{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T17:58:47Z","timestamp":1790791127020,"version":"4.1.0"},"reference-count":36,"publisher":"Public Library of Science (PLoS)","issue":"9","license":[{"start":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:00:00Z","timestamp":1790726400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS One"],"abstract":"<jats:p>Forecasting financial market movements requires integrating numerical time-series data with semantic information from financial narratives that shape investor behavior. While deep learning has advanced time-series prediction, existing methods often exploit trivial price autocorrelation rather than capturing genuine predictive signals from multimodal sources. We propose the Semantic-Time Fusion Architecture (STFA), which integrates structured market data with GPT-4-supervised FinBERT semantic representations of financial news through three key innovations: delay-aware temporal alignment between text publication and market reaction, semantic-guided attention mechanisms emphasizing news-relevant historical patterns, and multi-scale temporal fusion with multi-objective training to balance accuracy and interpretability. We evaluate our model on a large-scale financial news and stock price dataset using GPT-4 sentiment annotation across stratified high-liquidity stocks with strictly chronological train-validation-test splits (2013\u20132020 for training, 2021 for validation, 2022\u20132023 for testing). Sentiment annotations were generated independently for each article without using any future market information, ensuring strict temporal separation and preventing information leakage. Experiments demonstrate that STFA significantly outperforms traditional time-series models, multimodal baselines, and random walk benchmarks on return prediction, where price autocorrelation vanishes, rather than relying on price-level forecasting. Statistical validation with bootstrap confidence intervals, effect size analysis, and Bonferroni-corrected significance tests confirms robust improvements across independent runs. Ablation studies reveal that GPT-4-supervised FinBERT semantic representations provide superior signals compared with lexicon-based sentiment, with each architectural component contributing significantly to performance. This work demonstrates how temporally aligned semantic understanding enhances both predictive accuracy and model interpretability in financial forecasting.<\/jats:p>","DOI":"10.1371\/journal.pone.0356139","type":"journal-article","created":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T17:36:15Z","timestamp":1790789775000},"page":"e0356139","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":0,"title":["Using large models and time series forecasting for market reaction analysis"],"prefix":"10.1371","volume":"21","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3108-2998","authenticated-orcid":true,"given":"Hong","family":"He","sequence":"first","affiliation":[{"name":"School of Economics and Management, Harbin Petroleum Institute","place":["Harbin, Heilongjiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinhai","family":"Li","sequence":"additional","affiliation":[{"name":"Accounting college, Harbin University of Commerce","place":["Harbin, Heilongjiang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2026,9,30]]},"reference":[{"key":"pone.0356139.ref001","first-page":"34","article-title":"Quantitative finance and machine learning: transforming investment strategies, risk modeling, and market forecasting in global markets","author":"O Alao","year":"2025","journal-title":"Int J Comput Appl Technol Res"},{"key":"pone.0356139.ref002","doi-asserted-by":"crossref","unstructured":"Tian T, Cooper R, Deng J, Zhang Q. Transforming Investment Strategies and Strategic Decision-Making: Unveiling a Novel Methodology for Enhanced Performance and Risk Management in Financial Markets. arXiv preprint arXiv:240501892. 2024. doi: 10.48550\/arXiv.2405.01892","DOI":"10.2139\/ssrn.5159264"},{"key":"pone.0356139.ref003","volume-title":"Financial Management and Market Dynamics","author":"YK Jain","year":"2024"},{"issue":"1","key":"pone.0356139.ref004","doi-asserted-by":"crossref","first-page":"7","DOI":"10.3390\/sci7010007","article-title":"LSTM\u2013Transformer-Based Robust Hybrid Deep Learning Model for Financial Time Series Forecasting","volume":"7","author":"MR Kabir","year":"2025","journal-title":"Sci"},{"key":"pone.0356139.ref005","doi-asserted-by":"crossref","unstructured":"Kehinde TO, Khan WA, Chung SH. Financial Market Forecasting Using RNN, LSTM, BiLSTM, GRU and Transformer-Based Deep Learning Algorithms. In: Proceedings of the IEOM International Conference on Smart Mobility and Vehicle Electrification. Detroit (MI); 2023. p. 10\u201312.","DOI":"10.46254\/EV01.20230037"},{"key":"pone.0356139.ref006","doi-asserted-by":"crossref","first-page":"113229","DOI":"10.1016\/j.asoc.2025.113229","article-title":"Time series prediction for cryptocurrency markets with transformer and parallel convolutional neural networks","volume":"177","author":"MA Izadi","year":"2025","journal-title":"Appl Soft Comput"},{"issue":"2","key":"pone.0356139.ref007","first-page":"53","article-title":"Long short-term memory (LSTM) networks for time series forecasting: A comprehensive survey of models, applications, and challenges","volume":"26","author":"B Aitbekov","year":"2025","journal-title":"Cent Asian Sci J"},{"issue":"1","key":"pone.0356139.ref008","doi-asserted-by":"crossref","first-page":"21","DOI":"10.1080\/1350178X.2018.1419105","article-title":"Models as speech acts: the telling case of financial models","volume":"25","author":"N Brisset","year":"2018","journal-title":"J Econ Methodol"},{"issue":"3","key":"pone.0356139.ref009","doi-asserted-by":"crossref","first-page":"1","DOI":"10.47363\/JBBER\/2024(2)118","article-title":"Advancing Sentiment Analysis Through Emotionally-Agnostic Text Mining in Large Language Models (LLMS)","volume":"2","author":"J Hutson","year":"2024","journal-title":"J Biosen and Bioelec Res"},{"key":"pone.0356139.ref010","unstructured":"Shabir G, Yuille A. Evaluating Large Language Models for E-Commerce Sentiment Analysis Using Causal Reasoning Frameworks. Preprint. 2024. doi: 10.13140\/RG.2.2.15211.96803"},{"key":"pone.0356139.ref011","doi-asserted-by":"crossref","unstructured":"Dong Z, Fan X, Peng Z. Fnspid: A comprehensive financial news dataset in time series. In: Proceedings of the 30th ACM SIGKDD Conference on Knowledge Discovery and Data Mining. 2024. p. 4918\u201327.","DOI":"10.1145\/3637528.3671629"},{"issue":"3","key":"pone.0356139.ref012","doi-asserted-by":"crossref","first-page":"661","DOI":"10.1111\/j.1540-6261.1988.tb04598.x","article-title":"Stock Prices, Earnings, and Expected Dividends","volume":"43","author":"JY Campbell","year":"1988","journal-title":"J Finance"},{"issue":"2","key":"pone.0356139.ref013","doi-asserted-by":"crossref","first-page":"383","DOI":"10.2307\/2325486","article-title":"Efficient Capital Markets: A Review of Theory and Empirical Work","volume":"25","author":"EF Fama","year":"1970","journal-title":"J Finance"},{"key":"pone.0356139.ref014","volume-title":"Market response models: econometric and time series analysis","author":"DM Hanssens","year":"2001"},{"issue":"4","key":"pone.0356139.ref015","doi-asserted-by":"crossref","first-page":"470","DOI":"10.1177\/002224378001700406","article-title":"Market Response, Competitive Behavior, and Time Series Analysis","volume":"17","author":"DM Hanssens","year":"1980","journal-title":"J Market Res"},{"key":"pone.0356139.ref016","doi-asserted-by":"crossref","DOI":"10.1287\/mksc.14.3.G109","article-title":"Empirical Generalizations About Market Evolution and Stationarity","volume":"14","author":"MG Dekimpe","year":"1995","journal-title":"Market Sci"},{"issue":"5","key":"pone.0356139.ref017","doi-asserted-by":"crossref","first-page":"1130","DOI":"10.3390\/math11051130","article-title":"Stock Market Analysis Using Time Series Relational Models for Stock Price Prediction","volume":"11","author":"C Zhao","year":"2023","journal-title":"Mathematics"},{"issue":"12","key":"pone.0356139.ref018","article-title":"Forecasting leading industry stock prices based on a hybrid time-series forecast model","volume":"13","author":"M-C Tsai","year":"2018","journal-title":"PLoS One"},{"key":"pone.0356139.ref019","volume-title":"Introduction to time series analysis and forecasting","author":"DC Montgomery","year":"2015"},{"key":"pone.0356139.ref020","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/j.irfa.2014.02.006","article-title":"Textual sentiment in finance: A survey of methods and models","volume":"33","author":"C Kearney","year":"2014","journal-title":"Int Rev Financ Analys"},{"key":"pone.0356139.ref021","doi-asserted-by":"crossref","first-page":"111","DOI":"10.1016\/j.eswa.2016.11.022","article-title":"Company event popularity for financial markets using Twitter and sentiment analysis","volume":"71","author":"M Daniel","year":"2017","journal-title":"Exp Syst Appl"},{"issue":"1","key":"pone.0356139.ref022","doi-asserted-by":"crossref","first-page":"36","DOI":"10.1108\/IJEFM-06-2020-0034","article-title":"Customers\u2019 experience of purchasing event tickets: mining online reviews based on topic modeling and sentiment analysis","volume":"12","author":"K Celuch","year":"2020","journal-title":"IJEFM"},{"key":"pone.0356139.ref023","unstructured":"Todd A. Financial sentiment beyond text: a multimodal approach to understanding financial market dynamics and investor behaviours. Preprint. 2025. doi: 10.48730\/21mt-gw93"},{"key":"pone.0356139.ref024","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1016\/j.dss.2014.08.001","article-title":"Analyzing firm-specific social media and market: A stakeholder-based event analysis framework","volume":"67","author":"S Jiang","year":"2014","journal-title":"Decis Support Syst"},{"key":"pone.0356139.ref025","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1109\/WI-IAT.2013.48","article-title":"Stock prediction using event-based sentiment analysis.","volume-title":"2013 IEEE\/WIC\/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT)","author":"M Makrehchi","year":"2013"},{"issue":"1","key":"pone.0356139.ref026","doi-asserted-by":"crossref","first-page":"372","DOI":"10.1007\/s12559-021-09819-8","article-title":"Does Twitter Affect Stock Market Decisions? Financial Sentiment Analysis During Pandemics: A Comparative Study of the H1N1 and the COVID-19 Periods","volume":"14","author":"D Valle-Cruz","year":"2022","journal-title":"Cognit Comput"},{"key":"pone.0356139.ref027","unstructured":"Qin J. MSMF: Multi-scale multi-modal fusion for enhanced stock market prediction. arXiv preprint arXiv:240907855. 2024. doi: 10.48550\/arXiv.2409.07855"},{"issue":"5","key":"pone.0356139.ref028","first-page":"1","article-title":"Enhanced sentiment analysis for financial markets using transformer-based models and multi-modal data fusion","volume":"12","author":"S Yadav","year":"2024","journal-title":"Int J Innov Res Eng Multidiscip Phys Sci"},{"key":"pone.0356139.ref029","doi-asserted-by":"crossref","first-page":"3375","DOI":"10.1109\/TMM.2022.3160060","article-title":"Multimodal Sentiment Analysis With Image-Text Interaction Network","volume":"25","author":"T Zhu","year":"2023","journal-title":"IEEE Trans Multimedia"},{"key":"pone.0356139.ref030","unstructured":"Ai L, School TN, Ji S, Song Z, Zhong F, Jia J, et al. Chinese Stock Prediction Based on a Multi-Modal Transformer Framework: Macro-Micro Information Fusion. arXiv preprint arXiv:250116621. 2025. doi: 10.48550\/arXiv.2501.16621"},{"key":"pone.0356139.ref031","doi-asserted-by":"crossref","first-page":"108606","DOI":"10.1016\/j.engappai.2024.108606","article-title":"Multi-modal transform-based fusion model for new product sales forecasting","volume":"133","author":"X Li","year":"2024","journal-title":"Eng Appl Artific Intell"},{"issue":"9","key":"pone.0356139.ref032","doi-asserted-by":"crossref","DOI":"10.1007\/s40747-025-02023-3","article-title":"Stock movement prediction with multimodal stable fusion via gated cross-attention mechanism","volume":"11","author":"C Zong","year":"2025","journal-title":"Complex Intell Syst"},{"issue":"1","key":"pone.0356139.ref033","article-title":"Stock prediction with improved feedforward neural networks and multimodal fusion","volume":"4","author":"Y Wang","year":"2025","journal-title":"J Comput Technol Softw"},{"issue":"1","key":"pone.0356139.ref034","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1007\/s10489-024-05894-0","article-title":"Multimodal market information fusion for stock price trend prediction in the pharmaceutical sector","volume":"55","author":"H Wang","year":"2025","journal-title":"Appl Intell"},{"key":"pone.0356139.ref035","unstructured":"Taylor K, Ng J. Natural language processing and multimodal stock price prediction. arXiv preprint arXiv:240101487. 2024. doi: 10.48550\/arXiv.2401.01487"},{"key":"pone.0356139.ref036","doi-asserted-by":"crossref","first-page":"110211","DOI":"10.1016\/j.patcog.2023.110211","article-title":"Multimodal multiscale dynamic graph convolution networks for stock price prediction","volume":"149","author":"R Liu","year":"2024","journal-title":"Pattern Recognit"}],"container-title":["PLOS One"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0356139","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T17:36:24Z","timestamp":1790789784000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0356139"}},"subtitle":[],"editor":[{"given":"Issa","family":"Atoum","sequence":"first","affiliation":[{"name":"Philadelphia University","place":["JORDAN"]}],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2026,9,30]]},"references-count":36,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2026,9,30]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0356139","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,30]]}}}