پیش‌بینی روند سهام با استفاده از شاخص احساسات و SVM بهبودیافته با تابع هزینه مبتنی بر آنتروپی احساسات
محورهای موضوعی : مهندسی برق و کامپیوتر
مهین یعقوب زاده
1
,
عباس ابراهیمی مقدم
2
*
,
مرتضی خادمی
3
,
هادی صدوقی یزدی
4
1 - گروه برق، دانشکده مهندسی، دانشگاه فردوسی مشهد ،مشهد،ایران
2 - گروه برق، دانشکده مهندسی، دانشگاه فردوسی مشهد ،مشهد،ایران
3 - گروه برق، دانشکده مهندسی، دانشگاه فردوسی مشهد ،مشهد،ایران
4 - گروه کامپیوتر، دانشکده مهندسی، دانشگاه فردوسی مشهد ،مشهد،ایران
کلید واژه: پیش‌بینی بازار سهام, تحلیل احساسات, Fin-BERT, SVM,
چکیده مقاله :
پیش‌بینی بازار سهام همیشه مورد توجه پژوهشگران بوده است. پیشرفت در زمینه هوش مصنوعی و الگوریتم‌های یادگیری ماشین باعث شده که بتوان از داده‌های متنی در کنار داده‌های عددی، جهت پیش‌بینی و عملکرد بهتر بازار بهره برد. در این پژوهش جهت پیش‌بینی روند شاخص بازار سهام نیویورک (NYSE) از داده‌های عددی، داده‌های متنی و یک مدل یادگیری ماشین استفاده شده است. ورودی مدل اولاً داده‌های عددی و ثانیاً نتایج تحلیل احساسات از متن‌های استخراج‌شده از شبکه X است. تحلیل احساسات با یک الگوریتم خاص مبتنی بر یادگیری ماشین (Fin-BERT) انجام شده است. همچنین برای بهبود نتایج پیش‌بینی، در طبقه‌بند پیشنهادی (SVM) دانش پیشینی که در مورد توزیع داده‌ها موجود است در تابع هزینه SVM وارد شده است. این دانش از طریق محاسبه آنتروپی احساسات به دست می‌آید. نتایج آزمایش‌ها نشان می‌دهند که با در نظر گرفتن آنتروپی احساسات در تابع هزینه مدل، نتایج پیش‌بینی بهبود می‌یابد.
Stock market prediction has always been a focus of researchers. Advances in artificial intelligence and machine learning algorithms have enabled the use of textual data alongside numerical data for better stock market forecasting and performance. In this research, to predict the trend of the NewYork Stock Exchange (NYSE) index, numerical data, textual data, and a machine learning model were employed. The model's input includes numerical data as well as the results of sentiment analysis from texts extracted from X (formerly Twitter). Sentiment analysis is performed using a specific machine learning algorithm, Fin-BERT. Additionally, to improve prediction results, prior knowledge of data distribution is incorporated into the cost function of the proposed classifier (SVM). This knowledge is obtained through the calculation of sentiment entropy. Experimental results show that incorporating sentiment entropy into the model's cost function improves prediction performance.
[1] S. Usmani and J. A. Shamsi, "News sensitive stock market prediction: literature review and suggestions," Peer J. Comput. Sci., vol. 7, no. 4, Article ID: e490, 2021.
[2] F. G. Monteiro and D. R. Ferreira, "How much does stock Prediction improve with sentiment analysis?" in Proc. 5th ECML PKDD Workshop, pp. 16-31, Ghent, Belgium, 18-18 Sept. 2020.
[3] O. Bustos, "Stock market movement forecast: a systematic review," Expert Syst. Appl., vol. 156, Article ID: 113464, Oct. 2020.
[4] K. Fataliyev, A. Chivukula, M. Prasad, and W. Liu, Stock Market Analysis with Text Data: A Review, arXiv preprint arXiv:2106.12985.
[5] M. Rodríguez-Ibánez, A. Casánez-Ventura, F. Castejón-Mateos, and P.-M. Cuenca-Jiménez, "A review on sentiment analysis from social media platforms," Expert Systems with Applications, vol. 223, Article ID: 119862, 2021.
[6] P. Sudhir and V. D. Suresh, "Comparative study of various approaches, applications and classifiers for sentiment analysis," in Glob. Transitions Proc., vol. 2, no. 2, pp. 205-211, Nov. 2021.
[7] C. Michele, et al., "Machine learning sentiment analysis, COVID-19 news and stock market reactions," Research in International Business and Finance, vol. 64, Article ID: 101881, Jan. 2023.
[8] D. Kelvin, et al., "Financial sentiment analysis: techniques and applications," ACM Computing Surveys, vol. 56, no. 9, Article ID: 220, Sept. 2024.
[9] D. Nabanita, et al., "Effect of public sentiment on stock market movement prediction during the COVID-19 outbreak," Social Network Analysis and Mining, vol. 12, no. 1, Article ID: 92, 2022.
[10] N. Rouf, et al., "Stock market prediction using machine learning techniques: a decade survey on methodologies, recent developments, and future directions," Electron., vol. 10, no. 21, Article ID: 2127, 2021.
[11] N. Jing, Z. Wu, and H. Wang, "A hybrid model integrating deep learning with investor sentiment analysis for stock price prediction," Expert Syst. Appl., vol. 178, Article ID: 115019, Sept. 2021.
[12] D. Kumar, P. K. Sarangi, and R. Verma, "A systematic review of stock market prediction using machine learning and statistical techniques," in Mater. Today Proc., vol. 49, pt. 8., pp. 3187-3191, 2022.
[13] C. Chou, J. Park, and E. Chou, "Predicting stock closing price after COVID-19 based on sentiment analysis and LSTM," in Proc. IEEE Adv. Inf. Technol. Electron. Autom. Control Conf., pp. 2752-2756, Chongqing, China, 12-14 Mar. 2021.
[14] M. Peji, Text Mining for Big Data Analysis in Financial Sector: A Literature Review, 2019.
[15] K. Mishev, A. Gjorgjevikj, I. Vodenska, L. T. Chitkushev, and D. Trajanov, "Evaluation of sentiment analysis in finance: from lexicons to transformers," IEEE Access, vol. 8, pp. 131662-131682, 2020.
[16] Y. Qi, "Stock prediction under COVID-19 based on LSTM," in Proc. IEEE Asia-Pacific Conference on Image Processing, Electronics and Computers, pp. 93-98, Dalian, China, 4-16 Apr. 2021.
[17] N. Christina and C. Tjortjis, "A methodology for stock movement prediction using sentiment analysis on Twitter and stocktwits data," in Proc. 6th South-East Europe Design Automation, Computer Engineering, Computer Networks and Social Media Conf., vol. 7 pp., Preveza, Greece, 24-26 Sept.2021.
[18] C. Liapis, A. Karanikola, and S. Kotsiantis, "Investigating deep stock market forecasting with sentiment analysis," Entropy, vol. 25, no. 2, Article ID: 219, Feb. 2023.
[19] W. Zhaoxia, et al., "Learning-based stock trending prediction by incorporating technical indicators and social media sentiment," Cognitive Computation, vol. 15, no. 3, pp. 1092-1102, 2023.
[20] N. Zaman, et al., "Stock market prediction based on machine learning and social sentiment analysis," TechRxiv. Mar. 27, 2023., DOI: 10.36227/techrxiv.22315069.v1.
[21] D. Narayana, et al., "Stock price prediction using sentiment analysis and deep learning for Indian markets," arXiv preprint arXiv:2204.05783, 2022.
[22] K. Jihwan, H. Kim, and S. Y. Choi, "Forecasting the S&P 500 index using mathematical-based sentiment analysis and deep learning models: a FinBERT transformer model and LSTM," Axioms, vol. 12, no. 9, Article ID: 835, Sept. 2023.
[23] Q. Xiao and B. Ihnaini, "Stock trend prediction using sentiment analysis," Peer J. Computer Science, vol. 9, Article ID; e1293, 2023.
[24] Y. Qiu, Z. Song, and Z. Chen, "Short-term stock trends prediction based on sentiment analysis and machine learning," Soft Comput., vol. 26, no. 5, pp. 2209-2224, Mar. 2022.
[25] J. Liu, J. Leu, and S. Holst, "Stock price movement prediction based on stocktwits investor sentiment using FinBERT and ensemble SVM," Peer J. Computer Science, vol. 9, Article ID; e1403, 2023.
[26] R. Ren, D. D. Wu, and D. D. Wu, "Forecasting stock market movement direction using sentiment analysis and support vector machine," IEEE Syst. J., vol. 13, no. 1, pp. 760-770, Mar. 2019.