Financial Video Analysis Using Natural Language Processing: An Empirical Study of Stock Forecast
Keywords:
natural language processing, unstructured data, financial data analysis, ARIMA, LLMAbstract
The proliferation of unstructured financial video content presents a significant challenge for traditional investment analysis. Natural Language Processing (NLP) offers a promising solution for extracting value from this data. This empirical study investigates whether NLP technologies can automatically extract, structure, and validate actionable investment insights from financial videos. We propose an automated pipeline using video transcription services and Large Language Models (LLMs). The methodology was tested on 22 YouTube financial analysis videos focusing on Amazon (AMZN) and Google (GOOG). The ChatGPT-4 model processed transcripts to extract stock tickers, risk levels, and price forecasts into a structured JSON format. The system achieved 100% accuracy in company recognition and filtering irrelevant content. Empirical validation against actual market data revealed an overall forecast accuracy of 85% (90% for AMZN, 70% for GOOG). This NLP approach also outperformed traditional ARIMA time-series models. The findings confirm that NLP can feasibly automate the analysis of financial video, transforming unstructured media into validated, structured data to support investment decisions.
References
F. Duarte, “Amount of Data Created Daily (2024),” Exploding Topics, Feb. 23, 2025. https://explodingtopics.com/blog/data-generated-per-day.
T. Tian, R. Cooper, A. Vasilakos, J. Deng, Q. Zhang, “From Data to Strategy: A Public Market Framework for Competitive intelligence,” Expert Systems With Applications, vol. 296, 129061, 2025. https://doi.org/10.1016/j.eswa.2025.129061.
J. Chou, K. Lin, T. Pham, “AI-fused construction portfolio investment system with risk hedging using machine learning and long-short strategies,” Applied Soft Computing, vol. 183, 113555, 2025. https://doi.org/10.1016/j.asoc.2025.113555.
K. Lipianina-Honcharenko, C. Wolff, A. Sachenko, O. Desyatnyuk, S. Sachenko, I. Kit. “Intelligent information system for product promotion in internet market,” Applied Sciences, vol. 13, issue 17, 9585, 2023. https://doi.org/10.3390/app13179585.
N. Maslej, L. Fattorini, R. Perrault, Y. Gil, V. Parli, N. Kariuki, E. Capstick, A. Reuel, E. Brynjolfsson, J. Etchemendy, K. Ligett, T. Lyons, J. Manyika, J.C. Niebles, Y. Shoham, R. Wald, T. Walsh, A. Hamrah, L. Santarlasci, J.B. Lotufo, A. Rome, A. Shi, S. Oak, “The AI Index 2025 Annual Report,” AI Index Steering Committee, Institute for Human-Centered AI, Stanford University, Stanford, CA, April 2025. https://doi.org/10.48550/arXiv.2504.07139.
Y. Zhang, Y. Li, W. Wang, “Comparative analysis of investor sentiment and attention in the U.S. and Chinese stock markets: Implications for financial stability,” International Review of Financial Analysis, vol. 109, 104751, 2025. https://doi.org/10.1016/j.irfa.2025.104751
S. Feuerriegel, J. Gordon, “Long-term stock index forecasting based on text mining of regulatory disclosures,” Decision Support Systems, vol. 112, pp. 88–97, 2018. https://doi.org/10.1016/j.dss.2018.06.008.
M. Abdullah, Z. Sulong, M.А.F. Chowdhury, “Explainable deep learning model for stock price forecasting using textual analysis,” Expert Systems With Applications, vol. 249, 123740, 2024. https://doi.org/10.1016/j.eswa.2024.123740.
S. S. Mehrkian, H. Davari-Ardakani, “An integrated model of sentiment analysis and quantitative index data for predicting stock market trends: A case study of the Tehran stock exchange,” Expert Systems with Applications, vol. 269, 126298, 2024. https://doi.org/10.1016/j.eswa.2024.126298.
S. García-Méndez, F. De Arriba-Pérez, A. Barros-Vila, F. J. González-Castaño, “Targeted aspect-based emotion analysis to detect opportunities and precaution in financial Twitter messages,” Expert Systems with Applications, vol. 218, 119611, 2023. https://doi.org/10.1016/j.eswa.2023.119611.
J. Jiang, K. K. Bandeli, K. Srinivasan, “Dynamic model selection in enterprise forecasting systems using sequence modeling,” Decision Support Systems, vol. 193, 114439, 2025. https://doi.org/10.1016/j.dss.2025.114439.
V. Iatsiuta, V. Kobets, “Transforming business communication with solutions based on artificial intelligence technologies with support for natural language processing,” Science and Innovation, vol. 21, issue 5, pp. 126–143, 2025. https://doi.org/10.15407/scine21.05.126.
O. Ivanov, V. Kobets, “Integrating semantic analysis and financial indicators of business reports for predicting stock prices,” In Communications in Computer and Information Science, 2025, pp. 297–308, 2025. https://doi.org/10.1007/978-3-031-81372-6_22.
O. Ivanov, V. Kobets, “Future financial impact analysis from sentiment and indicators analysis,” Computational Economics, vol. 66, pp. 4959–4985, 2025. https://doi.org/10.1007/s10614-025-10891-7.
P. K. Naik, J. Soni, “Asymmetric and temporal effects of investor sentiment and institutional trading behavior on returns and volatility: evidence from the Indian stock market,” Review of Behavioral Finance, vol. 18, no. 2, pp. 186-214, 2026. https://doi.org/10.1108/rbf-09-2025-0387.
T. Boufateh, Z. Saadaoui, Z. Jiao, “On the time-varying responses of Fintech stock returns to geopolitical, financial and market sentiment shocks,” The Quarterly Review of Economics and Finance, vol. 101, 101951, 2025. https://doi.org/10.1016/j.qref.2024.101951
V. Iatsiuta, V. Kobets, “Generalized AI-based solutions with NLP support for processing business requests,” In Communications in computer and information science pp. 233–245, 2025. https://doi.org/10.1007/978-3-031-81372-6_17.
I-C. Chiu, M.-W. Hung, “Finance-specific large language models: Advancing sentiment analysis and return prediction with LLaMA 2,” Pacific-Basin Finance Journal, vol. 90, 102632, 2025. https://doi.org/10.1016/j.pacfin.2024.102632.
A. H. Huang, H. Wang, and Y. Yang, “FinBERT: A large language model for extracting information from financial text,” Contemporary Accounting Research, vol. 40, no. 2, pp. 806-841, 2022. https://doi.org/10.1111/1911-3846.12832.
O. Romanko, A. Narayan, and R. H. Kwon, “ChatGPT-based investment portfolio selection,” Operations Research Forum, vol. 4, no. 4, 2023. https://doi.org/10.1007/s43069-023-00277-6.
K. Kirtac and G. Germano, “Sentiment trading with large language models,” Finance Research Letters, vol. 62, pp. 105227–105227, 2024. https://doi.org/10.1016/j.frl.2024.105227.
F. Sayyed, R. Argiddi and S. Apte, “Generating recommendations for stock market using collaborative filtering,” Int. J. Comput. Eng. Sci., vol. 3, pp. 46-49, 2013.
Q. Liu, X. Wang, and Y. Du, “The weekly cycle of investor sentiment and the holiday effect – An empirical study of Chinese stock market based on natural language processing,” Heliyon, vol. 8, no. 12, e12646, Dec. 2022. https://doi.org/10.1016/j.heliyon.2022.e12646.
J.M. Oliveira, P. Ramos, J.M. Oliveira, P. Ramos, “Evaluating the effectiveness of time series transformers for demand forecasting in retail,” Mathematics, vol. 12, 2728, 2024. https://doi.org/10.3390/MATH12172728.
Y. Ensafi, S.H. Amin, G. Zhang, B. Shah, “Time-series forecasting of seasonal items sales using machine learning – a comparative analysis,” International Journal of Informational Management Data Insights, vol. 2, issue 1, 100058, 2022. https://doi.org/10.1016/j.jjimei.2022.100058.
L. Feng and A. Sinchai, “Deep context-attentive transformer transfer learning for financial forecasting,” Peer Journal of Computer Science, vol. 11, e2983, 2025. https://doi.org/10.7717/peerj-cs.2983.
S. W. K. Chan and M. W. C. Chong, “Sentiment analysis in financial texts,” Decision Support Systems, vol. 94, pp. 53-64 2017. https://doi.org/10.1016/j.dss.2016.10.006.
D. Tiwari et al., “Attention-augmented hybrid CNN-LSTM model for social media sentiment analysis in cryptocurrency investment decision-making,” Springer Nature, vol. 15, 33201, 2025. https://doi.org/10.1038/s41598-025-18245-x.
A. Erfani and H. Khanjar, “Large language models for construction risk classification: A comparative study,” Buildings, vol. 15, no. 18, p. 3379, 2025. https://doi.org/10.3390/buildings15183379.
D. Noor Mohammadzadeh Maleki, S. Abbaskhani, A. Farhadi, A. Zamanifar, “Artificial intelligence methods for financial market prediction: A systematic review,” Computers & Electrical Engineering, 134, 111110, 2026. https://doi.org/10.1016/j.compeleceng.2026.111110
“Create and Multistream Live Video,” Restream. [Online]. Available at: https://restream.io.
O. I. Beley, S. I. Sachenko, “The information system of control risks,” In Proceedings of the International Workshop on Intelligent Data Acquisition and Advanced Computing Systems: Technology and Applications. IDAACS'2001 (No.01EX510), pp. 270-274, 2001. https://10.1109/IDAACS.2001.942029.
P. Q. Dao, M. Roantree, T. B. Nguyen-Tat, and V. M. Ngo, “Exploring multimodal sentiment analysis models: A comprehensive survey,” Aug. 2024, https://doi.org/10.20944/preprints202408.0127.v1.
“Amazon.com, Inc. (AMZN) Stock Historical Prices & Data - Yahoo Finance,” [Online]. Available at: https://finance.yahoo.com/quote/AMZN/history.
Downloads
Published
How to Cite
Issue
Section
License
International Journal of Computing is an open access journal. Authors who publish with this journal agree to the following terms:• Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
• Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
• Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
