In 2020, over 3.6 billion people worldwide engaged with SM, with a predicted number of around 4.41 billion users in 2025. There are multiple functionalities on offer, rendering SM one of the most popular online activities. During recent years SM public usage has greatly increased. People have been using Social Media (SM) in an extensive global scale, exchanging messages, posting opinions, news and more. Our methodology facilitates producing more accurate and generalizable results, whilst exposing implications regarding social media user attitudes. Our findings showcase that 50 initially retrieved topics are narrowed down to just 4, when combining Latent Dirichlet Allocation with ARM. We also employ frequent wordset identification to reduce the number of extracted topics. Therefore, only strong wordsets are stored after discarding trivia ones. The goal is to utilize ARM as a postprocessing technique to enhance the output of any topic extraction method. It then uses Association Rule Mining (ARM) to discover frequent wordsets and generate rules that infer to user attitudes. The proposed methodology comprises topic extraction and visualization techniques, such as WordClouds, to form clusters or themes of opinions. It exploits the COVID-19 pandemic as a use case, and analyzes tweets gathered between February and August 2020. This work utilizes data from Twitter to mine association rules and extract knowledge about public attitudes regarding worldwide crises.
0 Comments
Leave a Reply. |