Mozad Timothy Waluyan
Unknown Affiliation

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

Found 1 Documents
Search

Analisis Sentimen Kebutuhan Fast Track Pada Originals Vidio Menggunakan Support Vector Machine Mozad Timothy Waluyan; Kristoko Dwi Hartomo
JATISI (Jurnal Teknik Informatika dan Sistem Informasi) Vol 9 No 3 (2022): JATISI (Jurnal Teknik Informatika dan Sistem Informasi)
Publisher : Lembaga Penelitian dan Pengabdian pada Masyarakat (LPPM) STMIK Global Informatika MDP

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/jatisi.v9i3.2348

Abstract

Sentiment analysis is an analysis of textual data that provides a detailed analysis of expressed emotions, opinions, and can predict opportunities related to the results of the analysis. This study was conducted to see how Vidio.Com users responded to the original series, which did not yet have fast track capabilities. This helps Vidio.Com grow and improve its business compared to some other OTT companies that already have this feature. This survey uses Vidio.Com's original series of comments, which consists of 1403 comments. Since the dataset has no data labels, perform sentiment analysis to determine positive, neutral, and negative emotions. Sentiment analysis revealed 663 neutral emotions, 517 positive emotions, and 224 negative emotions. Based on these results, we can conclude that most Vidio.Com users need the fast-track features of the original series. This study also used the support vector machine method to test the distribution of training data and test data with 25%, 50%, 75%, and 100% characteristics. In addition, TfIdf weighting was performed and tests were run using the KFoldCrossValidationSystem. The 25er offers the highest accuracy at 86.04%. In tests using the kfold cross-validation system, a second kfold gives the highest accuracy with an accuracy score of 87.74%.