The internet has played an important role in influencing all human activities in today's technological era. With the internet can be used for various purposes, including sharing knowledge, transacting, socializing, shopping, business, education, and many other things that can be done. While the internet is getting more and more popular, various kinds of digital transactions continue to develop, one of which is the exchange of coins for other coins which are called cryptocurrencies. Cryptocurrencies are digital assets that use strong cryptography to encrypt financial transactions, and verify asset transfers. One of the cryptocurrency exchanges for investment in Indonesia is Tokocrypto. With such enthusiasm for cryptocurrency, many Indonesians use social media such as Twitter to find information, provide opinions, as well as information. To classify public tweets on Twitter into positive and negative categories, a sentiment analysis model is needed. This study uses the Long Short Term Memory (LSTM) method, where LSTM is a neural network development that can be used for modeling time series data on Twitter users' tweets against the Tokocrypto exchange. There were 2022 positive tweets, 1632 negative tweets, and 1012 neutral tweets.
Copyrights © 2022