Opinion Mining of Environmental Issues on Instagram

Abstract

Indonesia has a complicated waste issue and is one of the biggest waste producers worldwide. The development of Instagram as one of the popular social media in conveying public opinion in the form of photos and captions has the potential to produce useful information for solving the waste issue. The study aims to investigate public opinion particularly the Instagram users about the waste crisis. It applied opinion mining in which the data sets were obtained from Instagram posts. The overall number of posts using #sampah until December 20th, 2019 was 109K, and the research sample cover posts from January 1st, 2018 to December 20th, 2019, totaling 54K posts. The developed system consists of three subprocess, namely document subjectivity, opinion orientation and target detection. The data were classified using feature reduction. The result showed that the most popular type of post was about social learning, while the meme posts were relatively low. The conclusion stated that public opinion on the waste issue in the captioned photos can be categorized into five including waste crisis monitoring, social learning, information enlightenment, cultural transformation, and memes. The discussion and solutions elaborated in this study can be utilized by the stakeholders of Penta Helix to realize the solution for waste issues