This study aims to evaluate the impact of the policy issued by the Minister of Communication and Information Technology (PERMENKOMINFO No.5 of 2020) on the public's ability to access content through Private Scope Electronic System Providers (PSE). The study uses sentiment analysis and data classification methods to analyze the content of PERMENKOMINFO No.5 of 2020 and provides results on the accuracy of sentiment prediction. The results of the study show that the data classification method in sentiment analysis can provide accurate results in predicting the sentiment towards the content of PERMENKOMINFO No.5 of 2020. The study also highlights the need for improvement and better policy to ensure the interests of the public in accessing online information. The negative sentiment of 80.34% obtained through sentiment analysis provides important contributions for policy evaluation and feedback for improvement. This study provides valuable insights into the public's sentiment towards the PERMENKOMINFO No.5 of 2020 policy and its impact on their ability to access content. It also contributes to understanding the legal uncertainty in accessing content and reinforces the case for better policy to ensure the interests of the public.
Social media is free to access that can be used by the public to express opinions or voice opinions on a problem that arises and often becomes a trending topic. On July 30, 2022, viral #BlokirKominfo and #PSEMelanggarHAM for the implementation of supervision in the implementation of private electronic systems (PSE) as regulated in PERMENKOMINFO No.5 of 2020, which imposes sanctions applied to companies that do not or have not registered their system services, which causes the community not to be able to access the company's services. The various responses that arise need to be analyzed to understand the opinions conveyed. This study uses the sentiment analysis method to understand whether the opinions that appear are positive, negative, or neutral regarding the virality of the hashtag. Sentiment labelling was carried out on a dataset of 10,869 tweets using the Lexicon-Based Approach by implementing the Indonesian Sentiment (InSet) lexical dictionary based on the research of Fajri Koto and Gemala Y Rahmaningtyas and the classification of data on sentiment analysis in this study. The research results showed that 44.82% of the public had a negative response to the implementation of this regulation, 42.21% had a positive response, and 12.97% had a neutral response. Sentiment value prediction testing was carried out using a classification method consisting of 3 methods, namely Support Vector Machine (SVM), K-Nearest Neighbors (KNN), and Naïve Bayes Classifier (NBC). The highest classification results were obtained in the SVM method with an accuracy value of 79%, the second result was obtained in the NBC method with an accuracy value of 71%, and the lowest result was obtained in the KNN method with an accuracy value of 61%.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.