Twitter Sentiment Analysis-Based Adjustment of Cryptocurrency Action Recommendation Model for Profit Maximization

Abstract

Cryptocurrencies have recently attracted considerable attention, resulting in research mainly on deep learning-based price prediction models to maximize profit. Two research approaches have been adopted. Studies adopting the first approach directly predict the future cryptocurrency price. Long short-term memory (LSTM) and gated recurrent unit (GRU), which show high performance in time-series data, are mainly used for this approach. Further, studies adopting the second approach recommend actions to investors to maximize profits, such as ''Sell'', ''Buy'', and ''Wait.'' In this approach, classification models are used and results are derived based on probabilities. However, these action recommendation models do not consider the quality of the result. For example, it is risky to accept the result when the probability that the result of the action recommendation model for two classes is the correct answer is approximately 51%. To solve this problem, we recommend a method for adjusting the result of the action recommendation model based on Twitter sentiment analysis. The experimental results show that the proposed adjustment method improves the performance by approximately 3% compared to the conventional methods and are statistically validated.

Factors influencing the adoption of cryptocurrency in Bangladesh: an investigation using the technology acceptance model (TAM)

“…The sentiment surrounding Bitcoin holds considerable influence in accurately forecasting Bitcoin prices, even when accounting for other pertinent elements. Moreover, empirical data suggests that the attitude surrounding the prevailing cryptocurrency, specifically Bitcoin, exerts an influence on the value of other cryptocurrencies (Anamika et al ., 2023; Park and Seo, 2023; Kyriazis et al ., 2023).…”

Multi-domain aspect-oriented sentiment analysis for movie recommendations using feature extraction

“…The movie recommendation system efficiently assists users in discovering movies that match their preferences, whether derived from their own experiences or from the other users. Hence, sentiment analysis is implemented to reviews/comments to also contribute to movie ratings and lead to better recommendations [13]. Multi-domain sentiment analysis approaches focus on developing models to transfer information between different domains.…”

Cryptocurrency Price Prediction Model Based on Sentiment Analysis and Social Influence

“…In the study of Park et al, to predict the closing prices of cryptocurrencies, the performance evaluation of a genetic algorithm tuned for deep learning (DL) and boosted treebased techniques was investigated [25]. By comparing the results of Convolutional Neural Networks (CNN), Deep Forward Neural Networks, and Gated Recurrent Units, it was found that the CNN model had the least mean average percentage error of 0.08 and produced a consistent and highest explained variance score of 0.96 (on average) compared to other models [26]. In another study, long shortterm memory (LSTM) and gated recurrent unit (GRU) were used to predict the future prices of cryptocurrencies, and according to the Twitter sentiment analysis, an action recommendation model was proposed to recommend actions to investors for maximizing profits, such as "sell", "buy " , and "wait".…”