Abigail Rosandrine Kayla Putri Rahadi
Atma Jaya Catholic University of Indonesia, Jakarta

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

Sentiment and Topic Analysis of Aftermovie Piala Presiden eSports 2019 (Onic Esport) Ruben William Setiawan; Abigail Rosandrine Kayla Putri Rahadi; Yerik Afrianto Singgalen
Journal of Information System Research (JOSH) Vol 5 No 3 (2024): April 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v5i3.5036

Abstract

This research addresses the research problem of sentiment classification and topic analysis in the context of the Aftermovie Piala Presiden Esports 2019 (Onic Esport), employing the CRISP-DM methodology. Leveraging a dataset comprising 1830 posts, sentiment analysis was conducted on 191 posts using Vader and TextBlob algorithms, revealing the distribution of polarity values: 7.41% negative, 58.02% neutral, and 34.57% positive sentiments. Furthermore, the study evaluates the performance of classification algorithms, such as k-nearest Neighbors (k-NN), Support Vector Machine (SVM), and Decision Tree (DT), utilizing SMOTE. Notably, SVM demonstrated an accuracy of 90.34%, AUC of 0.995, precision of 99.91%, recall of 80.77%, and F-measure of 89.29%. Similarly, DT exhibited an accuracy of 94.83%, AUC of 0.950, precision of 92.12%, recall of 98.12%, and F-measure of 95.00%. K-NN displayed an accuracy of 92.83%, AUC of 0.972, precision of 98.01%, recall of 87.46%, and F-measure of 92.42%. The analysis also revealed frequently used words in the dataset, including 'onic' (127 occurrences), 'udil' (95 occurrences), and 'piala' (28 occurrences). This study sheds light on sentiment patterns and prevalent topics among esports enthusiasts, offering insights for content optimization and event management strategies.