TNS Vol.2 (CIAP 2022), 02 February 2023
* Author to whom correspondence should be addressed.
In order for investors to maximize their benefit by having better forecasts of the complex dynamics of the stock market, there are many factors that affect the stock market, from a company's financial ratios to investor sentiment and reactions to financial news. This project aims to collect UK business news from the Guardian and uses NLP techniques to transform unstructured text data into usable structured sentiment data to predict the movement of the FTSE100 index. The program uses two different libraries TEXTBLOB and VADER to extract sentiments from both the headlines and main bodies of the business news articles. Four machine learning algorithms including Logistic Regression, Naive Bayes, K-Nearest Neighbours and Support Vector Machines and a voting classifier were used to predict FTSE100 index movement given the business news sentiments of the previous day.
sentiment analysis, NLP, Stock price prediction
1. S. Barsa, "Classification of Hot News for Financial Forecast Using NLP Techniques," International Conference on Big Data, New Delhi, 2018.
2. S. Mehtab and J. Sen, "A Robust Predictive Model for Stock Price Prediction Using Deep Learning and Natural Language Processing," School of Computing and Analytics, Kolkata, 2019.
3. S. Mohan, S. Mullapudi, S. Sammeta, P. Vijayvergia and D. C. Anastasiu, "Stock Price Prediction Using News Sentiment Analysis," 2019 Fifth International Conference on Big Data Computing Service and Applications, New Delhi, 2019.
4. R. Akita, A. Yoshihara, T. Matsubara and K. Uehara, "Deep Learning for Stock Prediction Using Numerical and Textual Information," Kobe University, Seoul, 2019.
5. S. Kumar and S. Acharya, "Application of Machine Learning Algorithms in Stock Market Prediction: A Comparative Analysis," Indian Institute of Management, Indore, 2020.
6. I. Chatterjee, J. Gwan, Y. J. Kim, M. S. Lee and M. Cho, "An NLP and LSTM BasedStock Prediction and Recommender System for KOSDAQ and KOSPI," Intelligent Human Computer Interaction, 2021.
7. D. Shah, I. Haruma and F. Zulkernine, "Predicting the Effects of News Sentiments on the Stock Market," School of Computing, Queens University, Kingston, 2019.
8. x. Li, H. Xie, L. Chen, J. Wang and X. Deng, "News impact on stock price return via sentiment analysis," City University of Hong Kong, Hong Kong, 2014.
9. X. Wan, J. Yang, S. Marinov, J. P. Calliess, S. Zohren and X. Dong, "Sentiment correlation in financial news networks and associated market movements," Nature Portfolio, 2021.
10. I. Zheludev, R. Smith and T. Aste, "When Can Social Media Lead Financial Markets," Scientific Reports, 2014.
11. M. G. Sousa, K. Sakiyama, L. S. Rodrigues, P. H. Moraes, E. R. Fernandes and E. T. Matsubara, "BERT for Stock Market Sentiment Analysis," International Conference on Tools with Artificial Intelligence, New Delhi, 2019.
12. Y. Kim, S. R. Jeong and I. Ghani, "Text Opinion Mining to Analyze News for Stock Market Prediction," Kookmin University, Seoul, 2014.
The datasets used and/or analyzed during the current study will be available from the authors upon reasonable request.
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License. Authors who publish this journal agree to the following terms:
1. Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
2. Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
3. Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See Open Access Instruction).