Sentiment Analysis on Twitter through Machine Learning: A Comprehensive Approach with User-Centric Visualisations

Abstract

Sentiment analysis is a crucial field that deals with the intricate task of identifying and systematically categorizing the various perspectives and opinions expressed within the original text. In today's digital age, social media platforms serve as a prolific source of data, inundated with a relentless stream of status updates, tweets, and content imbued with sentiments. Analysing the sentiments conveyed by users in this vast reservoir of data holds a pivotal role in comprehending the collective sentiments of the user community, dissecting dialogues, and aggregating viewpoints. This, in turn, can be instrumental in shaping strategies for commerce, conducting insightful political research, and gauging the pulse of communal activities. Examining sentiments on Twitter presents an increased difficulty because of the frequency of spelling errors, casual language, icons, and emojis. This research focuses on Twitter sentiment analysis, with a specific emphasis on a particular user account. The approach involves a combination of Python programming and Machine Learning techniques. By embarking on a comprehensive sentiment analysis journey within a specific domain, the aim is to discern the profound impact of that domain's data on sentiment categorization. Furthermore, this paper introduces a novel feature that enhances the organization of a user's most recent tweets and their presentation through visual aids such as graphs, charts, and word clouds. This visualization approach empowers a more intuitive and insightful exploration of the sentiments and trends embedded within the user's Twitter activity, facilitating a deeper understanding of their thoughts and emotions as expressed through their digital interactions.