Enhancing Multi-label Emotion Prediction through Rule-based Voting with LLM and BERT Variants

preprint OA: closed
Full text JSON View at publisher
AI-generated deep summary by claude@2026-07, 2026-07-04 · read from full text

This preprint studied multi-label emotion prediction from text using an ensemble framework that combines Large Language Models and BERT variants with an adaptive, rule-based voting mechanism. Using the SemEval-2025 Task 11 (Track A) test set, the authors report a macro F1 of 80.42% and micro F1 of 82.33%, outperforming both the best individual transformer architecture (DeBERTa) and the best listed LLM approach, with particular strength on complex and ambiguous expressions and improved performance across all five emotion categories. The paper notes a major caveat that it is a preprint that has not been peer reviewed. This paper does not explicitly discuss endometriosis or adenomyosis; it was included in the corpus via a keyword match in the upstream search index.

Read from the paper's body, not the abstract. Not a substitute for reading the paper. No clinical advice. How this works

Full text 39,534 characters · extracted from preprint-html · click to expand
Enhancing Multi-label Emotion Prediction through Rule-based Voting with LLM and BERT Variants | 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 Enhancing Multi-label Emotion Prediction through Rule-based Voting with LLM and BERT Variants Minh Hieu Le, Cong Phuoc Phan, Thanh Tuan Nguyen, Thi Thanh Sang Nguyen This is a preprint; it has not been peer reviewed by a journal. https://doi.org/ 10.21203/rs.3.rs-7501928/v1 This work is licensed under a CC BY 4.0 License Status: Under Review Version 1 posted 7 You are reading this latest preprint version Abstract Emotion analysis in text has become increasingly crucial for applications ranging from social media monitoring to mental health assessment. While advancements in natural language processing (NLP) have improved capabilities in this area, accurately identifying and categorizing complex emotional expressions remains a challenging task. This difficulty arises from the contextual implications and the complexity inherent in human emotions. This paper presents a novel framework that combines Large Language Models (LLMs) and BERT variants through an adaptive rule-based voting mechanism for robust multi-label emotion analysis. Our approach introduces three key components: (1) an adaptive weighted voting strategy that dynamically adjusts model contributions based on confidence scores, (2) a sophisticated prompt engineering technique that enables LLMs to better understand emotional context through template-based approaches, and (3) a hybrid decision-making mechanism that effectively integrates the complementary strengths of both LLM and BERT architectures through rule-based aggregation. Experimental results on the SemEval-2025 Task 11 (Track A) test set demonstrate that our proposed method achieves a macro F1 of 80.42% and micro F1 of 82.33%, outperforming the strongest individual transformer architecture (DeBERTa) by 9.8% and 7.4% respectively, and highest-performing LLM method (SFT Data-Augmented) by 2.1% and 1.7% respectively. Notably, our system shows particular strength in handling complex emotional expressions and ambiguous contexts, with consistent improvements across all five emotion categories, particularly excelling in fear detection (86.97% F1-score) and demonstrating robust performance on challenging low-frequency emotions like anger (74.62% F1-score). Emotion Analysis Large Language Models BERT Voting Mechanisms Multi-label Classification Full Text Additional Declarations No competing interests reported. Cite Share Download PDF Status: Under Review Version 1 posted Reviewers agreed at journal 01 Apr, 2026 Reviews received at journal 12 Feb, 2026 Reviewers agreed at journal 21 Jan, 2026 Reviewers invited by journal 27 Oct, 2025 Editor assigned by journal 14 Oct, 2025 Submission checks completed at journal 01 Sep, 2025 First submitted to journal 31 Aug, 2025 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-7501928","acceptedTermsAndConditions":true,"allowDirectSubmit":false,"archivedVersions":[],"articleType":"Research Article","associatedPublications":[],"authors":[{"id":535654856,"identity":"920ce7e1-60a2-4c26-81e2-f36ecead4e60","order_by":0,"name":"Minh Hieu Le","email":"","orcid":"","institution":"Dong Thap University","correspondingAuthor":false,"prefix":"","firstName":"Minh","middleName":"Hieu","lastName":"Le","suffix":""},{"id":535654857,"identity":"d502a89e-a3a4-4eff-8bb4-09f45af7e870","order_by":1,"name":"Cong Phuoc Phan","email":"","orcid":"","institution":"National Cheng Kung University","correspondingAuthor":false,"prefix":"","firstName":"Cong","middleName":"Phuoc","lastName":"Phan","suffix":""},{"id":535654858,"identity":"bc2fcfcf-d5d8-4465-9d3d-9d4c327ea808","order_by":2,"name":"Thanh Tuan Nguyen","email":"","orcid":"","institution":"University of Greenwich","correspondingAuthor":false,"prefix":"","firstName":"Thanh","middleName":"Tuan","lastName":"Nguyen","suffix":""},{"id":535654860,"identity":"fc671432-8fda-4530-adce-63eda95560df","order_by":3,"name":"Thi Thanh Sang Nguyen","email":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAAZAAAAAyAQMAAABI0h/eAAAABlBMVEX///8AAABVwtN+AAAACXBIWXMAAA7EAAAOxAGVKw4bAAAA00lEQVRIiWNgGAWjYBADOQMgcQCIGRsIqmVjBlPGpGtJ3ADlE9ZiLt9/+MPPHbXp29lPJx7mYbCR3XCAx+wBPi2Wbcxskr1njufu7MndANSSZgzUYm6AT4vBMWY2Bt62Y7kbbvCCtBxO3HCALU2CgBbmj3/bjqUbQLT8J0oLgzRvW00CVMsBoBbmYwS0JJtJy7YdMNxwJnfDwTkGycYzDxPScvjg449v2+rkDY6f3fzhTYWdbN/xxja8WqDgMMwEIGYmQj0Q1BGnbBSMglEwCkYmAABeTE2gmXXIawAAAABJRU5ErkJggg==","orcid":"","institution":"International University","correspondingAuthor":true,"prefix":"","firstName":"Thi","middleName":"Thanh Sang","lastName":"Nguyen","suffix":""}],"badges":[],"createdAt":"2025-08-31 16:38:15","currentVersionCode":1,"declarations":"","doi":"10.21203/rs.3.rs-7501928/v1","doiUrl":"https://doi.org/10.21203/rs.3.rs-7501928/v1","draftVersion":[],"editorialEvents":[],"editorialNote":"","failedWorkflow":false,"files":[{"id":95258292,"identity":"a4cae823-7a66-4039-9458-719d74d0517d","added_by":"auto","created_at":"2025-11-06 03:44:17","extension":"json","order_by":0,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":6364,"visible":true,"origin":"","legend":"","description":"","filename":"f2d194d76cac46eb9a87720749bf277c.json","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/5216ce4f2d1e3eeab87b35b4.json"},{"id":95258295,"identity":"d247a01f-d5c5-4d7d-9d92-5812be3cd198","added_by":"auto","created_at":"2025-11-06 03:44:17","extension":"xml","order_by":1,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":124541,"visible":true,"origin":"","legend":"","description":"","filename":"f2d194d76cac46eb9a87720749bf277c1enriched.xml","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/e1e8ee64a1a4477de73abb66.xml"},{"id":95312783,"identity":"0050d793-6d3a-4664-81b8-3fc3e6d48b37","added_by":"auto","created_at":"2025-11-06 15:50:18","extension":"png","order_by":2,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":109980,"visible":true,"origin":"","legend":"","description":"","filename":"BERTopic4EmotionCls.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/81e7557e3a9afc3c4c1cb8c4.png"},{"id":95258293,"identity":"0620328d-bc64-412f-85f1-ab7b082989c8","added_by":"auto","created_at":"2025-11-06 03:44:17","extension":"png","order_by":3,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":236692,"visible":true,"origin":"","legend":"","description":"","filename":"Bert.LLM.Voting.Framework.SelectedModel.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/baad55b8fa66748f7e8c6514.png"},{"id":95258294,"identity":"a45dfaf8-443c-40d8-8a4f-746c45aba0b4","added_by":"auto","created_at":"2025-11-06 03:44:17","extension":"png","order_by":4,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":256586,"visible":true,"origin":"","legend":"","description":"","filename":"Bert.LLM.VotingRules.SelectModels.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/8ee73d4ba1c94bebbfd4420b.png"},{"id":95258298,"identity":"35974170-9e65-4ea6-b422-f5578589c804","added_by":"auto","created_at":"2025-11-06 03:44:17","extension":"png","order_by":5,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":80812,"visible":true,"origin":"","legend":"","description":"","filename":"EmotionCls.ML.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/9b69862e7569ceb74ed1bf2e.png"},{"id":95313127,"identity":"b34601ff-bdf9-437b-bfdf-6765617d21a6","added_by":"auto","created_at":"2025-11-06 15:50:57","extension":"pdf","order_by":6,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1608399,"visible":true,"origin":"","legend":"","description":"","filename":"LanguageResourceEvaluation2025v2025090102.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/35c82471f0ae5a13354e4586.pdf"},{"id":95258301,"identity":"ac0f3758-32fa-4df1-88b7-503ab57535ce","added_by":"auto","created_at":"2025-11-06 03:44:17","extension":"png","order_by":7,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2241054,"visible":true,"origin":"","legend":"","description":"","filename":"Stat.Data.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/8dbd08587526d187f22be834.png"},{"id":95312906,"identity":"ad5215a3-7d85-4be3-b785-48d8d69f6a6a","added_by":"auto","created_at":"2025-11-06 15:50:33","extension":"png","order_by":8,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":17235,"visible":true,"origin":"","legend":"","description":"","filename":"Stat.DevData.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/dc47de1a3bd8e5155f346023.png"},{"id":95258297,"identity":"9a30ec99-dd93-4781-9d00-4a7cb2a7a872","added_by":"auto","created_at":"2025-11-06 03:44:17","extension":"png","order_by":9,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":21619,"visible":true,"origin":"","legend":"","description":"","filename":"Stat.TestData.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/54e637e8f528f7a979e44211.png"},{"id":95258299,"identity":"be620fa6-df41-4b90-b84d-6c44cc8ef7e0","added_by":"auto","created_at":"2025-11-06 03:44:17","extension":"png","order_by":10,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":21287,"visible":true,"origin":"","legend":"","description":"","filename":"Stat.TrainData.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/79d95c55882cd83d43a6a294.png"},{"id":95258306,"identity":"a050640d-534d-4f13-be10-543383103a5f","added_by":"auto","created_at":"2025-11-06 03:44:17","extension":"png","order_by":11,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":197558,"visible":true,"origin":"","legend":"","description":"","filename":"albertchart.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/026185ff5ef18fc0be480a41.png"},{"id":95312570,"identity":"1eb1a35f-cbe3-4007-8997-c93ee765aa17","added_by":"auto","created_at":"2025-11-06 15:49:45","extension":"png","order_by":12,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":198537,"visible":true,"origin":"","legend":"","description":"","filename":"bartchart.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/d603df25aac3f1a6d283ed6f.png"},{"id":95313017,"identity":"744cfa74-1bfd-4dce-b589-a795ba3c4d6b","added_by":"auto","created_at":"2025-11-06 15:50:45","extension":"png","order_by":13,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":181665,"visible":true,"origin":"","legend":"","description":"","filename":"bertchart.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/5567f645e33e6adec1557577.png"},{"id":95313038,"identity":"22abac8a-630a-43be-a326-bb7929085405","added_by":"auto","created_at":"2025-11-06 15:50:47","extension":"png","order_by":14,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":192560,"visible":true,"origin":"","legend":"","description":"","filename":"debertachart.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/377cdeb836004e584de23d37.png"},{"id":95312645,"identity":"537e857a-7d71-4f6c-aa17-f1b288844b9f","added_by":"auto","created_at":"2025-11-06 15:49:55","extension":"png","order_by":15,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":202489,"visible":true,"origin":"","legend":"","description":"","filename":"distilbertchart.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/f42d64fa8439669c98dff36c.png"},{"id":95312770,"identity":"3b9e392c-9c24-4486-a948-6bcecae97336","added_by":"auto","created_at":"2025-11-06 15:50:15","extension":"png","order_by":16,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":198008,"visible":true,"origin":"","legend":"","description":"","filename":"electrachart.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/8f65e2f9457d24e71f882ee4.png"},{"id":95312918,"identity":"135a2555-80dc-419d-be68-ed0cf9f1bea3","added_by":"auto","created_at":"2025-11-06 15:50:37","extension":"eps","order_by":17,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2970,"visible":true,"origin":"","legend":"","description":"","filename":"empty.eps","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/b49e8fbdefec90e166aba240.eps"},{"id":95312909,"identity":"2452bd84-07b4-4743-93f1-19cf3307f664","added_by":"auto","created_at":"2025-11-06 15:50:33","extension":"eps","order_by":18,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":93049,"visible":true,"origin":"","legend":"","description":"","filename":"fig.eps","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/b73272f1a2a539c618d908c6.eps"},{"id":95258307,"identity":"1d3adc0c-a2ca-45e9-9155-261d104dae2b","added_by":"auto","created_at":"2025-11-06 03:44:17","extension":"png","order_by":19,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":650826,"visible":true,"origin":"","legend":"","description":"","filename":"llmmixturesoffinetuningmethodstructure.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/82e23e94e22679e78a190d45.png"},{"id":95313145,"identity":"197fb95e-9d5a-4d55-850c-2bb04ad86960","added_by":"auto","created_at":"2025-11-06 15:51:00","extension":"png","order_by":20,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":185404,"visible":true,"origin":"","legend":"","description":"","filename":"mbertchart.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/b7b13e53e18d1122fb0e2329.png"},{"id":95258318,"identity":"43f77e3b-0b5c-463d-887e-2841970315d8","added_by":"auto","created_at":"2025-11-06 03:44:17","extension":"png","order_by":21,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":200065,"visible":true,"origin":"","legend":"","description":"","filename":"robertachart.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/759836eef2fc63db718966b4.png"},{"id":95312769,"identity":"7cb61097-00a5-4735-abf4-b9872a67df9e","added_by":"auto","created_at":"2025-11-06 15:50:15","extension":"bst","order_by":22,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":151345,"visible":true,"origin":"","legend":"","description":"","filename":"snapacite.bst","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/f4a35e78a789561bf3231ddd.bst"},{"id":95258313,"identity":"5e5d5ed6-13ba-47ef-ae1f-64c5a3c3a03a","added_by":"auto","created_at":"2025-11-06 03:44:17","extension":"bst","order_by":23,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":31359,"visible":true,"origin":"","legend":"","description":"","filename":"snaps.bst","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/1ae13c766867ca3bbb7408a1.bst"},{"id":95258308,"identity":"b5209b95-1cc6-45ec-8477-d501b812175d","added_by":"auto","created_at":"2025-11-06 03:44:17","extension":"aux","order_by":24,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15068,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.aux","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/6503d40d3fdb28dbd794e90e.aux"},{"id":95258314,"identity":"0298f1e9-3d7a-4e34-be89-189c9c71df39","added_by":"auto","created_at":"2025-11-06 03:44:17","extension":"bbl","order_by":25,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":19929,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.bbl","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/b80dc7a68376eb4c5db60208.bbl"},{"id":95312796,"identity":"4ac7c06b-5fc0-48ce-af63-18b5ebd8724d","added_by":"auto","created_at":"2025-11-06 15:50:20","extension":"blg","order_by":26,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":2474,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.blg","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/e4e01c2af62a516e4fa3f524.blg"},{"id":95313106,"identity":"c18c6488-b88d-411e-af67-09377ad63961","added_by":"auto","created_at":"2025-11-06 15:50:53","extension":"fdb_latexmk","order_by":27,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":23628,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.fdblatexmk","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/bbd99632ce8f6b9a66b0950c.fdb_latexmk"},{"id":95258320,"identity":"ec19a299-b271-45fd-8e5d-f89892244cc4","added_by":"auto","created_at":"2025-11-06 03:44:17","extension":"fls","order_by":28,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":32742,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.fls","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/31712b5567cd35ed08fbd2b6.fls"},{"id":95258316,"identity":"c2c5a457-3ace-4b83-a278-be1fe443a909","added_by":"auto","created_at":"2025-11-06 03:44:17","extension":"log","order_by":29,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":37625,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.log","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/e1a9aca8063576626490f0da.log"},{"id":95258322,"identity":"44efcc43-9bc9-4c64-ae04-83d632ae348a","added_by":"auto","created_at":"2025-11-06 03:44:17","extension":"out","order_by":30,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":7788,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.out","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/16ab2664d13b1b5376133f9d.out"},{"id":95258332,"identity":"cfbda65a-506d-45f1-8efd-ac9368a0acb3","added_by":"auto","created_at":"2025-11-06 03:44:18","extension":"pdf","order_by":31,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":1567055,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/de29cc5cbb016471257b3ab9.pdf"},{"id":95258328,"identity":"dd7fc305-fb68-4dc0-91da-ee6c2f9a6cea","added_by":"auto","created_at":"2025-11-06 03:44:18","extension":"gz","order_by":32,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":220753,"visible":true,"origin":"","legend":"","description":"","filename":"snarticle.synctex.gz","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/b089e9d6d0c25a5ccecda768.gz"},{"id":95313034,"identity":"cee34505-9b3e-46d8-b16c-55481203d334","added_by":"auto","created_at":"2025-11-06 15:50:47","extension":"bst","order_by":33,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":37333,"visible":true,"origin":"","legend":"","description":"","filename":"snbasic.bst","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/c889c044e895ce92decf0bbb.bst"},{"id":95258324,"identity":"98be98a1-d7e0-4678-b9af-a90e6426d52d","added_by":"auto","created_at":"2025-11-06 03:44:18","extension":"bst","order_by":34,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":35651,"visible":true,"origin":"","legend":"","description":"","filename":"snchicago.bst","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/b1c0183e81e4bae167f59284.bst"},{"id":95313020,"identity":"014e078b-e3dd-4c2a-9458-dae8b82d453a","added_by":"auto","created_at":"2025-11-06 15:50:46","extension":"cls","order_by":35,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":57660,"visible":true,"origin":"","legend":"","description":"","filename":"snjnl.cls","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/cfdee343ef9750f44414b782.cls"},{"id":95258334,"identity":"93a4dd9b-fba4-43ec-bd33-0aaa69f69c77","added_by":"auto","created_at":"2025-11-06 03:44:18","extension":"bst","order_by":36,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":67231,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysay.bst","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/7809579ffadb52d9c0d84cd3.bst"},{"id":95312831,"identity":"4af5ebee-9869-4d8e-8c0d-f7e49f2f62ea","added_by":"auto","created_at":"2025-11-06 15:50:24","extension":"bst","order_by":37,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":67377,"visible":true,"origin":"","legend":"","description":"","filename":"snmathphysnum.bst","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/4ed072cdf1d1ee7bfbc925bc.bst"},{"id":95258330,"identity":"8661d233-0e81-4b14-8ee1-6c011df745b0","added_by":"auto","created_at":"2025-11-06 03:44:18","extension":"bst","order_by":38,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":39056,"visible":true,"origin":"","legend":"","description":"","filename":"snnature.bst","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/25a7ef45da11ba383e9afc22.bst"},{"id":95258326,"identity":"ab26c96b-5b3f-4213-accb-249a0b0687a8","added_by":"auto","created_at":"2025-11-06 03:44:18","extension":"bst","order_by":39,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":42035,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouveray.bst","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/79becb87273cd7b902dc08df.bst"},{"id":95313053,"identity":"248dc88d-b32d-48ce-be9c-9b9875a50fbd","added_by":"auto","created_at":"2025-11-06 15:50:49","extension":"bst","order_by":40,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":42779,"visible":true,"origin":"","legend":"","description":"","filename":"snvancouvernum.bst","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/f6a2036e9127c6e5d0780b41.bst"},{"id":95258329,"identity":"2d31a563-8ceb-4d04-95a8-d97711105f27","added_by":"auto","created_at":"2025-11-06 03:44:18","extension":"png","order_by":41,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":200980,"visible":true,"origin":"","legend":"","description":"","filename":"spanbertchart.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/13fa11521af7e10dfd551b32.png"},{"id":95313355,"identity":"5c0a04b4-51c7-41f4-8dbe-e80b962cfeb4","added_by":"auto","created_at":"2025-11-06 15:51:18","extension":"png","order_by":42,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":192589,"visible":true,"origin":"","legend":"","description":"","filename":"tinybertchart.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/872c2cee3555a2c4ebccf794.png"},{"id":95313039,"identity":"d48827fc-61fa-4e02-98e1-22ceca9b1ee5","added_by":"auto","created_at":"2025-11-06 15:50:47","extension":"pdf","order_by":43,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":418495,"visible":true,"origin":"","legend":"","description":"","filename":"usermanual.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/cdde7baa42563a3a54159e98.pdf"},{"id":95258350,"identity":"9ba53c00-0365-4691-899a-112690245e5f","added_by":"auto","created_at":"2025-11-06 03:44:18","extension":"png","order_by":44,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":206190,"visible":true,"origin":"","legend":"","description":"","filename":"xlmrchart.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/d563a0731db7ba7b2cceca6c.png"},{"id":95258343,"identity":"62663c6f-609d-44d3-b25b-20e8ac23f9d0","added_by":"auto","created_at":"2025-11-06 03:44:18","extension":"png","order_by":45,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":189656,"visible":true,"origin":"","legend":"","description":"","filename":"xlnetchart.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/35e76728e052f08633949a41.png"},{"id":95258333,"identity":"635caeba-b926-4b17-a293-2c23a393afd3","added_by":"auto","created_at":"2025-11-06 03:44:18","extension":"png","order_by":46,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":100031,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineBERTopic4EmotionCls.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/4bb2e0849fadca0fcaa75dcb.png"},{"id":95258341,"identity":"a28df585-1b04-4464-919d-dc9d87af294d","added_by":"auto","created_at":"2025-11-06 03:44:18","extension":"png","order_by":50,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":33308,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineStat.Data.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/94a8c1b0bf6c198601da7e26.png"},{"id":95258335,"identity":"0ce6d781-c47d-4d84-b2bb-0f21d203e29e","added_by":"auto","created_at":"2025-11-06 03:44:18","extension":"png","order_by":51,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":15364,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineStat.DevData.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/baa4ca6f46778f175008fb92.png"},{"id":95258353,"identity":"bb2f6517-34c5-4f07-b721-31126eb3a63c","added_by":"auto","created_at":"2025-11-06 03:44:18","extension":"png","order_by":52,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":19708,"visible":true,"origin":"","legend":"","description":"","filename":"OnlineStat.TestData.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/37f15f8db5e30bc1bac54a9c.png"},{"id":95313115,"identity":"5f82e419-0977-4d06-b15e-f6c6aa48ba74","added_by":"auto","created_at":"2025-11-06 15:50:55","extension":"png","order_by":54,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":87613,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinealbertchart.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/9a140569fe8f26f02e99873d.png"},{"id":95313030,"identity":"e704e1cf-9aa2-4480-9c00-c352e717cfa5","added_by":"auto","created_at":"2025-11-06 15:50:46","extension":"png","order_by":55,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":99918,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinebartchart.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/49e4e864cc3faad9764bcf75.png"},{"id":95313224,"identity":"b1fa2b39-3ce4-4378-b78a-99718ae90002","added_by":"auto","created_at":"2025-11-06 15:51:08","extension":"png","order_by":56,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":81370,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinebertchart.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/ebb0a9d6c39de5c5a64dcb25.png"},{"id":95312708,"identity":"c5b95cca-e98d-4ba5-94a5-1855d23b101d","added_by":"auto","created_at":"2025-11-06 15:50:06","extension":"png","order_by":57,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":93193,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinedebertachart.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/50eb5f904143fb546b9272b2.png"},{"id":95313170,"identity":"8f84cad0-6025-4b7d-a9f4-4e4b09d9ef7b","added_by":"auto","created_at":"2025-11-06 15:51:01","extension":"png","order_by":58,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":92701,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinedistilbertchart.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/d8a22ef5d248001ec3af298c.png"},{"id":95258348,"identity":"02005079-0bf4-46b6-9c7a-81ac910680ae","added_by":"auto","created_at":"2025-11-06 03:44:18","extension":"png","order_by":59,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":92347,"visible":true,"origin":"","legend":"","description":"","filename":"Onlineelectrachart.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/a6c100ca315fba1a269284cb.png"},{"id":95312755,"identity":"583556a2-e284-4477-ae61-34e05a35c8dd","added_by":"auto","created_at":"2025-11-06 15:50:13","extension":"png","order_by":61,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":86657,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinembertchart.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/258d6ea7110f62070139ed35.png"},{"id":95312687,"identity":"36e3631f-1508-4f89-87c4-0256a690b4fe","added_by":"auto","created_at":"2025-11-06 15:50:03","extension":"png","order_by":62,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":95302,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinerobertachart.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/f611cb9c88ebc6bbbb007170.png"},{"id":95258337,"identity":"abe96d68-4924-425f-8dc2-986761a002af","added_by":"auto","created_at":"2025-11-06 03:44:18","extension":"png","order_by":63,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":97688,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinespanbertchart.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/a75d945e554de10e609a406f.png"},{"id":95313105,"identity":"0f03d4c1-c2bf-41bd-b291-2b3101f3831c","added_by":"auto","created_at":"2025-11-06 15:50:53","extension":"png","order_by":64,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":93190,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinetinybertchart.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/7ad822e59a51cef91719e287.png"},{"id":95313114,"identity":"8e12d674-125a-48df-b2ae-62bb15410e84","added_by":"auto","created_at":"2025-11-06 15:50:55","extension":"png","order_by":65,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":106990,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinexlmrchart.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/b1667ca948ac0113a6cb3c05.png"},{"id":95258338,"identity":"b8de4747-16d8-43e3-bb3c-acac5e834d09","added_by":"auto","created_at":"2025-11-06 03:44:18","extension":"png","order_by":66,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":90454,"visible":true,"origin":"","legend":"","description":"","filename":"Onlinexlnetchart.png","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/77862b746bdbb512ca33c06b.png"},{"id":95313194,"identity":"514fb3dd-c8b2-4e8e-b3ec-9479576c769d","added_by":"auto","created_at":"2025-11-06 15:51:05","extension":"xml","order_by":67,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":137760,"visible":true,"origin":"","legend":"","description":"","filename":"f2d194d76cac46eb9a87720749bf277c1structuring.xml","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/e738f09a02f64a144c91d4ff.xml"},{"id":95258347,"identity":"0a7bb90f-4e7e-4c64-9f84-b56a4ace8e19","added_by":"auto","created_at":"2025-11-06 03:44:18","extension":"html","order_by":68,"title":"","display":"","copyAsset":false,"role":"acdc-reference","size":148494,"visible":true,"origin":"","legend":"","description":"","filename":"earlyproof.html","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1/5cb679fc26a7c23d4b17bb41.html"},{"id":95523717,"identity":"df3e08a3-e532-4877-80fb-3450926792fc","added_by":"auto","created_at":"2025-11-10 10:00:20","extension":"pdf","order_by":1,"title":"","display":"","copyAsset":false,"role":"manuscript-pdf","size":1475126,"visible":true,"origin":"","legend":"","description":"","filename":"LanguageResourceEvaluation2025v2025090102.pdf","url":"https://assets-eu.researchsquare.com/files/rs-7501928/v1_covered_a4303ebc-4bdf-456c-a86c-14a13fcf7bdd.pdf"}],"financialInterests":"No competing interests reported.","formattedTitle":"Enhancing Multi-label Emotion Prediction through Rule-based Voting with LLM and BERT Variants","fulltext":[],"fulltextSource":"","fullText":"","funders":[],"hasAdminPriorityOnWorkflow":false,"hasManuscriptDocX":false,"hasOptedInToPreprint":true,"hasPassedJournalQc":"","hasAnyPriority":false,"hideJournal":false,"highlight":"","institution":"","isAcceptedByJournal":false,"isAuthorSuppliedPdf":true,"isDeskRejected":"","isHiddenFromSearch":false,"isInQc":false,"isInWorkflow":false,"isPdf":true,"isPdfUpToDate":true,"isWithdrawnOrRetracted":false,"journal":{"display":true,"email":"[email protected]","identity":"language-resources-and-evaluation","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"lrev","sideBox":"Learn more about [Language Resources and Evaluation](http://link.springer.com/journal/10579)","snPcode":"10579","submissionUrl":"https://submission.nature.com/new-submission/10579/3","title":"Language Resources and Evaluation","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false},"keywords":"Emotion Analysis, Large Language Models, BERT, Voting Mechanisms, Multi-label Classification","lastPublishedDoi":"10.21203/rs.3.rs-7501928/v1","lastPublishedDoiUrl":"https://doi.org/10.21203/rs.3.rs-7501928/v1","license":{"name":"CC BY 4.0","url":"https://creativecommons.org/licenses/by/4.0/"},"manuscriptAbstract":"\u003cp\u003eEmotion analysis in text has become increasingly crucial for applications ranging from social media monitoring to mental health assessment. While advancements in natural language processing (NLP) have improved capabilities in this area, accurately identifying and categorizing complex emotional expressions remains a challenging task. This difficulty arises from the contextual implications and the complexity inherent in human emotions. This paper presents a novel framework that combines Large Language Models (LLMs) and BERT variants through an adaptive rule-based voting mechanism for robust multi-label emotion analysis. Our approach introduces three key components: (1) an adaptive weighted voting strategy that dynamically adjusts model contributions based on confidence scores, (2) a sophisticated prompt engineering technique that enables LLMs to better understand emotional context through template-based approaches, and (3) a hybrid decision-making mechanism that effectively integrates the complementary strengths of both LLM and BERT architectures through rule-based aggregation. Experimental results on the SemEval-2025 Task 11 (Track A) test set demonstrate that our proposed method achieves a macro F1 of 80.42% and micro F1 of 82.33%, outperforming the strongest individual transformer architecture (DeBERTa) by 9.8% and 7.4% respectively, and highest-performing LLM method (SFT Data-Augmented) by 2.1% and 1.7% respectively. Notably, our system shows particular strength in handling complex emotional expressions and ambiguous contexts, with consistent improvements across all five emotion categories, particularly excelling in fear detection (86.97% F1-score) and demonstrating robust performance on challenging low-frequency emotions like anger (74.62% F1-score).\u003c/p\u003e","manuscriptTitle":"Enhancing Multi-label Emotion Prediction through Rule-based Voting with LLM and BERT Variants","msid":"","msnumber":"","nonDraftVersions":[{"code":1,"date":"2025-11-06 03:44:12","doi":"10.21203/rs.3.rs-7501928/v1","editorialEvents":[{"type":"communityComments","content":0},{"type":"reviewerAgreed","content":"158506623440695567158832389889552510466","date":"2026-04-01T09:17:35+00:00","index":"hide","fulltext":""},{"type":"editorInvitedReview","content":"","date":"2026-02-12T14:50:49+00:00","index":"hide","fulltext":""},{"type":"reviewerAgreed","content":"246102360203078295936178862205109718225","date":"2026-01-21T17:07:40+00:00","index":"hide","fulltext":""},{"type":"reviewersInvited","content":"","date":"2025-10-27T11:06:51+00:00","index":"","fulltext":""},{"type":"editorAssigned","content":"","date":"2025-10-14T15:17:52+00:00","index":"","fulltext":""},{"type":"checksComplete","content":"","date":"2025-09-01T15:56:24+00:00","index":"","fulltext":""},{"type":"submitted","content":"Language Resources and Evaluation","date":"2025-08-31T16:28:16+00:00","index":"","fulltext":""}],"status":"published","journal":{"display":true,"email":"[email protected]","identity":"language-resources-and-evaluation","isNatureJournal":false,"hasQc":true,"allowDirectSubmit":false,"externalIdentity":"lrev","sideBox":"Learn more about [Language Resources and Evaluation](http://link.springer.com/journal/10579)","snPcode":"10579","submissionUrl":"https://submission.nature.com/new-submission/10579/3","title":"Language Resources and Evaluation","twitterHandle":"","acdcEnabled":true,"dfaEnabled":true,"editorialSystem":"em","reportingPortfolio":"Springer Hybrid","inReviewEnabled":true,"inReviewRevisionsEnabled":false}}],"origin":"","ownerIdentity":"64ae4a30-e726-494d-8b18-39331d0d1fca","owner":[],"postedDate":"November 6th, 2025","published":true,"recentEditorialEvents":[],"rejectedJournal":[],"revision":"","amendment":"","status":"under-review","subjectAreas":[],"tags":[],"updatedAt":"2025-11-06T03:44:12+00:00","versionOfRecord":[],"versionCreatedAt":"2025-11-06 03:44:12","video":"","vorDoi":"","vorDoiUrl":"","workflowStages":[]},"version":"v1","identity":"rs-7501928","journalConfig":"researchsquare"},"__N_SSP":true},"page":"/article/[identity]/[[...version]]","query":{"redirect":"/article/rs-7501928","identity":"rs-7501928","version":["v1"]},"buildId":"XKTyCvWXoU3ODBz1xrDgd","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