Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
80 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Do Weibo platform experts perform better at predicting stock market? (2403.00772v1)

Published 12 Feb 2024 in q-fin.ST, cs.AI, cs.LG, and cs.SI

Abstract: Sentiment analysis can be used for stock market prediction. However, existing research has not studied the impact of a user's financial background on sentiment-based forecasting of the stock market using artificial neural networks. In this work, a novel combination of neural networks is used for the assessment of sentiment-based stock market prediction, based on the financial background of the population that generated the sentiment. The state-of-the-art language processing model Bidirectional Encoder Representations from Transformers (BERT) is used to classify the sentiment and a Long-Short Term Memory (LSTM) model is used for time-series based stock market prediction. For evaluation, the Weibo social networking platform is used as a sentiment data collection source. Weibo users (and their comments respectively) are divided into Authorized Financial Advisor (AFA) and Unauthorized Financial Advisor (UFA) groups according to their background information, as collected by Weibo. The Hong Kong Hang Seng index is used to extract historical stock market change data. The results indicate that stock market prediction learned from the AFA group users is 39.67% more precise than that learned from the UFA group users and shows the highest accuracy (87%) when compared to existing approaches.

PDF HTML Abstract
Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Bookmark Chat Bubble Oval Streamline Icon: https://streamlinehq.com Chat (Pro)
Definition Search Book Streamline Icon: https://streamlinehq.com
References (34)
  1. K. R. French, G. W. Schwert, and R. F. Stambaugh, “Expected stock returns and volatility,” Journal of Financial Economics, vol. 19, no. 1, pp. 3–29, 1987.
  2. Y. Xu, Z. Liu, J. Zhao, and C. Su, “Weibo sentiments and stock return: A time-frequency view,” PLOS ONE, vol. 12, no. 7, pp. 1–21, 07 2017. [Online]. Available: https://doi.org/10.1371/journal.pone.0180723
  3. T. O. Sprenger, A. Tumasjan, P. G. Sandner, and I. M. Welpe, “Tweets and trades: The information content of stock microblogs,” European Financial Management, vol. 20, no. 5, pp. 926–957, 2014.
  4. J. Bollen, H. Mao, and X. Zeng, “Twitter mood predicts the stock market,” Journal of computational science, vol. 2, no. 1, pp. 1–8, 2011.
  5. A. Mittal and A. Goel, “Stock prediction using twitter sentiment analysis,” Standford University, CS229 (2011 http://cs229. stanford. edu/proj2011/GoelMittal-StockMarketPredictionUsingTwitterSentimentAnalysis. pdf), vol. 15, 2012.
  6. G. W. Brown and M. T. Cliff, “Investor sentiment and the near-term stock market,” Journal of empirical finance, vol. 11, no. 1, pp. 1–27, 2004.
  7. X. Chu, C. Wu, and J. Qiu, “A nonlinear granger causality test between stock returns and investor sentiment for chinese stock market: a wavelet-based approach,” Applied Economics, vol. 48, no. 21, pp. 1915–1924, 2016.
  8. X. Jin, D. Shen, and W. Zhang, “Has microblogging changed stock market behavior? evidence from china,” Physica A: Statistical Mechanics and its Applications, vol. 452, pp. 151–156, 2016.
  9. H. Peng, E. Cambria, and A. Hussain, “A review of sentiment analysis research in chinese language,” Cognitive Computation, vol. 9, no. 4, pp. 423–435, 2017.
  10. Y. Rao, J. Lei, L. Wenyin, Q. Li, and M. Chen, “Building emotional dictionary for sentiment analysis of online news,” World Wide Web, vol. 17, no. 4, pp. 723–742, 2014.
  11. T. Mikolov, K. Chen, G. S. Corrado, and J. Dean, “Efficient estimation of word representations in vector space,” 2013.
  12. J. Devlin, M.-W. Chang, K. Lee, and K. Toutanova, “Bert: Pre-training of deep bidirectional transformers for language understanding,” arXiv preprint arXiv:1810.04805, 2018.
  13. B. Wuthrich, V. Cho, S. Leung, D. Permunetilleke, K. Sankaran, and J. Zhang, “Daily stock market forecast from textual web data,” vol. 3, 11 1998, pp. 2720 – 2725 vol.3.
  14. M. A. Mittermayer and G. Knolmayer, “Newscats: A news categorization and trading system,” pp. 1002–1007, 2006.
  15. Z. Zhou, J. Zhao, and K. Xu, “Can online emotions predict the stock market in china?” in International conference on web information systems engineering.   Springer, 2016, pp. 328–342.
  16. W. Zhao, F. Wu, Z. Fu, Z. Wang, and X. Zhang, “Sentiment analysis on weibo platform for stock prediction,” in International Conference on Artificial Intelligence and Security.   Springer, 2020, pp. 323–333.
  17. I. Kaastra and M. Boyd, “Designing a neural network for forecasting financial and economic time series,” Neurocomputing, vol. 10, no. 3, pp. 215 – 236, 1996, financial Applications, Part II.
  18. S. Hochreiter and J. Schmidhuber, “Lstm can solve hard long time lag problems,” in Advances in neural information processing systems, 1997, pp. 473–479.
  19. Q. Zhuge, L. Xu, and G. Zhang, “Lstm neural network with emotional analysis for prediction of stock price.” Engineering letters, vol. 25, no. 2, 2017.
  20. X. Jiawei and T. Murata, “Stock market trend prediction with sentiment analysis based on lstm neural network,” in Proceedings of the International MultiConference of Engineers and Computer Scientists, 2019, pp. 13–15.
  21. Tracy-Talent, “tracy-talent/curriculum.” [Online]. Available: https://github.com/tracy-talent/curriculum/tree/master/DataMining/sentiment
  22. rguthrie3, “rguthrie3/deeplearningfornlpinpytorch.” [Online]. Available: https://github.com/rguthrie3/DeepLearningForNLPInPytorch
  23. A. Karimi, L. Rossi, A. Prati, and K. Full, “Adversarial training for aspect-based sentiment analysis with bert,” arXiv preprint arXiv:2001.11316, 2020.
  24. P.-H. Chi, P.-H. Chung, T.-H. Wu, C.-C. Hsieh, Y.-H. Chen, S.-W. Li, and H.-y. Lee, “Audio albert: A lite bert for self-supervised learning of audio representation,” in 2021 IEEE Spoken Language Technology Workshop (SLT).   IEEE, 2021, pp. 344–350.
  25. F. A. Gers, J. Schmidhuber, and F. Cummins, “Learning to forget: Continual prediction with lstm,” 1999.
  26. K. Chen, Y. Zhou, and F. Dai, “A lstm-based method for stock returns prediction: A case study of china stock market,” in 2015 IEEE international conference on big data (big data).   IEEE, 2015, pp. 2823–2824.
  27. Dataabc, “dataabc/weibo-search.” [Online]. Available: https://github.com/dataabc/weibo-search
  28. Google-Research, “google-research/bert.” [Online]. Available: https://github.com/google-research/bert
  29. SophonPlus, “Sophonplus/chinesenlpcorpus.” [Online]. Available: https://github.com/SophonPlus/ChineseNlpCorpus/tree/master/datasets/
  30. C. Sun, X. Qiu, Y. Xu, and X. Huang, “How to fine-tune bert for text classification?” in China National Conference on Chinese Computational Linguistics.   Springer, 2019, pp. 194–206.
  31. L. Guo, W. Wang, S. Cheng, and X. Que, “Event-based user classification in weibo media,” The Scientific World Journal, vol. 2014, 2014.
  32. W. platform, “Weibo customer service.” [Online]. Available: https://kefu.weibo.com/faqdetail?id=20831
  33. Kaihui Zhang, Lei Li, Peng Li, and Wenda Teng, “Stock trend forecasting method based on sentiment analysis and system similarity model,” in Proceedings of 2011 6th International Forum on Strategic Technology, vol. 2, 2011, pp. 890–894.
  34. T. Linjordet and K. Balog, “Impact of training dataset size on neural answer selection models,” in European Conference on Information Retrieval.   Springer, 2019, pp. 828–835.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Ziyuan Ma (3 papers)
  2. Conor Ryan (6 papers)
  3. Jim Buckley (10 papers)
  4. Muslim Chochlov (6 papers)
X Twitter Logo Streamline Icon: https://streamlinehq.com

Tweets