A Complete VADER-Based Sentiment Analysis of Bitcoin (BTC) Tweets during the Era of COVID-19

Abstract

During the COVID-19 pandemic, many research studies have been conducted to examine the impact of the outbreak on the financial sector, especially on cryptocurrencies. Social media, such as Twitter, plays a significant role as a meaningful indicator in forecasting the Bitcoin (BTC) prices. However, there is a research gap in determining the optimal preprocessing strategy in BTC tweets to develop an accurate machine learning prediction model for bitcoin prices. This paper develops different text preprocessing strategies for correlating the sentiment scores of Twitter text with Bitcoin prices during the COVID-19 pandemic. We explore the effect of different preprocessing functions, features, and time lengths of data on the correlation results. Out of 13 strategies, we discover that splitting sentences, removing Twitter-specific tags, or their combination generally improve the correlation of sentiment scores and volume polarity scores with Bitcoin prices. The prices only correlate well with sentiment scores over shorter timespans. Selecting the optimum preprocessing strategy would prompt machine learning prediction models to achieve better accuracy as compared to the actual prices.

COVID-19 Vaccination Awareness and Aftermath: Public Sentiment Analysis on Twitter Data and Vaccinated Population Prediction in the USA

“…There have been several works related to analyzing the Twitter dataset on different topics during the COVID-19 pandemic [12][13][14][15]. Only a few studies focus on the Twitter data related to COVID-19 vaccination [16,17].…”

“…Glowacki et al [12] performed text mining to identify addiction concerns during the COVID-19 pandemic. They captured public tweets containing the two keywords "addiction" and "covid" together and came up with 14 prevalent topics and provided discussion on those topics.…”

A Multi-Method Survey on the Use of Sentiment Analysis in Multivariate Financial Time Series Forecasting

“…Therefore, there are a significant number of studies directed towards this research area as well. In [ 18 ], different text preprocessing strategies for correlating the sentiment scores from Twitter scraped textual data with Bitcoin prices during the COVID-19 pandemic were compared, to identify the optimum preprocessing strategy that would prompt machine learning prediction models to achieve better accuracy. Twitter data were also used in [ 19 ] to predict the future value of the SSECI (Shanghai Stock Exchange Composite Index) by applying a NARX time series model combined with a weighted sentiment representation extracted from tweets.…”

VADER Sentiment Analysis without and with English Punctuation Marks

“…The heuristics incorporate medicines for; (1) Punctuation (for example, number of '! 's); (2) capitalization (for example, 'I HATE YOU' is more extraordinary than 'I hate you'); (3) degree modifiers (for example, 'The service here is extremely good is more extraordinary than 'The service here is good); (4) constructive conjunction 'yet' to move the polarity; (5) tri-gram assessment to distinguish negation (for example 'The food here isn't actually all that great'') [9]. Punctuation is fundamental, and is utilized to pass on and explain the importance of written language.…”