Analýza sentimentu ve finančních zprávách
| Název práce v češtině: | Analýza sentimentu ve finančních zprávách |
|---|---|
| Název v anglickém jazyce: | Financial News Sentiment Analysis |
| Klíčová slova: | finanční zprávy|analýza sentimentu|data mining |
| Klíčová slova anglicky: | financial news|sentiment analysis|data mining |
| Akademický rok vypsání: | 2023/2024 |
| Typ práce: | bakalářská práce |
| Jazyk práce: | |
| Ústav: | Katedra softwarového inženýrství (32-KSI) |
| Vedoucí / školitel: | doc. RNDr. Irena Holubová, Ph.D. |
| Řešitel: | skrytý - zadáno a potvrzeno stud. odd. |
| Datum přihlášení: | 17.02.2024 |
| Datum zadání: | 19.02.2024 |
| Datum potvrzení stud. oddělením: | 19.02.2024 |
| Zásady pro vypracování |
| With the growing volume of information on the Internet, evaluating the current state of an organisation can become a time-consuming process for users, especially in the context of investment decisions. On the other hand, using a rich source of information, such as news articles, for sentiment analysis allows us to create a powerful tool for evaluating a company's current market situation. Studies suggest a correlation between stock price changes and the polarity of financial news mentioning a company's stock symbol.
The thesis aims to design and implement a tool to provide users with sentiment analysis of news articles to aid investment decision-making. After discussing the relevant existing sentiment analysis approaches for solving this problem, it will then focus on the problem of how to acquire the input data, as it is not always freely available. The tool will enable the particular analysis and provide a user-friendly and parameterisable visualisation of the results and their correlation with the stock market using a selected sentiment analysis approach. The tool will be verified on a selected set of historical data. The architecture of the system will be modular so that it ensures adding/replacing the analytical approaches, as well as integrating new types of input data. |
| Seznam odborné literatury |
| Bing Liu: Sentiment Analysis and Opinion Mining. Synthesis Lectures on Human Language Technologies, Morgan & Claypool Publishers 2012, ISBN 978-3-031-01017-0
Ayman E. Khedr, S.E.Salama, Nagwa Yaseen,"Predicting Stock Market Behavior using Data Mining Technique and News Sentiment Analysis", International Journal of Intelligent Systems and Applications(IJISA), Vol.9, No.7, pp.22-30, 2017. DOI:10.5815/ijisa.2017.07.03 Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, Veselin Stoyanov: RoBERTa: A Robustly Optimized BERT Pretraining Approach. CoRR abs/1907.11692 (2019). |