Sentiment Analysis on Cryptocurrency Based on Tweets and Retweets Using Support Vector Machines and Chi-Square

Abstract

The high public interest in cryptocurrencies is increasing over time. Cryptocurrencies are gaining worldwide attention because of their unique and unpredictable nature. Nowadays, cryptocurrencies can be used for various things, one of which is for investment. In investing in cryptocurrencies, various analyzes are needed to consider trade flows. One way to analyze it is by analyzing public sentiment which consists of positive and negative sentiments. However, there has been no previous research on the use of machine learning approaches and feature selection in sentiment analysis of Twitter tweets and retweets. The research was conducted by analyzing public sentiment using a machine learning algorithm, namely the Support Vector Machine. In addition to using the Support Vector Machine, Chi-square is also used in feature selection to help reduce noise in a sentence. Retweets will considerably improve sentiment label classification. The performance of sentiment analysis can be improved across the board by at least 91%. The sentiment analysis findings from this study are positive. This implies that a trader can take cryptocurrencies like Bitcoin, Ethereum, and Ripple into account while deciding on the type of investment.