Sentiment analysis and topic modeling of BPJS Kesehatan based on twitter crawling data using Indonesian Sentiment Lexicon and Latent Dirichlet Allocation algorithm

• Published in: Journal of physics. Conference series Vol. 1821; no. 1; p. 12054
• Main Authors: Dikiyanti, T D, Rukmi, A M, Irawan, M I
• Format: Journal Article
• Language: English
• Published: Bristol IOP Publishing 01.03.2021
• Subjects: Algorithms; Customer services; Data mining; Digital media; Dirichlet problem; Modelling; Physics; Public opinion; Sentiment analysis; Social networks
• ISSN: 1742-6588; 1742-6596
• DOI: 10.1088/1742-6596/1821/1/012054

Abstract In today’s era, company performance is influenced by quick and easy responses to interacting with users. Twitter is one of the social media which is believed that public opinion on Twitter can influence the government or companies to make policies. Public criticism on Twitter is more quickly responded than people who contacting customer service directly, this is because the companies or government do not want their image to be bad due to delays in responding to public complaints on Twitter. Studies related to opinion writing on social media can use the method of topic modeling and sentiment analysis in order to get what topics are currently being discussed and also the value of their sentiments. Modeling of the topic was carried out using Latent Dirichlet Allocation and sentiment analysis using the Indonesian Sentiment Lexicon. A case study of public opinion on BPJS Kesehatan using Twitter data for 3 months from February to April 2020, obtained 5 main topics with the BPJS Kesehatan’s New Contribution Rate as a trending topic with a sentiment value of 61.7% positive and 38.3% negative.