Design of a Text-Mining Model Based on ParsBERT and a Financial Sentiment Lexicon for Extracting Stock-Selection Signals from Board of Directors’ Activity Reports: Evidence from the Tehran Stock Exchange
Keywords:
Data Envelopment Analysis, Stock selection, Support Vector Machine, Sentiment analysis; ParsBERT; Board of Directors' activity report, Text miningAbstract
Objective: This study aimed to design and validate a multilayer text-mining model for converting board of directors’ activity reports of Tehran Stock Exchange-listed firms into quantitative stock-selection signals and to test the economic value of combining these signals with accounting information.
Methodology: This applied, ex post facto study examined 330 firms listed on the Tehran Stock Exchange, from which 161 firms were selected through systematic elimination for the 2009–2023 period. The four-layer model comprised Persian-text preprocessing using Hazm, development of a domain-specific financial sentiment lexicon incorporating negation and intensification controls, polarity classification using ParsBERT, and conversion of textual indicators into calibrated probability scores using a support vector machine with Platt calibration. Three portfolios were constructed using textual information, accounting information, and their combination. Portfolio efficiency was measured using the slacks-based measure of data envelopment analysis. The study hypothesis was tested using Welch’s t-test, a 95% confidence interval, and Cohen’s d effect size.
Findings: Welch’s t-test demonstrated that the hybrid portfolio achieved significantly greater efficiency than the text-based portfolio, with a mean efficiency difference of 0.354 (t=2.48, df=19.8, p=0.022). The 95% confidence interval for the mean difference ranged from 0.056 to 0.652 and excluded zero. Cohen’s d was 1.06, indicating a large effect and supporting the research hypothesis. Sensitivity analyses involving alternative risk-free rates, alternative risk definitions, and exclusion of 2020 and 2021 did not alter the direction of the findings.
Conclusion: Textual signals extracted from board activity reports provide greater economic value when integrated with accounting information rather than used independently; accordingly, combining ParsBERT-based natural language processing with fundamental accounting indicators can provide a more effective framework for stock-selection decisions in the Iranian capital market.
Downloads
References
Ali, M. (2023). A Study on Financial Literacy, Investors’ Sentiment, and Financing Decisions With the Moderating Role of Investors’ Experience: Evidence From Pakistan. Abcief, 3(1), 15-32. https://doi.org/10.62019/abcief.v3i1.34
Amin, M. S. (2024). Harmonizing Macro-Financial Factors and Twitter Sentiment Analysis in Forecasting Stock Market Trends. Journal of Computer Science and Technology Studies, 6(1), 58-67. https://doi.org/10.32996/jcsts.2024.6.1.7
Ashtiani, M. N., & Raahemi, B. (2023). News-based intelligent prediction of financial markets using text mining and machine learning: A systematic literature review. Expert Systems with Applications, 217, 119509. https://doi.org/10.1016/j.eswa.2023.119509
Biancone, P., Brescia, V., Chmet, F., & Lanzalonga, F. (2025). The evolution of integrated popular financial reporting: Toward a digital-driven collaborative approach using sentiment analysis tool. Euromed Journal of Business, 20(5), 75-97. https://doi.org/10.1108/EMJB-11-2023-0298
Bogdan, S., Brmalj, N., & Mujacevic, E. (2023). Impact of liquidity and investor sentiment on herd behavior in cryptocurrency market. International Journal of Financial Studies, 11(3), 97.
Chung, M. H., & Chang, Y. K. (2024). Financial Reporting Complexity, Investor Sentiment, and Stock Prices. Finance Research Letters, 62(1), 1-21. https://doi.org/10.1016/j.frl.2024.105026
Deng, G., Deng, Q., Yan, J., & Li, X. (2026). ESG Sentiment, Investor Behavior, and Corporate Cost of Equity Capital. International Review of Financial Analysis, 109, 104800. https://doi.org/10.1016/j.irfa.2025.104800
Du, K. (2024). Financial Sentiment Analysis: Techniques and Applications. Acm Computing Surveys. https://doi.org/10.1145/3649451
Duxbury, D., & Wang, W. (2024). Investor Sentiment and the Risk-Return Relation: A Two-in-One Approach. European Financial Management, 30, 496-543. https://doi.org/10.1111/eufm.12427
Faccia, A., McDonald, J. A. K., & George, B. (2023). NLP Sentiment Analysis and Accounting Transparency: A New Era of Financial Record Keeping. Computers, 13(1), 5. https://doi.org/10.3390/computers13010005
Farahani, M., Gharachorloo, M., Farahani, M., & Manthouri, M. (2021). ParsBERT: Transformer-based model for Persian language understanding. Neural Processing Letters, 53(6), 3831-3847. https://doi.org/10.1007/s11063-021-10528-4
Gu, C., Guo, X., Adikaram, R., Chan, K. C., & Lu, J. (2023). Treasury Return Predictability and Investor Sentiment. The Journal of Financial Research, 46(4), 905-924. https://doi.org/10.1111/jfir.12342
Hájek, P., & Munk, M. (2023). Speech Emotion Recognition and Text Sentiment Analysis for Financial Distress Prediction. Neural Computing and Applications, 35(29), 21463-21477. https://doi.org/10.1007/s00521-023-08470-8
Jafaei Rahni, M. (2026). Examining the relationship between investor sentiment and the speed of capital structure adjustment considering the role of financial constraints. Quantitative Research in Intelligent Financial Systems, 1(4).
Jawale, P. (2023). Sentiment Analysis for Financial Markets. International Journal for Research in Applied Science and Engineering Technology, 11(12), 535-541. https://doi.org/10.22214/ijraset.2023.57385
Kamath, A. N. (2023). Impact of Personality Traits on Investment Decision-Making: Mediating Role of Investor Sentiment in India. Investment Management and Financial Innovations, 20(3), 200-211. https://doi.org/10.21511/imfi.20(3).2023.17
Karimkhani, M., Mohseni, H., Izadyar, A., & Alibaygi Beni, N. (2023). Investigating the impact of the number of daily cases of the Coronavirus pandemic on the stock market indices of developed countries with the approaches of ARIMA and ARCH models. Transactions on Data Analysis in Social Science, 5(4), 176-184. https://doi.org/10.47176/tdass/2023.176
Maqbool, J., Aggarwal, P., Kaur, R., Mittal, A. K., & Ganaie, I. A. (2023). Stock Prediction by Integrating Sentiment Scores of Financial News and MLP-Regressor: A Machine Learning Approach. Procedia Computer Science, 218, 1067-1078. https://doi.org/10.1016/j.procs.2023.01.086
Maurya, P. K., Bansal, R., & Mishra, A. K. (2025). Investor sentiment and its implication on global financial markets: a systematic review of literature. Qualitative Research in Financial Markets. https://doi.org/10.1108/QRFM-04-2024-0087
Messaoud, D., Ben Amar, A., & Boujelbene, Y. (2023). Investor sentiment and liquidity in emerging stock markets. Journal of Economic and Administrative Sciences, 39(4), 867-891. https://doi.org/10.1108/JEAS-11-2020-0198
Montazeralhaj, N., & Rezaei Shouraki, M. (2023). Investigating the impact of investor sentiment on investment returns and financial performance in companies listed on the Tehran Stock Exchange.
Moreau, L. (2025). Sentiment, Readability, and Disclosure Quality in Corporate Financial Reporting: A Textual and Behavioral Perspective on Market Information Efficiency. Academic Research Library for International Journal of Computer Science & Information System, 10(11), 119-123.
Nuriksan, S., & Nikmah, N. (2025). Financial News Sentiment and Investor Confidence: Determinants of Stock Price Volatility in IDX30. Journal of Humanities Social Sciences and Business (Jhssb), 4(3), 493-506. https://doi.org/10.55047/jhssb.v4i3.1648
Rahmanian Koshki, A., & Saadat, A. (2023). The impact of investor sentiment on returns, cash flows, discount rates, and performance of companies listed on the Tehran Stock Exchange. Quarterly Journal of Financial and Economic Policies, 11(41), 43-79. https://qjfep.ir/article-1-1425-fa.html
Sakariyahu, R., Lawal, R., Adigun, R., Paterson, A., & Johan, S. (2024). One Crash, Too Many: Global Uncertainty, Sentiment Factors and Cryptocurrency Market. Journal of International Financial Markets, Institutions and Money, 94. https://doi.org/10.1016/j.intfin.2024.102028
Shah, S. S., Qureshi, F., & Memon, F. A. (2024). Financial literacy and investment behavior of individuals in Pakistan: Evidence from an Environment prone to religious sentiment. Journal of Behavioral and Experimental Finance, 44, 138-155. https://doi.org/10.1016/j.jbef.2024.100974
Shakeri Ardakani, M. S., Arefmanesh, Z., & Bozorg, M. M. (2025). The effect of corporate social responsibility on financial performance: The moderating role of investor sentiment. Accounting Advances, Shiraz University, 17(88), 225-261.
Taftiyan, A., & Bazrafshan Poor, R. (2023). Firm's Financial Risk and Risk Sentiment in Annual Reports: Evidence from Companies Listed in the Tehran Stock Exchange Using a Static-and-Dynamic Approach. Journal of Asset Management and Financing, 11(1), 121-142. https://amf.ui.ac.ir/article_27627.html
Taftiyan, A., Mansuri Mohammad Abadi, F., & Abdollahi Asad Abaadi, A. (2023). The economic consequence of Risk Sentiment in annual reports using dynamic models. Empirical Studies in Financial Accounting, 19(76), 161-187. https://qjma.atu.ac.ir/article_15528.html
Vu, L. T. (2023). Sentiments Extracted From News and Stock Market Reactions in Vietnam. International Journal of Financial Studies, 11(3), 101. https://doi.org/10.3390/ijfs11030101
Vuong, N. B. (2022). Investor sentiment, corporate social responsibility, and financial performance: Evidence from Japanese companies. Borsa Istanbul Review, 22(5), 911-924. https://doi.org/10.1016/j.bir.2022.06.010
Zare Bahman-Miri, M. J., Nazari Shams-Abadi, M. J., & Beikri, A. (2022). Social Responsibility and Investor Sentiment with a Simultaneous Equations Approach. Financial Accounting Research, 12(1), 61-80.
Zhong, N., & Ren, J. (2022). Using Sentiment Analysis to Study the Relationship Between Subjective Expression in Financial Reports and Company Performance. Frontiers in psychology, 13. https://doi.org/10.3389/fpsyg.2022.949881
Zhou, K., & Park, J. (2025). A hybrid framework for financial fraud detection: Integrating the Dechow F-Score with financial news sentiment analysis. INFORMS Journal on Applied Analytics, 55(1), 33-51.
Downloads
Publication Timeline
- Submitted
- Revised
- Accepted
Issue
Section
License
Copyright (c) 1404 Hossein Nabieiboroujeni, Hamidreza Jafari Dehkordi (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
