Article Per Year (5 Year)
p-Index From 2020 - 2025
0.659
P-Index
This Author published in this journals
All Journal Jurnal Informa: Jurnal Penelitian dan Pengabdian Masyarakat Journal Of Artificial Intelligence And Software Engineering
Cipto Utomo, Bangun Prajadi
Unknown Affiliation
Computer Science & IT

Published : 3 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : Journal Of Artificial Intelligence And Software Engineering

 1 
Sentiment Analysis of Fans Toward Brand Merchandise Releases Using Support Vector Machine (SVM) Munaiseche, Christian Imanuel; Nurchim, Nurchim; Cipto Utomo, Bangun Prajadi
Journal of Artificial Intelligence and Software Engineering Vol 5, No 3 (2025): September
Publisher : Politeknik Negeri Lhokseumawe

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30811/jaise.v5i3.7264

Abstract

The release of merchandise by idol groups often sparks various emotional reactions among fans, particularly on social media platforms. This study investigates fan sentiment regarding the birthday merchandise release by JKT48 members on the X (Twitter) platform using the Support Vector Machine (SVM) algorithm. A total of 1,062 comments were collected using the Tweet Harvest tool and manually categorized into three sentiment classes: positive, neutral, and negative. The collected data underwent several pre-processing stages, including case folding, data cleansing, tokenization, and stopword removal. The text data were then transformed into numerical features using the Term Frequency-Inverse Document Frequency (TF-IDF) method. To address the class imbalance issue, the Synthetic Minority Over-sampling Technique (SMOTE) was applied. Experimental results show that the SVM model without SMOTE achieved an accuracy of 84.62% and an F1-score of 76.79%. After applying SMOTE, model performance improved significantly, with accuracy reaching 90.09% and F1-score increasing to 90.15%. Furthermore, the results of 5-fold cross-validation confirmed the positive impact of SMOTE in enhancing the model's ability to classify sentiment, particularly for underrepresented classes.
Co-Authors Munaiseche, Christian Imanuel Nurchim Nurchim Santosa, Tri Djoko Suryani, Fajar