\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003ecompound nouns\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cem\u003efuel pressure\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003eTechnical terminology\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cstrong\u003eTable 5\u003c/strong\u003e. Imperative Constructions\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePattern\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eExample\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eFunction\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003eVerb (base form)\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cem\u003estart dumping fuel\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003eCommanding or instructing\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003eVerb + NP\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cem\u003eturn off fuel valves\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003eImmediate corrective actions\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cstrong\u003eTable 6\u003c/strong\u003e. Interrogative Instructions\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePattern\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eExample\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eFunction\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003eWh- questions\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cem\u003eWhat was the fuel weight?\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003eInformation requests\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003eYes/No questions\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cem\u003eYou dumping fuel?\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003eConfirmation or permission-seeking\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cstrong\u003eTable 7\u003c/strong\u003e. Elliptical/ Fragmented Speech\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePattern\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eExample\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eFunction\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003eFragmented clause\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cem\u003eDumping fuel in progress\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003eSpeed and efficiency in communication\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003eReduced questions\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003e\u003cem\u003eYou dumping fuel?\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 192px;\"\u003e\n \u003cp\u003eRapid coordination\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cstrong\u003e1.1. \u0026nbsp;\u003c/strong\u003e\u003cstrong\u003eAustin\u0026rsquo;s Speech Act Theory Analysis\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eAustin\u0026rsquo;s Speech Act Theory suggests that communication has three layers: the literal meaning of the utterance (locutionary act), the speaker\u0026rsquo;s communicative intent (illocutionary act), and the listener\u0026rsquo;s response or the effect of the utterance (perlocutionary act). This framework is useful in aviation training and safety communication research, helping to assess speech form, intent, and effectiveness during emergencies. \u003cstrong\u003eTable 8.\u003c/strong\u003e shows the analysis that contributes to developing comprehensive materials by elucidating the intricate layers of communication.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 8\u003c/strong\u003e.\u0026nbsp;Sample Austin\u0026apos;s Speech Act Theory Analysis\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eLexical Bundle\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eLocutionary Act (Literal)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eIllocutionary Act (Speaker\u0026rsquo;s Intention)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003e\u003cstrong\u003ePerlocutionary Act (Effect on Listener)\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003e\u003cem\u003erunning out of fuel\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eStating current fuel status\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eWarning / alert\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eATC prioritizes emergency response or issues immediate clearance\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003e\u003cem\u003eyou dumping fuel?\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eAsking about current action\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eRequest for confirmation\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eListener confirms or updates status\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003e\u003cem\u003estart dumping fuel\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eCommand to begin dumping\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eDirective / order\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eFuel dump procedure initiated by crew\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003e\u003cem\u003efuel on board\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eReporting available fuel\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eInformational update\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eATC assesses situation, possibly requests more info\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003e\u003cem\u003ezero fuel weight\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eReporting weight without fuel\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eTechnical briefing / status report\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eUsed to calculate landing configuration\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003e\u003cem\u003eleaking fuel ignited\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eDescribing cause of fire\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eIncident explanation\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eTriggers emergency response, informs investigation\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003e\u003cem\u003eturn off all fuel valves\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eInstruction to shut fuel flow\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eDirective for safety\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eListener complies, preventing escalation\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003e\u003cem\u003ecan we dump fuel?\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eAsking for permission\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003ePolite request\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eATC approves or denies clearance\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003e\u003cem\u003elosing fuel like mad\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eReporting rapid fuel loss\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eAlarm / emergency alert\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eListener initiates troubleshooting or priority actions\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003e\u003cem\u003enumber of souls on board and your fuel\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eRequesting critical passenger/fuel data\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eEmergency coordination\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 150px;\"\u003e\n \u003cp\u003eSupports planning for evacuation, emergency landing, or rescue\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e\n\u003cp\u003e\u003cstrong\u003eSearle\u0026rsquo;s Speech Act Analysis\u0026nbsp;\u003c/strong\u003e\u003c/p\u003e\n\u003cp\u003eSearle\u0026rsquo;s theory of speech acts categorises communicative functions into five distinct roles. \u003cem\u003eAssertives\u003c/em\u003e express beliefs through verbs like state or claim, conveying information or describing conditions. \u003cem\u003eDirectives\u003c/em\u003e influence behaviour with verbs like request or command, common in instructions or appeals. \u003cem\u003eCommissives\u0026nbsp;\u003c/em\u003ecommit speakers to future actions with verbs like promise or volunteer, indicating intention or obligation. \u003cem\u003eExpressive\u0026nbsp;\u003c/em\u003ereflects psychological states or emotional reactions with verbs like thank or congratulate. \u003cem\u003eDeclarations\u0026nbsp;\u003c/em\u003echange the external world with verbs like resign or declare emergency. In high-stakes domains like aviation, understanding these categories ensures clear intentions and accurate communication. \u003cstrong\u003eTable 9.\u003c/strong\u003e shows a sample of Searle\u0026rsquo;s model pragmatic analysis that can contribute to Aviation English material design.\u0026nbsp;\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eTable 9\u003c/strong\u003e\u003cstrong\u003e.\u0026nbsp;\u003c/strong\u003eSample Searle\u0026rsquo;s Speech Act Analysis\u003c/p\u003e\n\u003ctable border=\"1\" cellspacing=\"0\" cellpadding=\"0\" class=\"fr-table-selection-hover\"\u003e\n \u003ctbody\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 200px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eLexical Bundle\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 83px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eSpeech Act Type\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 318px;\"\u003e\n \u003cp\u003e\u003cstrong\u003eCommunicative Function / Explanation\u003c/strong\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 200px;\"\u003e\n \u003cp\u003e\u003cem\u003erunning out of fuel\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 83px;\"\u003e\n \u003cp\u003eAssertive\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 318px;\"\u003e\n \u003cp\u003eStates a fact about fuel status; alerts listener to the developing critical condition.\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 200px;\"\u003e\n \u003cp\u003e\u003cem\u003eyou dumping fuel?\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 83px;\"\u003e\n \u003cp\u003eDirective\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 318px;\"\u003e\n \u003cp\u003eSeeks confirmation of an ongoing or planned action; checks alignment or coordination.\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 200px;\"\u003e\n \u003cp\u003e\u003cem\u003estart dumping fuel\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 83px;\"\u003e\n \u003cp\u003eDirective\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 318px;\"\u003e\n \u003cp\u003eA command given under time pressure initiates an immediate safety-related action.\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 200px;\"\u003e\n \u003cp\u003e\u003cem\u003efuel on board\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 83px;\"\u003e\n \u003cp\u003eAssertive\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 318px;\"\u003e\n \u003cp\u003eReports a factual measurement; typically used for operational decisions.\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 200px;\"\u003e\n \u003cp\u003e\u003cem\u003ezero fuel weight\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 83px;\"\u003e\n \u003cp\u003eAssertive\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 318px;\"\u003e\n \u003cp\u003eProvides calculated aircraft data used for load or landing calculations.\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 200px;\"\u003e\n \u003cp\u003e\u003cem\u003eleaking fuel ignited\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 83px;\"\u003e\n \u003cp\u003eAssertive\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 318px;\"\u003e\n \u003cp\u003eDescribes a factual event in the incident sequence; often post-event reporting.\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 200px;\"\u003e\n \u003cp\u003e\u003cem\u003eturn off all fuel valves\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 83px;\"\u003e\n \u003cp\u003eDirective\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 318px;\"\u003e\n \u003cp\u003eDirects safety-critical action to prevent escalation (fire/explosion).\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 200px;\"\u003e\n \u003cp\u003e\u003cem\u003ecan we dump fuel?\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 83px;\"\u003e\n \u003cp\u003eDirective\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 318px;\"\u003e\n \u003cp\u003eA polite request seeking ATC clearance to take a procedural action.\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 200px;\"\u003e\n \u003cp\u003e\u003cem\u003elosing fuel like mad\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 83px;\"\u003e\n \u003cp\u003eAssertive\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 318px;\"\u003e\n \u003cp\u003eA more urgent, emotionally charged assertion of fuel loss to escalate response.\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003ctr\u003e\n \u003ctd valign=\"top\" style=\"width: 200px;\"\u003e\n \u003cp\u003e\u003cem\u003enumber of souls on board and your fuel\u003c/em\u003e\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 83px;\"\u003e\n \u003cp\u003eDirective\u003c/p\u003e\n \u003c/td\u003e\n \u003ctd valign=\"top\" style=\"width: 318px;\"\u003e\n \u003cp\u003eRequesting critical information for emergency coordination (e.g., rescue planning).\u003c/p\u003e\n \u003c/td\u003e\n \u003c/tr\u003e\n \u003c/tbody\u003e\n\u003c/table\u003e"},{"header":"Discussion","content":"\u003cp\u003eThis study examined how AI-driven concordance tools can identify syntactic patterns in specialized aviation discourse, focusing on emergency communications involving fuel-related scenarios, and how these patterns can inform ICAO-compliant training materials. Analysis revealed that real-world aviation emergency communication is characterized by specific, functionally significant syntactic features: modal verbs for necessity and permission, imperatives for urgent directives, elliptical forms for speed and conciseness, repetition to ensure clarity, and technical noun phrases conveying precise operational meaning. Each pattern reflects the cognitive and procedural demands of high-stakes exchanges.\u003c/p\u003e \u003cp\u003eThe use of AI-driven tools\u0026mdash;validated by a Jaccard Similarity Index of 0.917 between AI-generated and manually extracted bundles\u0026mdash;demonstrated methodological reliability. This aligns with corpus-based ESP research (e.g., Pacheco et al., \u003cspan citationid=\"CR43\" class=\"CitationRef\"\u003e2023\u003c/span\u003e; Friginal \u0026amp; Cox, \u003cspan citationid=\"CR21\" class=\"CitationRef\"\u003e2025\u003c/span\u003e) showing that AI-enhanced tools such as #LancsBox integrated with ChatGPT can uncover linguistic patterns with precision and scalability. Beyond replication of manual work, AI amplifies analysis by revealing form\u0026ndash;function mappings that are often overlooked, consistent with usage-based and constructivist views of language learning (P\u0026eacute;rez-Paredes \u0026amp; Boulton, \u003cspan citationid=\"CR45\" class=\"CitationRef\"\u003e2025\u003c/span\u003e). This provides a scalable pathway for generating pedagogically relevant content rooted in authentic communication.\u003c/p\u003e \u003cp\u003eDrawing on Biber\u0026rsquo;s register analysis and usage-based linguistic theories (Ellis \u0026amp; Wulff, \u003cspan citationid=\"CR18\" class=\"CitationRef\"\u003e2020\u003c/span\u003e; Pemberton, \u003cspan citationid=\"CR44\" class=\"CitationRef\"\u003e2024\u003c/span\u003e; Tyler, \u003cspan citationid=\"CR57\" class=\"CitationRef\"\u003e2010\u003c/span\u003e), the study reinforces that language use is patterned according to context and purpose. Imperatives and modals embody the need for unambiguous authority in cockpit\u0026ndash;controller exchanges, while ellipsis and lexical compression facilitate rapid yet precise communication. These are not stylistic choices but operational necessities for safety and efficiency. By integrating Austin\u0026rsquo;s (\u003cspan citationid=\"CR5\" class=\"CitationRef\"\u003e1962\u003c/span\u003e) and Searle\u0026rsquo;s (\u003cspan citationid=\"CR47\" class=\"CitationRef\"\u003e1969\u003c/span\u003e, 1976) speech act theories, the study moves beyond structural description to explain communicative functions. For example, the lexical bundle \u003cem\u003estart dumping fuel\u003c/em\u003e acts as a \u003cem\u003edirective\u003c/em\u003e with immediate illocutionary force and perlocutionary effect, prompting procedural action. This discourse\u0026ndash;pragmatic approach bridges structural form and operational significance, offering a more complete understanding of how syntax functions in crisis communication.\u003c/p\u003e \u003cp\u003eEmbedding corpus-derived syntactic bundles into training materials can create realistic, context-sensitive resources that mirror actual cockpit and ATC exchanges. This goes beyond rote phrase memorization, helping learners develop pragmatic flexibility and situational awareness for non-routine scenarios. Speech act analysis strengthens this approach by focusing training on intentional language use, aligning with ICAO descriptors for Interaction and Structure. Corpus findings also provide a foundation for performance-based assessments, ensuring that evaluation criteria reflect operational demands.\u003c/p\u003e \u003cp\u003eEqually noteworthy is a contribution of the study to operational safety. The potential to incorporate syntactic pattern or lexical bundles recognition into similar models, such as the \u003cem\u003ecivil aviation safety risk intelligent early warning model\u003c/em\u003e developed by Hou et al. (\u003cspan citationid=\"CR27\" class=\"CitationRef\"\u003e2023\u003c/span\u003e) is significant. AI-assisted communication monitoring systems represent a novel application of corpus linguistics in aviation risk management. These systems can identify anomalous deviations from normative patterns, thereby alerting crews or controllers to developing communication disruptions. This aligns with the current trend toward data-driven predictive safety frameworks, which prioritize prevention over reactive measures (Sun \u0026amp; Tang, \u003cspan citationid=\"CR50\" class=\"CitationRef\"\u003e2021\u003c/span\u003e). Ultimately, the discussion emphasizes that syntactic choices in aviation emergencies are not arbitrary but are shaped by functional, procedural, and safety considerations. By illuminating these patterns through a combined lens of corpus analysis and speech act theory, the study underscores the value of linguistically informed, domain-specific training approaches in high-stakes communication domains.\u003c/p\u003e \u003cdiv id=\"Sec19\" class=\"Section2\"\u003e \u003ch2\u003eImplication of Syntactic Pattern Analysis\u003c/h2\u003e \u003cp\u003eThe recurrent structures identified\u0026mdash;imperatives, modals, urgent interrogatives\u0026mdash;mirror authentic emergency speech. For example, \u003cem\u003eWe\u0026rsquo;re running out of fuel\u003c/em\u003e reports status, while \u003cem\u003eStart dumping fuel\u003c/em\u003e issues a time-critical instruction. Integrating such data into scenario-based training prepares learners for the urgency and clarity required under stress. Exposure to authentic elliptical and repetitive structures builds awareness of how meaning is maintained despite compressed syntax.\u003c/p\u003e \u003cp\u003eTools like #LancsBox facilitate comparison between authentic and textbook language, enabling grammar-awareness tasks that support ICAO level calibration. Realistic assessment tasks can measure the ability to use appropriate syntactic forms under operational pressure. Table\u0026nbsp;\u003cspan refid=\"Tab10\" class=\"InternalRef\"\u003e10\u003c/span\u003e. in the original text outlines how training and assessment can target functional language practice, grammar awareness, communication strategies, and data-driven language insights.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab10\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 10\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eTraining and Assessment Framework\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"4\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c4\" colnum=\"4\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eArea of Application\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eKey Syntactic Features\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eApplication in Training Materials\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c4\"\u003e \u003cp\u003eAssessment Alignment\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eTargeted Functional Language Practice\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eImperatives (Start dumping fuel), Modals (Can we dump fuel?), Questions (Do we have enough fuel?)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eScenario-based dialogues and simulated ATC exchanges focusing on specific communicative functions in fuel emergencies.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eAssess learners\u0026rsquo; ability to use appropriate syntactic forms for different communicative functions in emergency scenarios.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eICAO Level Calibration through Grammar Awareness\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eModal verbs (necessity, possibility), Ellipsis (information omission), Imperatives (ATC commands)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eActivities distinguishing between ICAO Level 3 and Level 4\u0026thinsp;+\u0026thinsp;usage, practicing controlled and free production of appropriate structures.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eEvaluate learners\u0026rsquo; grammatical accuracy and appropriateness in using modal verbs, ellipsis, and imperatives according to ICAO standards.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eCommunication Strategy Training\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eRepetition (Fuel dump. Now.), Fragmentation (Fuel\u0026hellip;low)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eExercises teaching discourse management strategies for clarity and intelligibility in emergency communication.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eAssess learners\u0026rsquo; ability to use communication strategies effectively while maintaining clarity and intelligibility in emergency situations.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eData-Driven Language Awareness\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eHigh-frequency collocations (fuel flow), Syntactic variation (you dumping fuel?)\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eConcordance line analysis and pattern-matching exercises raising awareness of real-world syntactic patterns.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eEvaluate learners\u0026rsquo; awareness and use of high-frequency collocations and syntactic variation in emergency communication.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAssessment \u0026amp; Remediation Alignment\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eAll syntactic features extracted from the corpus\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eRubric-aligned assessment prompts targeting the production and comprehension of specific syntactic features.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c4\"\u003e \u003cp\u003eProvide feedback referencing specific grammar categories related to the use of syntactic features in emergency communication.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003cp\u003eFrom a training perspective, such integration aligns with task-based and case-based learning (Bui, \u003cspan citationid=\"CR12\" class=\"CitationRef\"\u003e2025\u003c/span\u003e; Ellis, \u003cspan citationid=\"CR17\" class=\"CitationRef\"\u003e2017\u003c/span\u003e; Golaghaie et al., \u003cspan citationid=\"CR24\" class=\"CitationRef\"\u003e2019\u003c/span\u003e). Trainees gain sensitivity to pragmatic norms and cues in degraded communication environments. For assessment, these patterns can serve as empirical benchmarks for fluency, coherence, and clarity, moving language testing toward performance-based validity (Douglas, \u003cspan citationid=\"CR15\" class=\"CitationRef\"\u003e2014\u003c/span\u003e).\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec20\" class=\"Section2\"\u003e \u003ch2\u003eImplication of Austin\u0026rsquo;s Speech Act Analysis\u003c/h2\u003e \u003cp\u003eIncorporating Austin\u0026rsquo;s model into aviation English design shifts the focus from form alone to communicative intent. Learners should practice recognizing illocutionary force\u0026mdash;whether an utterance is a \u003cem\u003erequest\u003c/em\u003e, \u003cem\u003edirective\u003c/em\u003e, or \u003cem\u003ereport\u003c/em\u003e\u0026mdash;and anticipate perlocutionary effects on listeners. Authentic corpus samples, such as \u003cem\u003eCan we dump fuel?\u003c/em\u003e can be classified by function, helping learners connect form to purpose.\u003c/p\u003e \u003cp\u003eRole-plays and scenario tasks grounded in real ATC\u0026ndash;cockpit transcripts train learners to produce language that achieves desired operational outcomes. Practicing frequent lexical bundles (\u003cem\u003erunning out of fuel\u003c/em\u003e, \u003cem\u003ewe need priority\u003c/em\u003e) in context enhances automaticity. Material design must also account for context-dependent multifunctionality, where the same phrase can perform different speech acts. This approach supports ICAO descriptors for Structure and Interactions, ensuring that communicative competence includes accuracy, clarity, and operational effectiveness.\u003c/p\u003e \u003c/div\u003e \u003cdiv id=\"Sec21\" class=\"Section2\"\u003e \u003ch2\u003eImplication of Searle\u0026rsquo;s Speech Act Analysis\u003c/h2\u003e \u003cp\u003eApplying Searle\u0026rsquo;s categories\u0026mdash;\u003cem\u003eassertives, directives, commissives, expressives, declarations\u003c/em\u003e\u0026mdash;further refines training by emphasizing functional language use aligned with ICAO LPRs. In emergencies, directives (e.g., \u003cem\u003eStart dumping fuel\u003c/em\u003e), assertives (e.g., reporting fuel status), and declarations (e.g., \u003cem\u003eMayday\u003c/em\u003e) are operationally critical. Scenario-based simulations can target each category: directives in time-critical instruction drills, assertives in factual reporting under pressure, and declarations in decision-making exercises.\u003c/p\u003e \u003cp\u003eSearle\u0026rsquo;s framework also bridges standard ICAO phraseology and real-life variation. While fixed phrases promote clarity, authentic emergencies require pragmatic flexibility. Contrasting standardized and naturally occurring utterances helps learners decide when adaptation is necessary. This dual awareness reinforces ICAO descriptors for Function, Structure, Vocabulary, and Interactions. Table\u0026nbsp;\u003cspan refid=\"Tab11\" class=\"InternalRef\"\u003e11\u003c/span\u003e. illustrates a material design framework based on Searle\u0026rsquo;s Speech act theory.\u003c/p\u003e \u003cp\u003e \u003cdiv class=\"gridtable\"\u003e\u003ctable float=\"Yes\" id=\"Tab11\" border=\"1\"\u003e \u003ccaption language=\"En\"\u003e \u003cdiv class=\"CaptionNumber\"\u003eTable 11\u003c/div\u003e \u003cdiv class=\"CaptionContent\"\u003e \u003cp\u003eFramework of Aviation English Material Design Based on Searle\u0026rsquo;s Speech Act Theory\u003c/p\u003e \u003c/div\u003e \u003c/caption\u003e \u003ccolgroup cols=\"3\"\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c1\" colnum=\"1\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c2\" colnum=\"2\"\u003e\u003c/div\u003e \u003cdiv align=\"left\" class=\"colspec\" colname=\"c3\" colnum=\"3\"\u003e\u003c/div\u003e \u003cthead\u003e \u003ctr\u003e \u003cth align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFocus Area\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c2\"\u003e \u003cp\u003eImplication for Material Design\u003c/p\u003e \u003c/th\u003e \u003cth align=\"left\" colname=\"c3\"\u003e \u003cp\u003eSuggested Activity / Design Idea\u003c/p\u003e \u003c/th\u003e \u003c/tr\u003e \u003c/thead\u003e \u003ctbody\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eFunction-Focused Communication Training\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eEmphasize communicative functions by teaching learners to identify and use assertives, directives, commissives, expressives, and declarations.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eInclude classification tasks where learners identify the speech act category of given utterances.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eRealistic Scenario-Based Learning\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eUse each speech act category in realistic scenarios that simulate ATC or cockpit environments to enhance functional language use.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eDevelop scripted role-plays and branching dialogues based on speech act functions.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003ePrioritizing High-Stakes Speech Acts\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eHighlight directives, assertives, and declarations due to their critical role in aviation emergencies and operational clarity.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eBuild targeted drills using lexical bundles from incident corpora to practice warning, alerting, and instructing.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eDeveloping Perlocutionary Awareness\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eHelp learners anticipate how their words will be interpreted and what actions will result, increasing communicative effectiveness.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eUse \u0026ldquo;What will happen next?\u0026rdquo; prediction tasks based on ATC or cockpit dialogues.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eBridging Standard Phraseology and Natural Speech\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eTeach students when to use ICAO phraseology and when natural speech is appropriate, especially in non-routine situations.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eContrast ICAO-standard phrases with corpus-derived utterances to foster pragmatic flexibility.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003ctr\u003e \u003ctd align=\"left\" colname=\"c1\"\u003e \u003cp\u003eAligning with ICAO Descriptors\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c2\"\u003e \u003cp\u003eMap speech act functions to ICAO descriptors like Function, Structure, Vocabulary, and Interactions for focused skills development.\u003c/p\u003e \u003c/td\u003e \u003ctd align=\"left\" colname=\"c3\"\u003e \u003cp\u003eCreate ICAO assessment-style tasks requiring appropriate speech act use in simulated non-routine situations.\u003c/p\u003e \u003c/td\u003e \u003c/tr\u003e \u003c/tbody\u003e \u003c/colgroup\u003e \u003c/table\u003e\u003c/div\u003e \u003c/p\u003e \u003c/div\u003e"},{"header":"Conclusion","content":"\u003cp\u003eThis study provides a comprehensive analysis of syntactic patterns in aviation emergency communication by employing AI-driven concordance techniques on a specialized corpus of pilot-ATC exchanges. Drawing on corpus linguistics and speech act theory, the research successfully identified and categorized recurrent lexical bundles\u0026mdash;including imperatives, modals, interrogatives, elliptical forms, and noun phrases\u0026mdash;that are functionally critical during high-stakes fuel-related emergencies. These patterns were systematically mapped to language functions such as status reporting, alerting, instructing, and requesting, and were subsequently interpreted through the perspectives of Austin's and Searle's speech act models. The findings demonstrate that in real-world crises, syntactic form is closely associated with communicative intent and operational effectiveness. By translating these syntactic insights into pedagogical strategies\u0026mdash;such as task-based drills, ICAO-aligned assessments, and scenario-based learning\u0026mdash;the study illustrates the potential of corpus-informed design to enhance the communicative readiness of aviation personnel.\u003c/p\u003e \u003cp\u003eDespite its practical significance, the research acknowledges several limitations. First, while the corpus was specialized and authentic, it was limited in size and scope, focusing primarily on fuel-related emergencies. This potentially narrows the generalizability of findings to other types of emergency discourse, such as medical, weather, or technical failures. Furthermore, the reliance on a pre-compiled, static corpus may not fully capture the dynamic and evolving nature of real-time pilot-ATC communication across various contexts, regions, or aircraft types. Second, although AI tools like #LancsBox facilitated efficient pattern mining, full semantic and pragmatic interpretation still required human expertise, posing a challenge for full automation. Additionally, the study relied on existing transcript data, which may lack prosodic or multimodal cues present in live communication. These limitations suggest the need for broader and multimodal corpora, as well as a deeper integration of AI with expert-validated annotations. The study did not include empirical validation through classroom implementation or pilot testing of instructional materials based on the extracted patterns. As such, the pedagogical effectiveness of using these patterns in real-world training or assessment contexts remains unverified and warrants further applied research. Nonetheless, from the perspective of air traffic controllers and pilot instructors, the potential pedagogical value derived from the data set is commendable\u003c/p\u003e \u003cp\u003eFuture research should expand beyond a single emergency theme and incorporate a wider variety of scenarios\u0026mdash;such as medical diversions, engine failure, or weather-related incidents\u0026mdash;to build a more holistic model of emergency discourse. Moreover, the potential of real-time AI monitoring tools should be explored for in-flight communication analysis and predictive safety interventions. Further validation of syntactic features through pilot studies and learner assessments can also strengthen the pedagogical impact of corpus-driven materials. Lastly, interdisciplinary collaboration across aviation linguists, AI developers, and safety experts will be essential to translate linguistic insights into scalable, adaptive, and operationally meaningful training and assessment systems.\u003c/p\u003e"},{"header":"Declarations","content":"\u003ch2\u003eAuthor Contribution\u003c/h2\u003e\u003cp\u003eDSN was responsible for the conceptualisation of the study, the development of the research methodology, the use of software tools for data analysis, and the writing of the original draft of the manuscript.EUH contributed to the proofreading of the manuscript and participated in the critical review of its content to improve clarity and coherence.RD was involved in the validation of the research findings and provided scholarly review to ensure the rigor and accuracy of the study.II supervised the research process and offered academic guidance throughout the development of the study.\u003c/p\u003e\u003ch2\u003eAcknowledgement\u003c/h2\u003e\u003cp\u003eIn the preparation of this manuscript, we utilised ChatGPT (GPT-3.5 and 4) to enhance the clarity and coherence of the language, ensuring its adherence to the standards expected in scholarly publications. While ChatGPT contributed to the refinement of the language, it did not generate any original ideas. The authors alone are responsible for any inaccuracies present in the manuscript\u003c/p\u003e\u003ch2\u003eData Availability\u003c/h2\u003e\u003cp\u003eData Sharing Statement. Transcripts were obtained from publicly available resources https://www.planecrashinfo.com/lastwords.htm\u003c/p\u003e\n\u003cp\u003e\u003cstrong\u003eEthical Standard.\u003c/strong\u003e The authors assert that all procedures contributing to this work comply with the ethical standards of the relevant national and institutional committees on human experimentation and with the Helsinki Declaration of 1975, as revised in 2008.\u0026nbsp;\u003c/p\u003e"},{"header":"References","content":"\u003col\u003e\n\u003cli\u003eAlasmary, A. (2024). Sustaining vocabulary knowledge growth through corpus-generated lists of lexical bundles and keywords in the law of contracts. \u003cem\u003eHeliyon\u003c/em\u003e, \u003cem\u003e10\u003c/em\u003e(9), e29944. https://doi.org/10.1016/J.HELIYON.2024.E29944\u003c/li\u003e\n\u003cli\u003eAlderson, J. C. (2009). Air Safety, Language Assessment Policy, and Policy Implementation: The Case of Aviation English . \u003cem\u003eAnnual Review of Applied Linguistics\u003c/em\u003e, \u003cem\u003e29\u003c/em\u003e, 168\u0026ndash;187. https://doi.org/10.1017/S0267190509090138\u003c/li\u003e\n\u003cli\u003eAnthony, L. (2024). \u003cem\u003eAn introduction to corpus building, corpus analysis, and AI-supported language pattern discovery\u003c/em\u003e (12761885). Art. 12761885. https://doi.org/none\u003c/li\u003e\n\u003cli\u003eAssassi, T. (2025). ESP practitioners\u0026rsquo; perspectives on the efficiency of using artificial intelligence \u0026lsquo;ChatGPT\u0026rsquo; in needs analysis. \u003cem\u003eComputer Assisted Language Learning\u003c/em\u003e, 1\u0026ndash;32. https://doi.org/10.1080/09588221.2024.2428943\u003c/li\u003e\n\u003cli\u003eAustin, J. L. (1962). \u003cem\u003eHow to Do Things with Words\u003c/em\u003e (J. O. Urmson \u0026amp; M. Sbisa, Eds.; 2nd ed.). Harvard University Press.\u003c/li\u003e\n\u003cli\u003eBarshi, I., \u0026amp; Farris, C. (2016). \u003cem\u003eMisunderstandings in ATC Communication: Language, Cognition, and Experimental Methodology\u003c/em\u003e. Routledge. https://doi.org/https://doi.org/10.4324/9781315595641\u003c/li\u003e\n\u003cli\u003eBayaga, A. (2025). Leveraging AI-enhanced and emerging technologies for pedagogical innovations in higher education. \u003cem\u003eEducation and Information Technologies\u003c/em\u003e, \u003cem\u003e30\u003c/em\u003e(1), 1045\u0026ndash;1072. https://doi.org/10.1007/s10639-024-13122-y\u003c/li\u003e\n\u003cli\u003eBiber, D., \u0026amp; Reppen, R. (2015). The Cambridge handbook of English corpus linguistics. In \u003cem\u003eThe Cambridge Handbook of English Corpus Linguistics\u003c/em\u003e. Cambridge University Press. https://doi.org/10.1007/9781139764377\u003c/li\u003e\n\u003cli\u003eBonnefon, J.-F., Feeney, A., \u0026amp; De Neys, W. (2011). The Risk of Polite Misunderstandings. \u003cem\u003eCurrent Directions in Psychological Science\u003c/em\u003e, \u003cem\u003e20\u003c/em\u003e(5), 321\u0026ndash;324. https://doi.org/10.1177/0963721411418472\u003c/li\u003e\n\u003cli\u003eBoux, I., Tomasello, R., Grisoni, L., \u0026amp; Pulverm\u0026uuml;ller, F. (2021). Brain signatures predict communicative function of speech production in interaction. \u003cem\u003eCortex\u003c/em\u003e, \u003cem\u003e135\u003c/em\u003e, 127\u0026ndash;145. https://doi.org/10.1016/J.CORTEX.2020.11.008\u003c/li\u003e\n\u003cli\u003eBrezina, V. (2025). Corpus linguistics and AI: #LancsBox X in the context of emerging technologies. \u003cem\u003eInternational Journal of Language Studies\u003c/em\u003e, \u003cem\u003e19\u003c/em\u003e(2), 75\u0026ndash;90.\u003c/li\u003e\n\u003cli\u003eBui, G. (2025). Task-Based Language Teaching. In \u003cem\u003eReference Module in Social Sciences\u003c/em\u003e. Elsevier. https://doi.org/10.1016/B978-0-323-95504-1.00434-8\u003c/li\u003e\n\u003cli\u003eCurry, N., \u0026amp; McEnery, T. (2025). Corpus linguistics for language teaching and learning: A research agenda. \u003cem\u003eLanguage Teaching\u003c/em\u003e, 1\u0026ndash;20. https://doi.org/10.1017/S0261444824000430\u003c/li\u003e\n\u003cli\u003eDoc 9835, Pub. L. No. Doc 9835 Manual on the Implementation of ICAO Language Proficiency Requirements, Manual (2010). https://skybrary.aero/sites/default/files/bookshelf/2497.pdf\u003c/li\u003e\n\u003cli\u003eDouglas, D. (2014). Nobody seems to speak English here today: Enhancing assessment and training in aviation English. \u003cem\u003eIranian Journal of Language Teaching Research\u003c/em\u003e, \u003cem\u003e2\u003c/em\u003e(2), 1\u0026ndash;12. https://doi.org/10.30466/ijltr.2014.20410\u003c/li\u003e\n\u003cli\u003eEgorova, N., Shtyrov, Y., \u0026amp; Pulverm\u0026uuml;ller, F. (2016). Brain basis of communicative actions in language. \u003cem\u003eNeuroImage\u003c/em\u003e, \u003cem\u003e125\u003c/em\u003e, 857\u0026ndash;867. https://doi.org/10.1016/j.neuroimage.2015.10.055\u003c/li\u003e\n\u003cli\u003eEllis, R. (2017). Task-Based Language Teaching. In S. Loewen \u0026amp; M. Sato (Eds.), \u003cem\u003eThe Routledge Handbook of Instructed Second Language Acquisition\u003c/em\u003e (pp. 108\u0026ndash;126). Routledge Taylor \u0026amp; Francis Group. https://doi.org/https://doi.org/10.4324/9781315676968\u003c/li\u003e\n\u003cli\u003eEllis, \u0026amp; Wulff, S. (2020). Usage-Based Approaches to L2 Acquisition. In B. VanPatten, G. D. Keating, \u0026amp; S. Wulff (Eds.), \u003cem\u003eTheories in Second Language Acquisition\u003c/em\u003e (pp. 63\u0026ndash;82). Routledge. https://doi.org/https://doi.org/10.4324/9780429503986\u003c/li\u003e\n\u003cli\u003eEstival, D., \u0026amp; Molesworth, B. R. C. (2020). Errors in air-ground pilot communication: an experimental study. \u003cem\u003eThe ESPecialist\u003c/em\u003e, \u003cem\u003e41\u003c/em\u003e(3). https://doi.org/10.23925/2318-7115.2020v41i3a5\u003c/li\u003e\n\u003cli\u003eFleckenstein, J., Meyer, J., Jansen, T., Keller, S. D., K\u0026ouml;ller, O., \u0026amp; M\u0026ouml;ller, J. (2024). Do teachers spot AI? Evaluating the detectability of AI-generated texts among student essays. \u003cem\u003eComputers and Education: Artificial Intelligence\u003c/em\u003e, \u003cem\u003e6\u003c/em\u003e, 100209. https://doi.org/10.1016/j.caeai.2024.100209\u003c/li\u003e\n\u003cli\u003eFriginal, E., \u0026amp; Cox, A. (2025). Corpus Linguistics and English for Specific Purposes. \u003cem\u003eReference Module in Social Sciences\u003c/em\u003e. https://doi.org/10.1016/B978-0-323-95504-1.00481-6\u003c/li\u003e\n\u003cli\u003eFriginal, E., \u0026amp; Roberts, J. (2020). English in Global Aviation. \u003cem\u003eEnglish in Global Aviation\u003c/em\u003e. https://doi.org/10.5040/9781350059344\u003c/li\u003e\n\u003cli\u003eGarcia, A. C. (2016). Air traffic communications in routine and emergency contexts: A case study of Flight 1549 \u0026lsquo;miracle on the Hudson.\u0026rsquo; \u003cem\u003eJournal of Pragmatics\u003c/em\u003e, \u003cem\u003e106\u003c/em\u003e, 57\u0026ndash;71. https://doi.org/10.1016/j.pragma.2016.10.005\u003c/li\u003e\n\u003cli\u003eGolaghaie, F., Asgari, S., Khosravi, S., Ebrahimimonfared, M., Mohtarami, A., \u0026amp; Rafiei, F. (2019). Integrating case-based learning with collective reflection: outcomes of inter-professional continuing education. \u003cem\u003eReflective Practice\u003c/em\u003e, \u003cem\u003e20\u003c/em\u003e(1), 42\u0026ndash;55. https://doi.org/10.1080/14623943.2018.1539660\u003c/li\u003e\n\u003cli\u003eHaddington, P., \u0026amp; Stokoe, E. (2023). Social interaction in high stakes crisis communication. \u003cem\u003eJournal of Pragmatics\u003c/em\u003e, \u003cem\u003e208\u003c/em\u003e, 91\u0026ndash;98. https://doi.org/10.1016/j.pragma.2023.02.014\u003c/li\u003e\n\u003cli\u003eHoltgraves, T. (2024). Emoji, Speech Acts, and Perceived Communicative Success. \u003cem\u003eJournal of Language and Social Psychology\u003c/em\u003e, \u003cem\u003e43\u003c/em\u003e(1), 83\u0026ndash;103. https://doi.org/https://doi.org/10.1177/0261927X231200450\u003c/li\u003e\n\u003cli\u003eHou, Z., Xiong, M., Wang, H., Lv, S., \u0026amp; Chen, L. (2023). Civil aviation safety risk intelligent early warning model based on text mining and multi-model fusion. \u003cem\u003eProceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering\u003c/em\u003e, \u003cem\u003e237\u003c/em\u003e(10), 2402\u0026ndash;2427. https://doi.org/10.1177/09544100231153298;CTYPE:STRING:JOURNAL\u003c/li\u003e\n\u003cli\u003eKala\u0026scaron;, F. (2025). \u003cem\u003eBridging Tradition and Innovation: Analysing Language Data with Chatgpt-4 in Corpus Linguistics\u003c/em\u003e. https://doi.org/10.2139/SSRN.5126316\u003c/li\u003e\n\u003cli\u003eKale, U., Herrera, M., \u0026amp; Nagy, A. (2021). Examining pragmatic failure and other language-related risks in global aviation. \u003cem\u003eAircraft Engineering and Aerospace Technology\u003c/em\u003e, \u003cem\u003e93\u003c/em\u003e(8), 1313\u0026ndash;1322. https://doi.org/10.1108/AEAT-03-2021-0081\u003c/li\u003e\n\u003cli\u003eKim, H. (2018). What constitutes professional communication in aviation: Is language proficiency enough for testing purposes? \u003cem\u003eLanguage Testing\u003c/em\u003e, \u003cem\u003e35\u003c/em\u003e(3), 403\u0026ndash;426.\u003c/li\u003e\n\u003cli\u003eKryszkiewicz, M. (2024). A New Approach to Deriving Jaccard Similarity and Jaccard Distance Properties with and without Considering Feature Weights. \u003cem\u003eCommunications in Computer and Information Science\u003c/em\u003e, \u003cem\u003e2145 CCIS\u003c/em\u003e, 341\u0026ndash;349. https://doi.org/10.1007/978-981-97-5934-7_29\u003c/li\u003e\n\u003cli\u003eKwakye, A. D., Jennions, I. K., \u0026amp; Ezhilarasu, C. M. (2024). Platform health management for aircraft maintenance \u0026ndash; a review. \u003cem\u003eProceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering\u003c/em\u003e, \u003cem\u003e238\u003c/em\u003e(3), 267\u0026ndash;283.\u003c/li\u003e\n\u003cli\u003eLin, M. H. (2021). Effects of Data-Driven Learning on College Students of Different Grammar Proficiencies: A Preliminary Empirical Assessment in EFL Classes. \u003cem\u003eSAGE Open\u003c/em\u003e, \u003cem\u003e11\u003c/em\u003e(3), 1\u0026ndash;15. https://doi.org/10.1177/21582440211029936\u003c/li\u003e\n\u003cli\u003eLiu, H., Macwhinney, B., Fromm, D., \u0026amp; Lanzi, A. (2023). Automation of Language Sample Analysis. \u003cem\u003eJournal of Speech, Language, and Hearing Research\u003c/em\u003e, \u003cem\u003e66\u003c/em\u003e(7), 2421\u0026ndash;2433. https://doi.org/10.1044/2023_JSLHR-22-00642,\u003c/li\u003e\n\u003cli\u003eLiu, X. J., Wang, J., \u0026amp; Zou, B. (2025). Evaluating an AI speaking assessment tool: Score accuracy, perceived validity, and oral peer feedback as feedback enhancement. \u003cem\u003eJournal of English for Academic Purposes\u003c/em\u003e, \u003cem\u003e75\u003c/em\u003e, 101505. https://doi.org/10.1016/j.jeap.2025.101505\u003c/li\u003e\n\u003cli\u003eMarcet, E. (2024). Teaching pragmatics to instructors of L2 Japanese: A relevance-theoretic approach. \u003cem\u003eSystem\u003c/em\u003e, \u003cem\u003e126\u003c/em\u003e, 103472. https://doi.org/10.1016/J.SYSTEM.2024.103472\u003c/li\u003e\n\u003cli\u003eMcEnery, T., \u0026amp; Hardie, A. (2012). Corpus linguistics: Method, theory and practice. In \u003cem\u003eCorpus Linguistics: Method, Theory and Practice\u003c/em\u003e. Cambridge University Press. https://doi.org/10.1017/CBO9780511981395\u003c/li\u003e\n\u003cli\u003eMeihami, H., \u0026amp; Khanlarzadeh, M. (2015). Pragmatic Content in Global and Local ELT Textbooks. \u003cem\u003eSage Open\u003c/em\u003e, \u003cem\u003e5\u003c/em\u003e(4). https://doi.org/10.1177/2158244015615168\u003c/li\u003e\n\u003cli\u003eMolesworth, B. R. C., \u0026amp; Estival, D. (2015). Miscommunication in general aviation: The influence of external factors on communication errors. \u003cem\u003eSafety Science\u003c/em\u003e, \u003cem\u003e73\u003c/em\u003e, 73\u0026ndash;79. https://doi.org/10.1016/j.ssci.2014.11.004\u003c/li\u003e\n\u003cli\u003eMurphy, A. (2001). The flight attendant dilemma: an analysis of communication and sensemaking during in-flight emergencies. \u003cem\u003eJournal of Applied Communication Research\u003c/em\u003e, \u003cem\u003e29\u003c/em\u003e(1), 30\u0026ndash;53. https://doi.org/10.1080/00909880128100\u003c/li\u003e\n\u003cli\u003eNoguera-D\u0026iacute;az, Y., \u0026amp; P\u0026eacute;rez-Paredes, P. (2019). Register analysis and ESP pedagogy: Noun-phrase modification in a corpus of English for military navy submariners. \u003cem\u003eEnglish for Specific Purposes\u003c/em\u003e, \u003cem\u003e53\u003c/em\u003e, 118\u0026ndash;130. https://doi.org/10.1016/J.ESP.2018.06.002\u003c/li\u003e\n\u003cli\u003eNugraha, D. S., Mayuni, I., \u0026amp; Anwar, M. (2023). Creating aviation English lesson: a corpus-informed material design. \u003cem\u003eJournal of Teaching English for Specific and Academic Purposes\u003c/em\u003e, \u003cem\u003e11\u003c/em\u003e(1), 23\u0026ndash;40. https://doi.org/DOI:10.22190/TESAP230131004N\u003c/li\u003e\n\u003cli\u003ePacheco, A., Garcia, A. C. de M., Monteiro, A. L. T., Prado, M. C. de A., \u0026amp; Tosqui-Lucks, P. (2023). Using corpus linguistics to create tasks for teaching and assessing Aeronautical English. \u003cem\u003eApplied Corpus Linguistics\u003c/em\u003e, \u003cem\u003e3\u003c/em\u003e(3), 100075. https://doi.org/10.1016/J.ACORP.2023.100075\u003c/li\u003e\n\u003cli\u003ePemberton, I. (2024). \u003cem\u003eUsage-Based Second Language Instruction\u003c/em\u003e. Springer Nature Switzerland. https://doi.org/10.1007/978-3-031-53414-0\u003c/li\u003e\n\u003cli\u003eP\u0026eacute;rez-Paredes, P., \u0026amp; Boulton, A. (2025). \u003cem\u003eData-driven Learning in and out of the Language Classroom\u003c/em\u003e. Cambridge University Press. https://doi.org/10.1017/9781009511384\u003c/li\u003e\n\u003cli\u003eSassen, C. (2005). \u003cem\u003eLinguistic Dimensions of Crisis Talk\u003c/em\u003e. John Benjamins Publishing Company.\u003c/li\u003e\n\u003cli\u003eSearle, J. R. (1969). \u003cem\u003eSpeech Acts\u003c/em\u003e. Cambridge University Press. https://doi.org/10.1017/CBO9781139173438\u003c/li\u003e\n\u003cli\u003eStaples, S. (2019). Using corpus-based discourse analysis for curriculum development: Creating and evaluating a pronunciation course for internationally educated nurses. \u003cem\u003eEnglish for Specific Purposes\u003c/em\u003e, \u003cem\u003e53\u003c/em\u003e, 13\u0026ndash;29. https://doi.org/10.1016/J.ESP.2018.08.005\u003c/li\u003e\n\u003cli\u003eStubbs, M. (2001). On inference theories and code theories: Corpus evidence for semantic schemas. \u003cem\u003eText - Interdisciplinary Journal for the Study of Discourse\u003c/em\u003e, \u003cem\u003e21\u003c/em\u003e(3). https://doi.org/10.1515/text.2001.007\u003c/li\u003e\n\u003cli\u003eSun, Z., \u0026amp; Tang, P. (2021). Automatic Communication Error Detection Using Speech Recognition and Linguistic Analysis for Proactive Control of Loss of Separation. \u003cem\u003eTransportation Research Record\u003c/em\u003e, \u003cem\u003e2675\u003c/em\u003e(5), 1\u0026ndash;12. https://doi.org/10.1177/0361198120983004\u003c/li\u003e\n\u003cli\u003eTarnavska, T., Baranovska, L., Glushanytsia, N., \u0026amp; Yahodzinskyi, S. (2021). The impact of psychological factor on the aircraft operation safety. \u003cem\u003eE3S Web of Conferences\u003c/em\u003e, \u003cem\u003e258\u003c/em\u003e, 02029. https://doi.org/10.1051/e3sconf/202125802029\u003c/li\u003e\n\u003cli\u003eThara, S., \u0026amp; Poornachandran, P. (2022). Social media text analytics of Malayalam\u0026ndash;English code-mixed using deep learning. \u003cem\u003eJournal of Big Data\u003c/em\u003e, \u003cem\u003e9\u003c/em\u003e(1), 1\u0026ndash;25. https://doi.org/10.1186/S40537-022-00594-3/TABLES/12\u003c/li\u003e\n\u003cli\u003eThorpe, A., Estival, D., Molesworth, B., \u0026amp; Eidels, A. (2022). Pilot errors: Communication comes last. \u003cem\u003eSafety Science\u003c/em\u003e, \u003cem\u003e149\u003c/em\u003e, 105686. https://doi.org/10.1016/j.ssci.2022.105686\u003c/li\u003e\n\u003cli\u003eTopping, K. J., Gehringer, E., Khosravi, H., Gudipati, S., Jadhav, K., \u0026amp; Susarla, S. (2025). Enhancing peer assessment with artificial intelligence. \u003cem\u003eInternational Journal of Educational Technology in Higher Education\u003c/em\u003e, \u003cem\u003e22\u003c/em\u003e(1), 3. https://doi.org/10.1186/s41239-024-00501-1\u003c/li\u003e\n\u003cli\u003eTosqui-Lucks, P., Prado, M. C. de A., Pacheco, A., Garcia, A. C. de M., \u0026amp; Monteiro, A. L. T. (2024). Challenges and possibilities in compiling Aeronautical English corpora: The case of the Aerocorpus. \u003cem\u003eResearch Methods in Applied Linguistics\u003c/em\u003e, \u003cem\u003e3\u003c/em\u003e(3), 100135. https://doi.org/10.1016/J.RMAL.2024.100135\u003c/li\u003e\n\u003cli\u003eTosqui-Lucks, P., \u0026amp; Silva, A. L. B. de C. e. (2020). Aeronautical English: Investigating the nature of this specific language in search of new heights. \u003cem\u003eThe ESPecialist\u003c/em\u003e, \u003cem\u003e41\u003c/em\u003e(3). https://doi.org/10.23925/2318-7115.2020v41i3a2\u003c/li\u003e\n\u003cli\u003eTyler, A. (2010). Usage-Based Approaches to Language and Their Applications to Second Language Learning. \u003cem\u003eAnnual Review of Applied Linguistics\u003c/em\u003e, \u003cem\u003e30\u003c/em\u003e, 270\u0026ndash;291. https://doi.org/10.1017/S0267190510000140\u003c/li\u003e\n\u003cli\u003eVerma, V., \u0026amp; Aggarwal, R. K. (2020). A comparative analysis of similarity measures akin to the Jaccard index in collaborative recommendations: empirical and theoretical perspective. \u003cem\u003eSocial Network Analysis and Mining\u003c/em\u003e, \u003cem\u003e10\u003c/em\u003e(1), 1\u0026ndash;16. https://doi.org/10.1007/S13278-020-00660-9/METRICS\u003c/li\u003e\n\u003cli\u003eWu, Q., Molesworth, B. R. C., \u0026amp; Estival, D. (2019). An Investigation into the Factors that Affect Miscommunication between Pilots and Air Traffic Controllers in Commercial Aviation. \u003cem\u003eInternational Journal of Aerospace Psychology\u003c/em\u003e, \u003cem\u003e29\u003c/em\u003e(1\u0026ndash;2), 53\u0026ndash;63. https://doi.org/10.1080/24721840.2019.1604138\u003c/li\u003e\n\u003cli\u003eYamada, N. K., \u0026amp; Halamek, L. P. (2014). Communication during resuscitation: Time for a change? \u003cem\u003eResuscitation\u003c/em\u003e, \u003cem\u003e85\u003c/em\u003e(12), e191\u0026ndash;e192. https://doi.org/10.1016/j.resuscitation.2014.08.034\u003c/li\u003e\n\u003cli\u003eYang, H.-H., Chang, Y.-H., \u0026amp; Chou, Y.-H. (2023). Subjective measures of communication errors between pilots and air traffic controllers. \u003cem\u003eJournal of Air Transport Management\u003c/em\u003e, \u003cem\u003e112\u003c/em\u003e, 102461. https://doi.org/10.1016/j.jairtraman.2023.102461\u003c/li\u003e\n\u003cli\u003eZhao, W. (2023). A corpus-based study on aviation English from the perspective of systemic functional linguistics. \u003cem\u003eDiscourse \u0026amp; Communication\u003c/em\u003e, \u003cem\u003e17\u003c/em\u003e(5), 630\u0026ndash;661. https://doi.org/10.1177/17504813231171644\u003c/li\u003e\n\u003cli\u003eZhao, W. (2024). A corpus-based multi-dimensional analysis of the linguistic features of Aviation English. \u003cem\u003eEnglish for Specific Purposes\u003c/em\u003e, \u003cem\u003e76\u003c/em\u003e, 57\u0026ndash;73. https://doi.org/10.1016/j.esp.2024.05.004\u003c/li\u003e\n\u003c/ol\u003e"}],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":true,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":true,"highlight":"","institution":"","isAcceptedByJournal":true,"isAuthorSuppliedPdf":false,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":false,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true},"keywords":"Aviation English, ChatGPT, Corpus, Lexical Bundles, Speech act","lastPublishedDoi":"10.21203/rs.3.rs-8373980/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-8373980/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eThis study examines how AI-driven concordance analysis can identify syntactic patterns in aviation emergency communication, with the goal of informing ICAO-aligned training materials. Routine aviation exchanges follow standard phraseology, but emergencies demand flexible, context-specific language. Miscommunication in such situations can compromise safety. Corpus linguistics and speech act theory provide complementary frameworks for understanding how pilots and air traffic controllers use language in crises. A specialized 14,000-word corpus of 83 authentic transcripts of related emergencies was compiled. #LancsBox V6.0 retrieved concordance lines, and ChatGPT generated lexical bundles, which were compared with manual extractions using the Jaccard Similarity Index. Lexical bundles were analyzed for syntactic patterns and communicative functions using Austin\u0026rsquo;s and Searle\u0026rsquo;s speech act models. The AI and manually generated bundle lists showed 91.7% similarity, confirming high reliability of AI assisted corpus analysis. Key syntactic features included imperatives, modal verbs, elliptical forms, and technical noun phrases, serving functions such as alerting, requesting, and instructing. Speech act analysis highlighted their operational significance. AI assisted corpus analysis effectively uncovers authentic linguistic patterns in aviation emergencies, enabling the design of scenario-based, ICAO-aligned training. Future work should expand to other emergency types, integrate multimodal data, and pilot-test materials to validate pedagogical impact.\u003c/p\u003e","manuscriptTitle":"From Corpus to Cockpit: Generating Emergency Lexical Bundles in Aviation Context","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-12-22 14:08:55","doi":"10.21203/rs.3.rs-8373980/v1","editorialEvents":[{"type":"communityComments","content":0}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"researchsquare","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":true,"externalIdentity":"","sideBox":"","snPcode":"","submissionUrl":"/submission","title":"Research Square","twitterHandle":"researchsquare","acdcEnabled":true,"dfaEnabled":false,"editorialSystem":"","reportingPortfolio":"","inReviewEnabled":false,"inReviewRevisionsEnabled":true}}],"origin":"","ownerIdentity":"8e5f5899-85e0-4a17-a186-8a5afc83b403","owner":[],"postedDate":"December 22nd, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"posted","subjectAreas":[],"tags":[],"updatedAt":"2026-03-23T16:06:28+00:00","versionOfRecord":{"articleIdentity":"rs-8373980","link":"https://doi.org/10.1007/s41701-026-00234-8","journal":{"identity":"corpus-pragmatics","isVorOnly":false,"title":"Corpus Pragmatics"},"publishedOn":"2026-03-17 15:59:33","publishedOnDateReadable":"March 17th, 2026"},"versionCreatedAt":"2025-12-22 14:08:55","video":"","vorDoi":"10.1007/s41701-026-00234-8","vorDoiUrl":"https://doi.org/10.1007/s41701-026-00234-8","workflowStages":[]},"version":"v1","identity":"rs-8373980","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-8373980","identity":"rs-8373980","version":["v1"]},"buildId":"8U1c8b4HqxoKbykW_rLl7","isFallback":false,"isExperimentalCompile":false,"dynamicIds":[84888],"gssp":true,"scriptLoader":[]}

Text is read by the "Ask this paper" AI Q&A widget below. Extraction quality varies by source — PMC NXML preserves structure cleanly, OA-HTML may include some navigation residue, and OA-PDF can have broken hyphenation. The publisher copy (via DOI) is the canonical version.

My notes (saved in your browser only)

Ask this paper AI returns verbatim quotes from the full text · source: preprint-html

Answers must be backed by verbatim quotes from this paper's full text. Hallucinated quotes are dropped automatically; if no verbatim passage answers the question, we say so. How this works

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. This is a recent paper (2025) — citers typically take a year or two to land, and the OpenAlex reference graph may still be filling in.

Source provenance

europepmc
last seen: 2026-05-20T01:45:00.602351+00:00
unpaywall
last seen: 2026-05-28T02:00:01.590549+00:00
License: CC-BY-4.0