基于股票新闻构建市场情绪指数的多模态深度学习框架

IF 3.5 3区计算机科学 Q2 COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE

Big Data Research Pub Date : 2025-05-17 DOI:10.1016/j.bdr.2025.100535

Yunting Liu, Yirong Huang

{"title":"基于股票新闻构建市场情绪指数的多模态深度学习框架","authors":"Yunting Liu, Yirong Huang","doi":"10.1016/j.bdr.2025.100535","DOIUrl":null,"url":null,"abstract":"<div><div>Unimodal sentiment analysis often fails to capture the complexity of financial sentiment. This paper proposes a multimodal deep learning framework that integrates text, audio, and image data from CCTV news videos on TikTok to construct a multimodal sentiment indicator for the Chinese stock market. Empirical results show that multimodal fusion enhances sentiment analysis, with text outperforming audio and image modalities. The indicator correlates weakly with stock returns but significantly with market volatility, aligns with seasonal sentiment patterns, and reflects significant events like COVID-19. Additionally, weekly sentiment trends indicate the lowest sentiment on Thursdays and the highest on Fridays. This study advances financial sentiment analysis by demonstrating the efficacy of multimodal indicators in capturing market sentiment and informing volatility forecasts.</div></div>","PeriodicalId":56017,"journal":{"name":"Big Data Research","volume":"41 ","pages":"Article 100535"},"PeriodicalIF":3.5000,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"A multimodal deep learning framework for constructing a market sentiment index from stock news\",\"authors\":\"Yunting Liu, Yirong Huang\",\"doi\":\"10.1016/j.bdr.2025.100535\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><div>Unimodal sentiment analysis often fails to capture the complexity of financial sentiment. This paper proposes a multimodal deep learning framework that integrates text, audio, and image data from CCTV news videos on TikTok to construct a multimodal sentiment indicator for the Chinese stock market. Empirical results show that multimodal fusion enhances sentiment analysis, with text outperforming audio and image modalities. The indicator correlates weakly with stock returns but significantly with market volatility, aligns with seasonal sentiment patterns, and reflects significant events like COVID-19. Additionally, weekly sentiment trends indicate the lowest sentiment on Thursdays and the highest on Fridays. This study advances financial sentiment analysis by demonstrating the efficacy of multimodal indicators in capturing market sentiment and informing volatility forecasts.</div></div>\",\"PeriodicalId\":56017,\"journal\":{\"name\":\"Big Data Research\",\"volume\":\"41 \",\"pages\":\"Article 100535\"},\"PeriodicalIF\":3.5000,\"publicationDate\":\"2025-05-17\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Big Data Research\",\"FirstCategoryId\":\"94\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S2214579625000309\",\"RegionNum\":3,\"RegionCategory\":\"计算机科学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Big Data Research","FirstCategoryId":"94","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S2214579625000309","RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"COMPUTER SCIENCE, ARTIFICIAL INTELLIGENCE","Score":null,"Total":0}

引用次数: 0

摘要

单模态情绪分析往往无法捕捉到金融情绪的复杂性。本文提出了一个多模态深度学习框架，该框架整合了TikTok上CCTV新闻视频的文本、音频和图像数据，构建了中国股市的多模态情绪指标。实证结果表明，多模态融合增强了情感分析，文本模式优于音频和图像模式。该指标与股票回报相关性较弱，但与市场波动性相关性显著，与季节性情绪模式一致，并反映了COVID-19等重大事件。此外，每周情绪趋势显示周四情绪最低，周五情绪最高。本研究通过展示多模态指标在捕捉市场情绪和为波动率预测提供信息方面的有效性，推进了金融情绪分析。

本文章由计算机程序翻译，如有差异，请以英文原文为准。

查看原文本刊更多论文

A multimodal deep learning framework for constructing a market sentiment index from stock news

Unimodal sentiment analysis often fails to capture the complexity of financial sentiment. This paper proposes a multimodal deep learning framework that integrates text, audio, and image data from CCTV news videos on TikTok to construct a multimodal sentiment indicator for the Chinese stock market. Empirical results show that multimodal fusion enhances sentiment analysis, with text outperforming audio and image modalities. The indicator correlates weakly with stock returns but significantly with market volatility, aligns with seasonal sentiment patterns, and reflects significant events like COVID-19. Additionally, weekly sentiment trends indicate the lowest sentiment on Thursdays and the highest on Fridays. This study advances financial sentiment analysis by demonstrating the efficacy of multimodal indicators in capturing market sentiment and informing volatility forecasts.

求助全文

通过发布文献求助，成功后即可免费获取论文全文。去求助

来源期刊

Big Data Research Computer Science-Computer Science Applications

CiteScore

8.40

自引率

3.00%

发文量

期刊介绍： The journal aims to promote and communicate advances in big data research by providing a fast and high quality forum for researchers, practitioners and policy makers from the very many different communities working on, and with, this topic. The journal will accept papers on foundational aspects in dealing with big data, as well as papers on specific Platforms and Technologies used to deal with big data. To promote Data Science and interdisciplinary collaboration between fields, and to showcase the benefits of data driven research, papers demonstrating applications of big data in domains as diverse as Geoscience, Social Web, Finance, e-Commerce, Health Care, Environment and Climate, Physics and Astronomy, Chemistry, life sciences and drug discovery, digital libraries and scientific publications, security and government will also be considered. Occasionally the journal may publish whitepapers on policies, standards and best practices.