Popular Events Detection from Blogs/Forums and Analyzing the Pattern of Users' Opinionwith Stock Market Movement

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

Abstract

Frequently, individuals share their thoughts on socialmedia regarding diverse events and policy announcements. The challenge of discerning how news or social events influencefluctuations in stock prices is a prominent one. Many investorshave come to recognize that gauging the impact of an event onstock prices holds a pivotal role in making informed strategicchoices. However, identifying relevant events within the realm ofsocial media presents a formidable obstacle. To address this issue,our study is structured into two distinct phases: In the initial partof our investigation, we have collected data pertaining to economicpolicies from the Government of India’s budget speechesin 2020 and 2021, alongside stock-related information from newspapers,stock blogs, and forums. Subsequently, we harnessed anarray of natural language processing (NLP) techniques to extractaspects and phrases from this textual data. It is worth noting thatconventional NLP methods often encounter difficulties when dealingwith new instances and necessitate substantial training data.To overcome this, we devised a strategy involving a combinationof predefined linguistic patterns with NLP methodologies, therebyenhancing the precision of our approach. This comprehensivedataset facilitated the identification of a diverse array of publicinterest events, encompassing political occurrences and economictrends. The next phase of our study introduces an algorithmdesigned to identify popular events within the realm of socialmedia. Additionally, we examine how sentiments and opinionsrelated to these events can exert influence on movements in thestock market. The strategy most likely includes sentiment analysisand an investigation of the correlations between fluctuations instock prices and social media sentiment. Notably, our proposedmethodology has demonstrated superior performance comparedto prevailing methods, particularly in terms of overall accuracy.

My notes (saved in your browser only)

Citation neighborhood (no data yet)

We don't have any in-corpus citations linked to this paper yet. The paper's references may be in our DB but unresolved to ``paper_id`` (resolution happens at ingest when the cited DOI matches a row we already have). Run the cross-source citation reconcile pass to retry.

Source provenance

europepmc
last seen: 2026-05-19T01:45:01.086888+00:00
unpaywall
last seen: 2026-08-15T06:29:46.044917+00:00
License: CC-BY-4.0