Text Analysis Of Russia-Ukraine War

No Thumbnail Available
Authors
Josey, Daniel
Issue Date
2024
Degree
MSc Business Analytics
Publisher
Dublin Business School
Rights
Abstract
In the Research, we assess the use of Twitter tweets to identify Fake News. Knowing the intent of the text can help classify the News as fake or not, and it can help in many policy makings and understanding the public opinion on any given topic. The study's primary purpose is to identify fake News based on tweets from the Russian and Ukrainian wars. The following is an ongoing war, termed cyber war, because of the use of social media. The study uses data from Twitter by writing the Python script and extracting the code in an HTML document with the help of understanding natural language and converting Python text analytics into a raw structured format. The Research seeks to find the label based on the data's subjectivity and polarity. Given that, clean text data is converted into vectors with the help of the TF-IDF metric. The values are fed into various machine-learning algorithms and tested on different accuracy matrices. The random forest model has achieved the maximum accuracy of 87% in identifying fake and real tweets. The given model can help identify fake News on the Internet and help reduce phoney content. The provided search has used a standard data mining approach concerning text analytics based on the given topic.