Table 6 Comparison with other studies
From: Bitcoin price change and trend prediction through twitter sentiment and data volume
Study | Maximum accuracy obtained | Days in dataset |
|---|---|---|
Present (Direction-BiLSTM) | 64.2% | 450\(\sim\) |
Present (Voting Classifier) | 77.2% | 450\(\sim\) |
Predicting the Price of Bitcoin Using Machine Learning-2018 McNally et al. | 52.78% | 1065\(\sim\) |
An Advanced CNN-LSTM Model for Cryptocurrency Forecasting-2021 Livieris et al. | 55.03% | 1400\(\sim\) |
Bitcoin price forecasting method based on CNN-LSTM hybrid neural network model-2019 Yan Li, Wei Dai | 64% (Precision) | 600\(\sim\) |
Bitcoin Response to Twitter Sentiments Galenchuk et al. | 68.6% | 912\(\sim\) |
Price Movement Prediction of Cryptocurrencies Using Sentiment Analysis and Machine Learning-2019 Valencia et al. | 72% | 60\(\sim\) |
Recurrent Neural Network Based Bitcoin Price Prediction by Twitter Sentiment Analysis-2018 Pant et al. | 77.62% | 180\(\sim\) |
Predicting Bitcoin price fluctuation with Twitter sentiment analysis-2017 Stenqvist, Lönnö | 83% | 30\(\sim\) |
Sentiment Analysis Based Direction Prediction in Bitcoin using Deep Learning Algorithms and Word Embedding Models-2020 Kilimci | 89.13% | 90\(\sim\) |