Forecasting Bitcoin Price Fluctuation by Twitter Sentiment Analysis

Sattarov, Otabek; Jeon, Heung Seok; Oh, Ryum-Duck; Lee, Jun Dong

doi:10.1109/icisct50599.2020.9351527

Cited by 49 publications

(32 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For instance, Lamon et al (2017) use tweets together with logistic regression to obtain accuracy of 0.44 and 0.62 when predicting price increase and decrease, respectively. Similarly, Sattarov – (2020) obtain 0.62 accuracy when predicting BTC price using sentiment analysis. Overall, the superiority of the SVM forecast is in line with previous studies which support SVM’s, such as Ismail et al (2020), Rouhani and Abedin (2020) and Mallqui and Fernandes (2019).…”

Section: Resultsmentioning

confidence: 90%

“…McNally et al (2018) reported ML tools used to predict BTC price. Sattarov et al (2020) found 62.48% accuracy when making predictions based on BTC-related tweet sentiment and historical BTC price. Abraham et al (2018) used a linear regressions and found tweets and Google trends data to accurately predict the direction of price changes for BTC and Ethereum.…”

Section: Sentiment Analysis Cryptocurrency and Machine Learningmentioning

confidence: 98%

See 1 more Smart Citation

Predicting bitcoin price movements using sentiment analysis: a machine learning approach

Gurrib

Kamalov

2021

SEF

View full text Add to dashboard Cite

Purpose Cryptocurrencies such as Bitcoin (BTC) attracted a lot of attention in recent months due to their unprecedented price fluctuations. This paper aims to propose a new method for predicting the direction of BTC price using linear discriminant analysis (LDA) together with sentiment analysis. Design/methodology/approach Concretely, the authors train an LDA-based classifier that uses the current BTC price information and BTC news announcements headlines to forecast the next-day direction of BTC prices. The authors compare the results with a Support Vector Machine (SVM) model and random guess approach. The use of BTC price information and news announcements related to crypto enables us to value the importance of these different sources and types of information. Findings Relative to the LDA results, the SVM model was more accurate in predicting BTC next day’s price movement. All models yielded better forecasts of an increase in tomorrow’s BTC price compared to forecasting a decrease in the crypto price. The inclusion of news sentiment resulted in the highest forecast accuracy of 0.585 on the test data, which is superior to a random guess. The LDA (SVM) model with asset specific (news sentiment and asset specific) input features ranked first within their respective model classifiers, suggesting both BTC news sentiment and asset specific are prized factors in predicting tomorrow’s price direction. Originality/value To the best of the authors’ knowledge, this is the first study to analyze the potential effect of crypto-related sentiment and BTC specific news on BTC’s price using LDA and sentiment analysis.

show abstract

Section: Resultsmentioning

confidence: 90%

Section: Sentiment Analysis Cryptocurrency and Machine Learningmentioning

confidence: 98%

Predicting bitcoin price movements using sentiment analysis: a machine learning approach

Gurrib

Kamalov

2021

SEF

View full text Add to dashboard Cite

show abstract

“…Pearson correlation [13], Bitcoin/Etherium [14], NewsSentiment [15], Word2vec and Ngram [16], Cumulative sentiment [17], Random Forest Regression [18], Q-Learning [This paper].…”

Section: Bitcoin Price Prediction With Public Opinionmentioning

confidence: 99%

“…In our previous research [18], we scrapped more than 9.2 thousand tweets that were posted in a two-month period, and found that when sentiment analysis was applied to tweets regarding Bitcoin and financial data, the sentiment on Twitter had a predictive impact on the Bitcoin findings.…”

Section: Resource Usage Minimizationmentioning

confidence: 99%

Twitter Attribute Classification with Q-Learning on Bitcoin Price Prediction

Sattarov¹,

Choi²

2022

Preprint

View full text Add to dashboard Cite

Aspiring to achieve an accurate Bitcoin price prediction based on people's opinions on Twitter usually requires millions of tweets, using different text mining techniques (preprocessing, tokenization, stemming, stop word removal), and developing a machine learning model to perform the prediction. These attempts lead to the employment of a significant amount of computer power, central processing unit (CPU) utilization, random-access memory (RAM) usage, and time. To address this issue, in this paper, we consider a classification of tweet attributes that effects on price changes and computer resource usage levels while obtaining an accurate price prediction. To classify tweet attributes having a high effect on price movement, we collect all Bitcoin-related tweets posted in a certain period and divide them into four categories based on the following tweet attributes: (i ) the number of followers of the tweet poster, (i i ) the number of comments on the tweet, (i i i ) the number of likes, and (i v ) the number of retweets. We separately train and test by using the Q-learning model with the above four categorized sets of tweets and find the best accurate prediction among them. Especially, we design several reward functions to improve the prediction accuracy of the Q-leaning. We compare our approach with a classic approach where all Bitcoin-related tweets are used as input data for the model, by analyzing the CPU workloads, RAM usage, memory, time, and prediction accuracy. The results show that tweets posted by users with the most followers have the most influence on a future price, and their utilization leads to spending 80% less time, 88.8% less CPU consumption, and 12.5% more accurate predictions compared with the classic approach.

show abstract

“…Research has shown that there is a high correlation between the Twitter influence users' probability and the probabilities influenced, whilst the majority of the users continue to have a balance in terms of sentiments in both cases (Ranasinghe & Halgamuge, 2021). Further analysis has shown that on the tweets related to Bitcoin and financial data scrutinized through sentiment analysis, the Twitter sentiment showed a predictive influence for the results of Bitcoin (Sattarov, Jeon, & Lee, 2020).…”

Section: Introductionmentioning

confidence: 99%

The impact of Tesla’s bitcoin investment and its plans to accept it as payment method on the evolution of bitcoin

Mironeanu¹,

Irimia²,

Săndulescu³

et al. 2021

Proceedings of the International Conference on Business Excellence

View full text Add to dashboard Cite

For the past years, cryptocurrencies have been a hot and controversial topic that has captured the attention of the whole tech world. Even if right now the portfolio of digital assets is considerable in size, the first cryptocurrency, Bitcoin, exploited its pioneer advantage and managed to remain at the center of attention both for the media and investors. During 2020, one of the most chaotic years, Bitcoin boomed in November 2020 almost doubling since the end of 2019. This boom is the result of a combination of factors, such as the fear of missing out translated into a chain reaction of public and private companies to consider Bitcoin a safe reserve asset, a hedging method against inflation, which represents a substitute for traditional hedging instruments, the infrastructure developed around it over the years, and lastly the hype created by influential figures through news and social media platforms. There have been many public figures that exhibited interest in cryptocurrencies through platforms such as Twitter, for instance Elon Musk, Bill Gates, Kanye West, Hugh Laurie, Mike Tyson and Gwyneth Paltrow are just some in a long list of celebrities that backed Bitcoin. This paper aims to analyze the impact that twitter posts have upon the evolution of Bitcoin, coupled with Tesla’s investment and recent statement of introducing Bitcoin as a method of payment in the near future. Our research tries to determine if the news and social media posts, such as tweets have an influence upon Bitcoin’s volatility and fluctuations.

show abstract

Forecasting Bitcoin Price Fluctuation by Twitter Sentiment Analysis

Cited by 49 publications

References 7 publications

Predicting bitcoin price movements using sentiment analysis: a machine learning approach

Predicting bitcoin price movements using sentiment analysis: a machine learning approach

Twitter Attribute Classification with Q-Learning on Bitcoin Price Prediction

The impact of Tesla’s bitcoin investment and its plans to accept it as payment method on the evolution of bitcoin

Contact Info

Product

Resources

About