Analisis Topik Tagar Covidindonesia pada Instagram Menggunakan Latent Dirichlet Allocation

Abstract

In this era, technology is increasingly sophisticated, this is evidenced by the number of people using the internet via cell phones, laptops, and other communication tools. One of the developments of this technology is social media such as Instagram. Along with technological developments, Instagram users can upload and share photos and videos using hashtags (#) so that other users can find the results of their posts. Instagram has now become one of the social media used by more than 1 billion people in the world. In this study, the authors wanted to know the dominant topics discussed through the hashtag covidindonesia. This research was conducted using the Latent Dirichlet Allocation (LDA) method. The analysis was carried out after doing text mining on 84 captions from various users on Instagram. To determine the optimal number of topics, by looking at the value of perplexity and topic coherence. The results obtained are the top 5 topics that are the content material in the uploaded video. These topics include covidindonesia, covid_19, pandemics in Indonesia, and discussion of covid-19 virus mutations.