Exploring Social Tendencies via Twitter Using Network Analysis

Social media is becoming the most prominent method of communication with the advent of diverse platforms being developed. As a result of this, societal norms have undergone a change in the recent past. This paper aims to explore dierent human tendencies on the social media platform- Twitter. In this study,we implement data science tools like Natural Language Processing and graph theory to conduct four independent analyses. First, we try to understand how information is spread on this platform by graphing the possible routes a tweet could have taken. We further expand on this and try to identify communities amongst a plethora of tweets using clustering techniques. For the third analysis, we conducted a sentiment analysis using the NRC lexicon which gave us insight to the emotions of people all over the world. In the midst of a pandemic, it was interesting to quantify the overall sentiments and observe the dierences between cities. The final study was to try to predict the origin of a tweet based on the user’s choice of words using machine learning algorithms such as random forests. This project was in essence an exploration of data gathered from Twitter where we observed promising results from each of the tools implemented in our analyses