The advent of the COVID-19 pandemic has undoubtedly affected the political scene worldwide and the introduction of new terminology and public opinions regarding the virus has further polarized partisan stances.Using a collection of tweets gathered from leading American political figures online (Republican and Democratic), we explored the partisan differences in approach, response, and attitude towards handling the international crisis.Implementation of the bag-of-words, bigram, and TF-IDF models was used to identify and analyze keywords, topics, and overall sentiments from each party.Results suggest that Democrats are more concerned with the casualties of the pandemic, and give more medical precautions and recommendations to the public whereas Republicans are more invested in political responsibilities such as keeping the public updated through media and carefully watching the progress of the virus.We propose a systematic approach to predict and distinguish a tweet's political stance (left or right leaning) based on its COVID-19 related terms using different classification algorithms on different language models.
The paper examines COVID-19 discourse on Twitter among American political leaders from both Democratic and Republican parties. By analyzing tweets collected from 60 political figures between November 2019 and November 2020, the authors utilize models like bag-of-words, bigram, and TF-IDF to identify keywords, topics, and sentiments related to COVID-19. Results indicate that Democrats focus more on the casualties of the pandemic and advocate for medical precautions, while Republicans emphasize political responsibilities and updates. The study aims to predict tweets' political stances and highlights the significant differences in terminology and sentiment between the two parties, using classification algorithms like LinearSVC and Naive Bayes for sentiment analysis. Various models yielded differing performances, with the best results for keywords associated with Democratic responses. The paper suggests directions for future research, including extending analyses to global political leaders' discourse.
This paper employs the following methods:
- bag-of-words
- bigram
- TF-IDF
- LinearSVC
- Naive Bayes
The following datasets were used in this research:
- Democrats more concerned with casualties and health recommendations
- Republicans focus on political responsibilities and updates
- SVM classification outperforms Naive Bayes in predicting stances
- CountVectorizer in bigram model yielded highest accuracy of 0.927
- Number of GPUs: None specified
- GPU Type: None specified
- Compute Requirements: None specified