Analyzing Brexit’s impact using sentiment analysis and topic modeling on Twitter discussion

Ilyas, Sardar Haider Waseem; Soomro, Zainab Tariq; Anwar, Ahmed; Shahzad, Hamza; Yaqub, Ussama

doi:10.1145/3396956.3396973

Cited by 22 publications

(14 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, the NLP techniques of dictionary-based sentiment analysis, using the software SentiStrength, and topic modeling, using the software ConText, were used [95,96]. The combination of sentiment analysis and topic modeling allows us to obtain a nuanced picture on Twitter discourse, including both Twitter users' emotional state and the topics being discussed (for previous uses of the combination of these methods, see [19,[97][98][99][100].…”

Section: Methods Of Analysismentioning

confidence: 99%

Lockdowns, lethality, and laissez-faire politics. Public discourses on political authorities in high-trust countries during the COVID-19 pandemic

Perlstein

Verboord

2021

PLoS ONE

View full text Add to dashboard Cite

This study looks at population response to government containment strategies during initial stages of the COVID-19 pandemic in four high-trust Northern European countries–Denmark, Germany, the Netherlands, and Sweden–with special emphasis on expressions of governmental trust. Sentiment analysis and topic modeling analysis were performed using Twitter data from three phases during the initial European lockdown, and results were compared over time and between countries. Findings show that, in line with existing theory, assertive crisis responses and proactive communication were generally well-received, whereas tentative crisis responses or indications by the authorities that the crisis was manageable were generally met with suspicion. In addition, while government support was high in all countries during the height of the crisis, messages critical of the government as well as conspiracy theories were nevertheless widely circulated. Importantly, countries with the least assertive strategies, rather than clear negative responses, saw heightened polarization of sentiment in the population. Furthermore, in the case of Sweden, a laissez-faire strategy was generally accepted by the population, despite strong criticism from other countries, until mortality rates started to rise. Possible explanations for these findings are discussed with an emphasis of prior trust as a potential explanatory factor. Future research should seek to replicate these findings in other countries with different levels of prior governmental trust or with a different severity of the COVID-19 outbreak than the countries in this study as well as triangulate the findings of this study using alternative methods.

show abstract

Section: Methods Of Analysismentioning

confidence: 99%

Lockdowns, lethality, and laissez-faire politics. Public discourses on political authorities in high-trust countries during the COVID-19 pandemic

Perlstein

Verboord

2021

PLoS ONE

View full text Add to dashboard Cite

show abstract

“…This study uncovered the most popular daily Twitter debates on the topics and discovered a positive correlation between Twitter's attitude towards Brexit and British pound exchange rate using the VADER library [19].…”

Section: Literature Reviewmentioning

confidence: 99%

Prediction of People Sentiments on Twitter Using Machine Learning Classifiers During Russian-Ukrainian Conflict

Baker

Taher

Jihad

2023

Preprint

View full text Add to dashboard Cite

Social media has become an excellent way to discover people's thoughts about various topics and situations. In recent years, many studies have focused on social media during crises, including natural disasters or wars caused by individuals. This study looks at how people expressed their feelings on Twitter during the conflict between Russia and Ukraine. This study met two goals: the collected data was unique, and it used machine learning (ML) to classify the tweets based on their effect on people's feelings. The first goal was to find the most relevant hashtags about the conflict to locate the data set. The second goal was to use several well-known ML models to organize the tweets into groups. The experimental results have shown that most of the performed ML classifiers have higher accuracy with a balanced dataset. However, the findings of the demonstrated experiments using data balancing strategies would not necessarily indicate that all classes would perform better. Therefore, it is important to highlight the importance of comparing and contrasting the data balancing strategies employed in SA and ML studies, including more classifiers and a more comprehensive range of use cases.

show abstract

“…For example, few studies have explored the political discourse on Twitter in the US presidential election (Yaqub et al, 2020), while other studies have focused on information Price of Bitcoin for our analysis dissemination during a public health crisis (Ilyas et al, 2021;Lent et al, 2017). In addition, previous studies have explored the relationship between Twitter sentiment and volatility in national currencies (Ilyas et al, 2020;Komariah et al, 2015;Ozturk and Ciftci, 2014). Recent studies have investigated the correlation between tweet sentiment and changes in the financial markets (Aich et al, 2017;Cakra and Distiawan Trisedya, 2015;Gupta and Singal, 2017;Ilyas et al, 2020).…”

Section: Literature Reviewmentioning

confidence: 99%

Analysis of Bitcoin’s price spike in context of Elon Musk’s Twitter activity

Zaman

Yaqub

Saleem

2022

GKMC

Self Cite

View full text Add to dashboard Cite

Purpose The purpose of this paper is to explore the effect of Elon Musk’s Twitter bio change on January 29, 2021 on the discourse around Bitcoin (BTC) on Twitter and to understand how these changes relate to the changes in Bitcoin price around that time. Design/methodology/approach This study implements sentiment analysis and text mining on Twitter data to explore changes in public sentiments toward Bitcoin after Elon Musk’s Twitter bio change. Furthermore, it uses Bitcoin price data obtained from the Binance exchange to understand its relation with Twitter discussion. Findings Elon Musk’s bio change on Twitter on January 29 increased the tweet volume mentioning Bitcoin. This increase in tweets had a strong positive correlation with Bitcoin price and preceded the rise in Bitcoin price. Although the bio change had an apparent effect on the tweet volume, there was no considerable effect on the tweet sentiments, indicating that tweet sentiment is a poor predictor of Bitcoin price. Originality/value This paper proposes an understanding of how social media influencers, like Elon Musk, affect the discourse around Bitcoin and can, in turn, have an impact on Bitcoin price.

show abstract

Analyzing Brexit’s impact using sentiment analysis and topic modeling on Twitter discussion

Cited by 22 publications

References 28 publications

Lockdowns, lethality, and laissez-faire politics. Public discourses on political authorities in high-trust countries during the COVID-19 pandemic

Lockdowns, lethality, and laissez-faire politics. Public discourses on political authorities in high-trust countries during the COVID-19 pandemic

Prediction of People Sentiments on Twitter Using Machine Learning Classifiers During Russian-Ukrainian Conflict

Analysis of Bitcoin’s price spike in context of Elon Musk’s Twitter activity

Contact Info

Product

Resources

About