Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Journal of Information Systems and Informatics

Sentiment Classification of TikTok Reviews on Almaz Fried Chicken Using IndoBERT and Random Oversampling Zaki, Imam Syahputra; Kurnia, Rizka Dhini; Meiriza, Allsela
Journal of Information System and Informatics Vol 7 No 4 (2025): December
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v7i4.1310

Abstract

The socio-political context surrounding the Indonesian Ulema Council's Fatwa No. 83 of 2023, which catalyzed a significant consumer shift, necessitates an accurate measure of public sentiment toward alternative local brands like Almaz Fried Chicken. Analyzing real-time consumer discourse on the challenging TikTok platform, the study utilized a final dataset of 4,374 unique comments to overcome the inherent problem of dataset imbalance and linguistic informality. The core method involved a seven-stage quantitative approach: data collection, preprocessing, sentiment labeling, data splitting (70:15:15), Random Oversampling (ROS), IndoBERT fine-tuning, and evaluation. This pipeline fine-tuned IndoBERT, a Transformer-based model, integrated with ROS applied exclusively to the training data. Evaluation demonstrated that ROS significantly reduced model bias and enhanced performance: Overall Accuracy increased by 2.0% (from 91% to 93%), and the Macro F1-Score improved by 3.4% (from 0.87 to 0.90). Most critically, the F1-Score for the minority Negative sentiment class surged from 0.78 to 0.84, confirming ROS's effectiveness in accurately detecting critical feedback. These findings provide timely, data-driven insights into brand perception amidst the boycott campaign and establish a robust, reliable IndoBERT-ROS methodology for advanced sentiment monitoring in dynamic social media environments.
Determinants of Impulsive Buying During Shopee Flash Sales: Ajzen’s Theory of Planned Behavior Approach Baidhawi, Alif; Afrina, Mira; Tania, Ken Ditha; Kurnia, Rizka Dhini
Journal of Information System and Informatics Vol 8 No 1 (2026): February
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i1.1452

Abstract

This research investigates the psychological elements that affect consumers’ impulsive buying behavior during Shopee flash sale events using the TPB. This inquiry employs a quantitative causal approach using survey data from 154 Shopee users engaged in flash sale purchases. Data were analyzed using a variance-based structural equation modeling approach with SmartPLS. The findings indicate that AT, SN, and PB jointly demonstrate significant effects on impulsive buying intention (β = 0.401; β = 0.395; β = 0.161), jointly explaining 59.9% of its variance. In addition, impulsive buying intention demonstrates a strong influence on actual impulsive buying behavior (β = 0.656, p < 0.001), accounting for 43.1% of the behavioral variance. Among the antecedents, attitude represents the most dominant predictor of intention, followed by subjective norms. A key advancement of this research stems from the integration of the TPB framework within flash sale contexts, positioning impulsive buying intention as a central psychological mechanism under conditions of time pressure. from a practical standpoint, the findings suggest that Shopee sellers and digital marketers should emphasize benefit-oriented messaging, urgency cues, and social validation features such as reviews, real time purchase indicators, and influencer endorsements to strengthen consumers’ impulsive buying intention during flash sale campaigns.