Comparative Study for Sentiment Analysis of Financial Tweets with Deep Learning Methods
Source abstract
Abstract
Nowadays, Twitter is one of the most popular social networking services. People post messages called “tweets”, which may contain photos, videos, links and text. With the vast amount of interaction on Twitter, due to its popularity, analyzing Twitter data is of increasing importance. Tweets related to finance can be important indicators for decision makers if analyzed and interpreted in relation to stock market. Financial tweets containing keywords from the BIST100 index were collected and the tweets were tagged as “POSITIVE”, “NEGATIVE” and “NEUTRAL”. Binary and multi-class datasets were created. Word embedding and pre-trained word embedding were used for tweet representation. As classifiers, Neural Network, Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), Gated Recurrent Units (GRU) and GRU-CNN models were used in this study. The best results for binary and multi-class datasets were observed with pre-trained word embedding with the CNN model (83.02%, 72.73%). When word embedding was employed, the Neural Network model had the best results on the multi-class dataset (63.85%) and GRU-CNN had the best results on the binary dataset (80.56%).
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Stock Market Forecasting Methods · Sentiment Analysis and Opinion Mining · Advanced Text Analysis Techniques
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Department of Computer Engineering, Ankara Yıldırım Beyazıt University, Ankara 06010, Türkiye
Turkish Embassy Office of Educational Counsellor, 1062 Budapest, Hungary
Department of Software Engineering, Istanbul Topkapi University, Istanbul 34087, Türkiye
Department of Automatic Control and System Engineering, University of the Basque Country (UPV/EHU), 01006 Vitoria-Gasteiz, Spain
Funding
Mobility Lab Foundation
References (50)
Show source-provided references
1. Twitter (2019, June 10). It’s What’s Happening. Available online: https://twitter.com/.
2. (2020, July 20). Twitter Statistics—Statistic Brain. Available online: https://twitter.com/StatisticBrain.
3. New Avenues in Opinion Mining and Sentiment Analysis10.1109/MIS.2013.30 ↗
4. Sentiment Analysis and Opinion Mining10.1007/978-3-031-02145-9 ↗
5. Sentiment Analysis Algorithms and Applications: A Survey10.1016/j.asej.2014.04.011 ↗
6. Memis, E., and Kaya, H. (2019, January 11–13). Association Rule Mining on the BIST100 Stock Exchange. Proceedings of the 3rd International Symposium on Multidisciplinary Studies and Innovative Technologies, ISMSIT 2019—Proceedings, Ankara, Turkey.10.1109/ISMSIT.2019.8932923 ↗
7. Eryiğit, G. (2014, January 26–30). ITU Turkish NLP Web Service. Proceedings of the Demonstrations at the 14th Conference of the European Chapter of the Association for Computational Linguistics (EACL), Gothenburg, Sweden.10.3115/v1/E14-2001 ↗
8. Mikolov, T., Sutskever, I., Chen, K., Corrado, G., and Dean, J. (2019, June 10). Distributed Representations of Words and Phrases and Their Compositionality. In Advances in Neural Information Processing Systems; 2013. Available online: https://proceedings.neurips.cc/paper_files/paper/2013/file/9aa42b31882ec039965f3c4923ce901b-Paper.pdf.
9. Mikolov, T., Karafiat, M., Burget, L., Cernocky, J., and Khudanpur, S. (2010, January 26–30). Recurrent Neural Network Based Language Model. Proceedings of the Interspeech 2010, Chiba, Japan.10.21437/Interspeech.2010-343 ↗
10. Socher, R., Perelygin, A., Wu, J.Y., Chuang, J., Manning, C.D., Ng, A.Y., and Potts, C. (2013, January 18–21). Recursive Deep Models for Semantic Compositionality over a Sentiment Treebank. Proceedings of the EMNLP 2013—2013 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference, Seattle, WA, USA.
11. Recent Trends in Deep Learning Based Natural Language Processing [Review Article]10.1109/MCI.2018.2840738 ↗
12. Grave, E., Bojanowski, P., Gupta, P., Joulin, A., and Mikolov, T. (2018, January 7–12). Learning Word Vectors for 157 Languages. Proceedings of the LREC 2018, 11th International Conference on Language Resources and Evaluation, Miyazaki, Japan.
13. Nasukawa, T. (2003, January 23–25). Sentiment Analysis: Capturing Favorability Using Natural Language Processing Definition of Sentiment Expressions. Proceedings of the 2nd International Conference on Knowledge Capture, Sanibel Island, FL, USA.10.1145/945645.945658 ↗
14. Sentiment analysis in Twitter10.1017/S1351324912000332 ↗
15. Almohaimeed, A.S. (2017). Using Tweets Sentiment Analysis to Predict Stock Market Movement. [Master’s Thesis, Auburn University].
16. Şimşek, M.U., and Özdemir, S. (2012, January 17–19). Analysis of the Relation between Turkish Twitter Messages and Stock Market Index. Proceedings of the 2012 6th International Conference on Application of Information and Communication Technologies (AICT), Tbilisi, Georgia.10.1109/ICAICT.2012.6398520 ↗
17. Yıldırım, M., and Yüksel, C.A. (2017). Sosyal Medya Ile Hisse Senedi Fiyatinin Günlük Hareket Yönü Arasindaki Ilişkinin Incelenmesi: Duygu Analizi Uygulamasi. Uluslararası İktisadi ve İdari İncelemeler Derg., 33–44.10.18092/ulikidince.352414 ↗
18. A Sentiment Analysis of Twitter Content as a Predictor of Exchange Rate Movements10.15353/rea.v6i2.1416 ↗
19. Eliaçik, A.B., and Erdogan, N. (2015). Mikro Bloglardaki Finans Toplulukları Için Kullanıcı Ağırlıklandırılmış Duygu Analizi Yöntemi. Ulus. Yazılım Mühendisliği Sempozyumu, 782–793.
20. Twitter Verileri Ile Duygu Analizi Sentiment Analysis with Twitter
21. Twitter Mood Predicts the Stock Market10.1016/j.jocs.2010.12.007 ↗
22. Velioglu, R., Yildiz, T., and Yildirim, S. (2018, January 20–23). Sentiment Analysis Using Learning Approaches over Emojis for Turkish Tweets. Proceedings of the UBMK 2018—3rd International Conference on Computer Science and Engineering, Sarajevo, Bosnia and Herzegovina.10.1109/UBMK.2018.8566260 ↗
23. Stream-Based Active Learning for Sentiment Analysis in the Financial Domain10.1016/j.ins.2014.04.034 ↗
24. Danışmanlı ve Yarı Danışmanlı Öğrenme Kullanarak Doküman Vektörleri Tabanlı Tweetlerin Duygu Analizi
25. Ayata, D., Saraclar, M., and Ozgur, A. (2017, January 15–18). Makine Öǧrenmesi ve Kelime Vektör Temsili Ile Türke Tweet Sentiment Analizi. Proceedings of the 2017 25th Signal Processing and Communications Applications Conference, SIU 2017, Antalya, Turkey.
26. How Are Twitter Activities Related to Top Cryptocurrencies’ Performance? Evidence from Social Media Network and Sentiment Analysis
27. Does Online Investor Sentiment Explain Analyst Recommendation Changes? Evidence from an Emerging Market
28. Popular Personal Financial Advice versus the Professors10.1257/jep.36.4.167 ↗
29. The Predictive Power of Public Twitter Sentiment for Forecasting Cryptocurrency Prices10.1016/j.intfin.2020.101188 ↗
30. Duffy, D., Durkan, J., Timoney, K., and Casey, E. (2012). Quarterly Economic Commentary, Winter 2012, The Economic and Social Research Institute.
31. Twitter Financial Community Sentiment and Its Predictive Relationship to Stock Market Movement10.1080/14697688.2015.1071078 ↗
32. Varanasi, R.A., Hanrahan, B.V., Wahid, S., and Carroll, J.M. (2017, January 28–30). TweetSight: Enhancing Financial Analysts’ Social Media Use. Proceedings of the 8th International Conference on Social Media & Society, Toronto, ON, Canada.10.1145/3097286.3097308 ↗
33. Text Categorization with Class-Based and Corpus-Based Keyword Selection
34. Nabi, J. (2018). Machine Learning—Text Processing, Towards Data Science.
35. Distributional Structure
36. Mikolov, T., Chen, K., Corrado, G., and Dean, J. (2013, January 2–4). Efficient Estimation of Word Representations in Vector Space. Proceedings of the 1st International Conference on Learning Representations, ICLR 2013—Workshop Track Proceedings, Scottsdale, AZ, USA.
37. Pennington, J., Socher, R., and Manning, C.D. (2014, January 25–29). GloVe: Global Vectors for Word Representation. Proceedings of the EMNLP 2014—2014 Conference on Empirical Methods in Natural Language Processing, Proceedings of the Conference, Doha, Qatar.10.3115/v1/D14-1162 ↗
38. Enriching Word Vectors with Subword Information10.1162/tacl_a_00051 ↗
39. Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2019, January 2–7). BERT: Pre-Training of Deep Bidirectional Transformers for Language Understanding. Proceedings of the NAACL HLT 2019—Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Minneapolis, MN, USA.
40. Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., and Darrell, T. (2014, January 3–7). Caffe: Convolutional Architecture for Fast Feature Embedding. Proceedings of the MM 2014—Proceedings of the 2014 ACM Conference on Multimedia, Orlando, FL, USA.10.1145/2647868.2654889 ↗
41. Razavian, A.S., Azizpour, H., Sullivan, J., and Carlsson, S. (2014, January 23–28). CNN Features Off-the-Shelf: An Astounding Baseline for Recognition. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops, Columbus, OH, USA.10.1109/CVPRW.2014.131 ↗
42. Collobert, R., and Weston, J. (2008, January 5–9). A Unified Architecture for Natural Language Processing: Deep Neural Networks with Multitask Learning. Proceedings of the Proceedings of the 25th International Conference on Machine Learning, Helsinki, Finland.10.1145/1390156.1390177 ↗
43. (2018, August 24). Elvis Deep Learning for NLP: An Overview of Recent Trends. Available online: https://medium.com/dair-ai/deep-learning-for-nlp-an-overview-of-recent-trends-d0d8f40a776d.
44. Finding Structure in Time10.1207/s15516709cog1402_1 ↗
45. Regularization Theory and Neural Networks Architectures10.1162/neco.1995.7.2.219 ↗
46. Park, S., and Kwak, N. (2016, January 20–24). Analysis on the Dropout Effect in Convolutional Neural Networks. Proceedings of the Computer Vision–ACCV 2016: 13th Asian Conference on Computer Vision, Taipei, Taiwan. Revised Selected Papers, Part II 13;.
47. Review of Classification Methods on Unbalanced Data Sets10.1109/ACCESS.2021.3074243 ↗
48. SMOTE: Synthetic Minority over-Sampling Technique10.1613/jair.953 ↗
49. Yap, B.W., Rani, K.A., Rahman, H.A.A., Fong, S., Khairudin, Z., and Abdullah, N.N. (2013, January 16–18). An Application of Oversampling, Undersampling, Bagging and Boosting in Handling Imbalanced Datasets. Proceedings of the First International Conference on Advanced Data and Information Engineering (DaEng-2013), Kuala Lumpur, Malaysia.10.1007/978-981-4585-18-7_2 ↗
50. Bäuerle, A., Van Onzenoodt, C., and Ropinski, T. (2019). Net2Vis: Transforming Deep Convolutional Networks into Publication-Ready Visualizations. arXiv.