A Dynamic Topic Identification and Labeling Approach of COVID-19 Tweets

TL;DR

This paper presents a framework for automatically identifying and labeling key COVID-19 related topics from Twitter data using LDA and unigram features, providing a dynamic overview of public opinion.

Contribution

It introduces a novel dynamic topic identification and labeling method leveraging LDA and unigram features, improving over manual static approaches.

Findings

Achieved 85.48% accuracy in topic labeling

Effectively captures evolving COVID-19 public discourse

Automates topic extraction from large tweet datasets

Abstract

This paper formulates the problem of dynamically identifying key topics with proper labels from COVID-19 Tweets to provide an overview of wider public opinion. Nowadays, social media is one of the best ways to connect people through Internet technology, which is also considered an essential part of our daily lives. In late December 2019, an outbreak of the novel coronavirus, COVID-19 was reported, and the World Health Organization declared an emergency due to its rapid spread all over the world. The COVID-19 epidemic has affected the use of social media by many people across the globe. Twitter is one of the most influential social media services, which has seen a dramatic increase in its use from the epidemic. Thus dynamic extraction of specific topics with labels from tweets of COVID-19 is a challenging issue for highlighting conversation instead of manual topic labeling approach. In this paper, we propose a framework that automatically identifies the key topics with labels from the tweets using the top Unigram feature of aspect terms cluster from Latent Dirichlet Allocation (LDA) generated topics. Our experiment result shows that this dynamic topic identification and labeling approach is effective having the accuracy of 85.48\% with respect to the manual static approach.