تحلیل احساسات برای پیش¬بینی بازار بورس با شبکه عصبی ژرف: مطالعه موردی برای پایگاه داده سهام شرکت¬های بین-المللی
محورهای موضوعی :حکیمه منصور 1 , سعیده ممتازی 2 , کامران لایقی 3
1 - دانشجو
2 - استادیار
3 - دانشگاه آزاد
کلید واژه: تحلیل احساسات, شبکه عصبی ژرف, مدل¬های شبکه عصبی پیچشی, شبکه حافظه کوتاه-مدت بلند, شبکه اقتصاد مالی. بازار سهام,
چکیده مقاله :
امروزه تحلیل احساسات به عنوان یکی از ارکان اصلی در زمینه های مختلف از جمله مدیریت مالی، بازاریابی، پیش بینی تغییرات اقتصادی درکشورهای مختلف بکار گرفته می شود. به منظور ساخت یک تحلیل گر احساسات بر مبنای نظرات کاربران در رسانه های اجتماعی، بعد از استخراج ویژگی های مهم بین کلمات توسط شبکه پیچشی، از شبکه حافظه کوتاه-مدت بلند استفاده می کنیم تا رابطه نهفته در دنبالـه ای از کلمات را کشف و ویژگی های مهم متن را استخراج نماییم. با کشف ویژگی های استخراج شده جدید توسط شبکه برگشتی با حافظه کوتاه-مدت بلند، توانایی مدل پیشنهادی در طبقه بندی ارزش سهام شرکت ها افزایش می یابد و در نهایت به پیش بینی سهام بورس در روز بعد براساس تحلیل احساسات می پردازیم. اﯾﻦ ﭘﮋوﻫﺶ ﺑﺮ اﺳﺎس دادهﻫﺎی ﻣﻘﺎﻟﻪ اﻧﮕﻮﯾﺎن و همکارانش اﻧﺠﺎم ﮔﺮﻓﺘﻪ اﺳﺖ و تنها از اﻃﻼﻋﺎت احساسی ﻣﺮدم در شبکه-ﻫﺎی اجتماعی ﺑﺮای ﭘﯿﺶبینی ﺳﻬﺎم اﺳﺘﻔﺎده می کند. با توجه به اینکه هر یک از پیـام های کاربـران را در 5 کلاس های احساسی طبقه بندی می کنیم، بنابراین این مدل ارزش سهام روز بعد را به دو حالت بالا یا پایین بودن آن می تواند پیش بینی کند. ساختار پیشنهادی شامل 21 لایه شبکه عصبی ژرف و متشکل از شبکه های پیچشی و حافظه کوتاه-مدت بلند است که برای پیش بینی سهام بورس 18 شرکت پیاده سازی شده است. اگرچه برخی مدل های ارائه شده قبل، از تحلیل احساسات به منظور پیش بینی بازار سرمایه بهره گرفته اند، اما از روش های ترکیبی و پیشرفته در شبکه های ژرف با میزان دقت پیش بینی بالا بهره نبرده اند. سنجش نتایج روش پیشنهادی با دیگر مطالعات نشان داده که عملکرد روش پیشنهادی در مقایسه با 8 روش دیگر، بطور قابل ملاحظه ای خوب بوده و در معیار ارزیابی صحت در پیش‌بینی روزانه سهام با بهبود 8/19 درصدی نسبت به مدل شبکه پیچشی ژرف، 5/24 درصدی نسبت به مدل پیشنهادی انگویان و همکاران (2015) و 94/23 درصدی نسبت به مدل پیشنهادی درخشان و همکاران (2019) از روش‌های رقیب پیشی بگیرد.
Emotional analysis is used as one of the main pillars in various fields such as financial management, marketing and economic changes forecasting in different countries. In order to build an emotion analyzer based on users' opinions on social media, after extracting important features between words by convolutional layers, we use LSTM layers to establish the relationship behind the sequence of words and extract the important features of the text. With discovery of new features extracted by LSTM, the ability of the proposed model to classify the stock values of companies increases. This article is based on the data of Nguyen et al. (2015) and uses only the emotional information of people in social networks to predict stocks. Given that we categorize each user's message into one of the emotional classes "Strong Buy", "Buy", "Hold", "Sell", "Strong Sell", this model can predict the stock value of the next day, whether it will be high or low. The proposed structure consisted of 21 layers of neural networks consisting of convolutional neural networks and long short-term memory network. These networks were implemented to predict the stock markets of 18 companies. Although some of the previously presented models have used for emotion analysis to predict the capital markets, the advanced hybrid methods have not been performed in deep networks with a good forecasting accuracy. The results were compared with 8 baseline methods and indicate that the performance of the proposed method is significantly better than other baselines. For daily forecasts of stocks changes, it resulted in 19.80% improvement in the prediction accuracy, compared with the deep CNN, and 24.50% and 23.94% improvement compared with the models developed by Nguyen et al. (2015) and Derakhshan et al. (2019), respectively.
نصراله پور، ف.، بحرانی، م.، بیجن خان، م. (1398). استفاده از روش‌های یادگیری ماشین جهت پیش‌بینی نوسانات نرخ ارز در متون خبری اقتصادی فارسی. اولین همایش ملی هوش مصنوعی و محاسبات نرم در علوم انسانی، مقاله کامل چاپ شده،
Akhtar, M.S., Kumar, A., Ekbal, A. and Bhattacharyya, P., 2016, December. A hybrid deep learning architecture for sentiment analysis. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers (pp. 482-493).
Bollen, J., Mao, H. and Zeng, X., 2011. Twitter mood predicts the stock market. Journal of computational science, 2(1):1–8.
Chan, W.S., 2003. Stock price reaction to news and no-news: drift and reversal after headlines. Journal of Financial Economics, 70(2):223–260.
Chun, J., Ahn, J., Kim, Y. and Lee, S., 2020. Using Deep Learning to Develop a Stock Price Prediction Model Based on Individual Investor Emotions. Journal of Behavioral Finance, pp.1-10.
Chen, W., Zhang, Y., Yeo, C.K., Lau, C.T. and Lee, B.S., 2017, September. Stock market prediction using neural network through news on online social networks. In 2017 international smart cities conference (ISC2) (pp. 1-6). IEEE.
Chong, E., Han, C. and Park, F.C., 2017. Deep learning networks for stock market analysis and prediction: Methodology, data representations, and case studies. Expert Systems with Applications, 83, pp.187-205.
Derakhshan, A. and Beigy, H. 2019. Sentiment analysis on stock social media for stock price movement prediction. Engineering Applications of Artificial Intelligence 85 (2019): 569-578
Gers, F.A., Schmidhuber, J. and Cummins, F., 1999. Learning to forget: Continual prediction with LSTM.
Goularas, D. and Kamis, S., 2019, August. Evaluation of deep learning techniques in sentiment analysis from Twitter data. In 2019 International Conference on Deep Learning and Machine Learning in Emerging Applications (Deep-ML) (pp. 12-17). IEEE.
Habimana, O., Li, Y., Li, R., Gu, X. and Yu, G., 2020. Sentiment analysis using deep learning approaches: an overview. Science China Information Sciences, 63(1), pp.1-36.
Hochreiter, S. and Schmidhuber, J., 1997. Long short-term memory. Neural computation, 9(8), pp.1735-1780.
Jin, Z., Yang, Y., & Liu, Y. (2019). Stock closing price prediction based on sentiment analysis and LSTM. Neural Computing and Applications. doi:10.1007/s00521-019-04504-2
Kim, Y., 2014. Convolutional neural networks for sentence classification, In Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP). Doha, Qatar. Association for Computational Linguistics. PP: 1746-1751.
LeCun, Y., Bottou, L., Bengio, Y. and Haffner, P., 1998. Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11), pp.2278-2324.
Li, Y. and Pan, Y., 2020. A novel ensemble deep learning model for stock prediction based on stock prices and news. arXiv preprint arXiv:2007.12620.
Liu, Y., Qin, Z., Li, P. and Wan, T., 2017, June. Stock volatility prediction using recurrent neural networks with sentiment analysis. In International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems (pp. 192-201). Springer, Cham.
Liu, B., 2020. Sentiment analysis: Mining opinions, sentiments, and emotions. Cambridge university press.
Luo, X., Zhang, J. and Duan, W., 2013. Social media and firm equity value. Information Systems Research, 24(1), pp.146-163
Mohan, S., Mullapudi, S., Sammeta, S., Vijayvergia, P. and Anastasiu, D.C., 2019, April. Stock Price Prediction Using News Sentiment Analysis. In 2019 IEEE Fifth International Conference on Big Data Computing Service and Applications (BigDataService) (pp. 205-208). IEEE.
Mohamed Ali, N., Abd El Hamid, M. M. and Youssif, A. 2019. Sentiment analysis for movies reviews dataset using deep learning modes, International Journal of Data Mining & Knowledge Management Process (IJDKP) Vol.9, No.2/3.
Nguyen, T. H., Shirai, K., & Velcin, J., 2015. Sentiment analysis on social media for stock movement prediction. Expert Systems with Applications, 42(24), 9603-9611.
Oh, C. & Sheng, O. (2011), Investigating Predictive Power of Stock Micro Blog Sentiment in Forecasting Future Stock Price Directional Movement., in Dennis F. Galletta & Ting-Peng Liang, ed., 'ICIS' , Association for Information Systems, .
Prabha, M.I. and Srikanth, G.U., 2019, April. Survey of sentiment analysis using deep learning techniques. In 2019 1st International Conference on Innovations in Information and Communication Technology (ICIICT) (pp. 1-9). IEEE.
Ramadhani, A.M. and Goo, H.S. 2017. [IEEE 2017 7th International Annual Engineering Seminar (InAES) - Yogyakarta, Indonesia (2017.8.1-2017.8.2)] 2017 7th International Annual Engineering Seminar (InAES) - Twitter sentiment analysis using deep learning methods. , (), 1–4.
Rambocas, M. and Pacheco, B.G. 2018, “Online sentiment analysis in marketing research: a review”, Journal of Research in Interactive Marketing, 12(2), pp 146–163.
Roberts, H.V., 1959. Stock-market" patterns" and financial analysis: methodological suggestions. The Journal of Finance, 14(1), pp.1-10.
Ruan, Y., Durresi, A. and Alfantoukh, L., 2018. Using Twitter trust network for stock market analysis. Knowledge-Based Systems, 145, pp.207-218.
Sadr, H., Pedram, M.M. and Teshnehlab, M., 2019. A robust sentiment analysis method based on sequential combination of convolutional and recursive neural networks. Neural Processing Letters, 50(3), pp.2745-2761
Sadr, H., Pedram, M.M. and Teshnehlab, M., 2020. Multi-View Deep Network: A Deep Model Based on Learning Features From Heterogeneous Neural Networks for Sentiment Analysis. IEEE Access, 8, pp.86984-86997.
Samat, N.A., Salleh, M.N.M. and Ali, H., 2020, January. The Comparison of Pooling Functions in Convolutional Neural Network for Sentiment Analysis Task. In International Conference on Soft Computing and Data Mining (pp. 202-210). Springer, Cham
Shi, Y., Zheng, Y., Guo, K. and Ren, X., 2020. Stock movement prediction with sentiment analysis based on deep learning networks. Concurrency and Computation: Practice and Experience, p.e6076.
Sukheja, S., Chopra, S. and Vijayalakshmi, M., 2020, March. Sentiment Analysis using Deep Learning–A survey. In 2020 International Conference on Computer Science, Engineering and Applications (ICCSEA) (pp. 1-4). IEEE.
Salloum, S.A., Khan, R. and Shaalan, K., 2020, April. A survey of semantic analysis approaches. In Joint European-US Workshop on Applications of Invariance in Computer Vision (pp. 61-70). Springer, Cham.
Wang, P., Xu, J., Xu, B., Liu, C., Zhang, H., Wang, F. and Hao, H., 2015, July. Semantic clustering and convolutional neural network for short text categorization. In Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 2: Short Papers) (pp. 352-357).
Xu, Y. and Keselj, V., 2019, December. Stock Prediction using Deep Learning and Sentiment Analysis. In 2019 IEEE International Conference on Big Data (Big Data) (pp. 5573-5580). IEEE.
Yu, Y., Duan, W. and Cao, Q., 2013. The impact of social and conventional media on firm equity value: A sentiment analysis approach. Decision support systems, 55(4), pp.919-926.
Yadav, A. and Vishwakarma, D.K., 2020. Sentiment analysis using deep learning architectures: a review. Artificial Intelligence Review, 53(6), pp.4335-4385.
Zhang, Ye, and Byron Wallace. "A sensitivity analysis of (and practitioners’ guide to) convolutional neural networks for sentence classification." arXiv preprint arXiv:1510.03820 (2015).
Zhou Y., 2020. A Review of Text Classification Based on Deep Learning. In Proceedings of the 2020 3rd International Conference on Geoinformatics and Data Analysis (ICGDA 2020). Association for Computing Machinery, New York, NY, USA, 132–136. DOI:https://doi.org/10.1145/3397056.3397082
Zhou, C.; Sun, C.; Liu, Z. & Lau, F. C. M. (2015), 'A C-LSTM Neural Network for Text Classification.’ CoRR abs/1511.08630 .
Zhang, Y., Roller, R. and Wallace, B. C., 2016. Mgnc-cnn: A simple approach to exploiting multiple word embeddings for sentence classification, Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Association for Computational Linguistics, pp.1522-1527
Zhang, L., Wang, S. and Liu, B., 2018. Deep learning for sentiment analysis: A survey. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 8(4), p.e1253
