Loading...
| Friend's email | |
| Your name | |
| Your email | |
| enter code | |
This page was sent successfuly
- Type of Document: M.Sc. Thesis
- Language: Farsi
- Document No: 53149 (01)
- University: Sharif University of Technology
- Department: Industrial Engineering
- Advisor(s): Akhavan Niaki, Taghi
- Abstract:
- Investors' sentiment toward a coin is very vital in cryptocurrencies' markets. If traders do not invest in a coin, its price will decline; therefore, it is essential for investors to take others' sentiment into account when they want to buy or sell a coin. Text mining on social media is one technique that can help traders understand others' opinions about the coin they are trading. Hence, in this research, we try to predict the top three cryptocurrencies, Bitcoin, Etheruem, and Litecoin, price movement for the next day based on Twitter posts and News title using text mining. In this research, we found out that considering all tweets can reduce our model's accuracy, and for better accuracy, we introduced a way to find top users that had better prediction in the past. We also used a feature-based sentiment analysis using a neural network that showed a better result than a rule-based sentiment analysis, VADAR. For the news titles, we separated each news source and fed it to our model because we showed that every news source had different sentiment toward cryptocurrencies. We then compared five machine learning algorithms for each coin and found the best algorithms for those coins. We also added twitter sentiment analysis to the news model and tried to predict price movement based on news titles and Twitter, which we conclude that using news titles and Twitter together would reduce the model's accuracy
- Keywords:
- Cryptocurrency ; Natural Language Processing ; Sentiment Analysis ; Machine Learning ; News ; Exchange Market
Digital Object List
-
محتواي کتاب
- view
Bookmark