A Framework for Topic Evolution and Tracking Their Sentiments With Time

Abstract

With the ongoing covid-19 pandemic, people rely on online communication to remain connected as a precautionary measure to maintain social distancing. When we have no one on our side to listen and console us in state of fear and dilemma, we try to find comfort in anonymity of social media. Tracking real-time changes in sentiments are quite difficult as it could not correlate well with human understanding and emotions, which changes with time and many other factors. Collecting sentiments from users on search results, news articles, paintings, photographs are nowadays common. This is a more robust and effective method as traditional ways do not rely on a lot of retrospectives. In this paper, we will be analyzing the data collected from Twitter on Covid-19 and see topic modelling can be meant to detect sentiment analysis. The challenge is here we need to see results over time, and changes detect in topics and sentiments. We analyze our method over covid-19 data and farmer’s protest. Results from this experiment using the proposed methodology are promising and giving valuable insights.