Data Aggregation of Tweets and Topic Modelling Based on the Twitter Dataset

Abstract

Twitter is one of the most popular online social networks. It has a relatively simple data model and an intuitive API to access Twitter data. This makes it easy to collect social data and analyse the patterns of online behaviour. Twitter has an impactful presence among politicians, entrepreneurs, news agencies, public figures, and this makes it a crucial playground for social discussion. The topics discussed on Twitter often lead to or are the cause of social events. Therefore, a lot of information can be inferred from Twitter data. This can be used by NGOs, government agencies or policymakers to develop meaningful understanding and respond to the emerging trends. In this project, I will discuss a method to aggregate tweets related to Elon Musk and Tesla from Twitter servers using the Twitter API in the form of a web crawler. The data obtained from the web crawler will be combined with a ready-made dataset containing similar information, and the datasets will be merged together. After collecting relevant tweet information, I will perform topic modelling using Latent Dirichlet Allocation (LDA) on his tweets to find out the most common topics tweeted by Elon Musk. © 2021 ACM.