Sentiment and Topic Modelling in Tweets and News Articles from the Russia-Ukraine War
Session Number
CMPS 17
Advisor(s)
Dr. Timothy Reid
Mr. Nour Jedidi, MIT Lincoln Laboratory
Discipline
Computer Science
Start Date
17-4-2024 10:25 AM
End Date
17-4-2024 10:40 AM
Abstract
Beginning in February 2022, Russia’s invasion in Ukraine marked one of the largest invasions of a European country since World War II and impacted numerous people worldwide. Our project aims to study public opinions and topics of discussion during this international crisis by analyzing daily tweets and news articles from April 2022 to June 2023. For our analyses, we utilized various Natural Language Processing libraries in Python to identify shifts in topics and compute sentiment. We used the BERTopic model to create topics and categorize tweets and news articles by topic. After applying a sentiment model on the tweets, we discovered the sentiment distribution of the tweets was 57% positive, 34% negative, and 9% neutral. Additionally, we investigated the correlation between the location associated with a tweet and its sentiment and found that tweets located in Nigeria and India were predominantly positive, while those in Ukraine were mostly negative. Furthermore, using a hashtag-prediction model, we determined that the majority of tweets and news articles were pro-Ukraine or neutral, while almost none were pro-Russia. These findings share valuable insights into the global perspectives on the Russia-Ukraine war as well as provide a framework for future analyses on other international crises.
Sentiment and Topic Modelling in Tweets and News Articles from the Russia-Ukraine War
Beginning in February 2022, Russia’s invasion in Ukraine marked one of the largest invasions of a European country since World War II and impacted numerous people worldwide. Our project aims to study public opinions and topics of discussion during this international crisis by analyzing daily tweets and news articles from April 2022 to June 2023. For our analyses, we utilized various Natural Language Processing libraries in Python to identify shifts in topics and compute sentiment. We used the BERTopic model to create topics and categorize tweets and news articles by topic. After applying a sentiment model on the tweets, we discovered the sentiment distribution of the tweets was 57% positive, 34% negative, and 9% neutral. Additionally, we investigated the correlation between the location associated with a tweet and its sentiment and found that tweets located in Nigeria and India were predominantly positive, while those in Ukraine were mostly negative. Furthermore, using a hashtag-prediction model, we determined that the majority of tweets and news articles were pro-Ukraine or neutral, while almost none were pro-Russia. These findings share valuable insights into the global perspectives on the Russia-Ukraine war as well as provide a framework for future analyses on other international crises.