Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Building of Informatics, Technology and Science Journal of Social Responsibility Projects by Higher Education Forum
Imam Saputra
Sekolah Tinggi Ilmu Manajemen Sukma, Medan
Aerospace Engineering Agriculture, Biological Sciences & Forestry Automotive Engineering Chemical Engineering, Chemistry & Bioengineering Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Electrical & Electronics Engineering Energy Engineering Industrial & Manufacturing Engineering Materials Science & Nanotechnology Mathematics Social Sciences

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Random Forest, LSTM, and IndoBERT Comparison for TikTok App Sentiment Analysis Imam Saputra; Mesran Mesran; Ruziana Mohamad Rasli
Building of Informatics, Technology and Science (BITS) Vol 8 No 1 (2026): June 2026
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v8i1.9714

Abstract

The rapid growth of social media platforms like TikTok has generated a massive volume of user reviews on the Google Play Store, serving as a critical indicator of application service quality. However, the unstructured nature of Indonesian social media text and the significant imbalance between sentiment classes pose substantial challenges for automated classification systems. Addressing this class imbalance is highly crucial for application developers, as critical negative and neutral feedback containing essential feature complaints is easily marginalized by the overwhelming majority of positive reviews, leading to biased operational insights. This research conducted a comprehensive comparative study of three distinct computational paradigms: Random Forest, Long Short-Term Memory (LSTM), and IndoBERT, to identify the most effective model for sentiment analysis. A dataset of 5,000 TikTok reviews was meticulously processed using a negation-aware preprocessing pipeline to preserve semantic integrity. To address class imbalance, architecture-specific techniques were deployed, including SMOTE for Random Forest, Class Weighting for LSTM, and Random OverSampling for IndoBERT. The experimental results demonstrate that IndoBERT significantly outperforms other models, achieving the highest global accuracy of 81% and a Macro F1-Score of 0.56. While Random Forest and LSTM yielded lower accuracies of 75% and 71%, respectively, they exhibited stability in predicting the majority class but struggled with the inherent ambiguity of neutral sentiments. The study concludes that IndoBERT’s bidirectional self-attention mechanism provides superior contextual understanding of Indonesian slang and non-formal syntax. This research contributes a robust framework for application developers to monitor public opinion objectively. Furthermore, the findings highlight that despite advanced balancing techniques, the "neutrality bottleneck" remains a challenge, suggesting that future research should explore aspect-based sentiment analysis to enhance classification granularity in the Indonesian NLP domain.
Utilization of Hybrid Digital Technologies for Optimizing Waste Bank Management and Elevating Community Literacy Imam Saputra; Mesran Mesran; Dian Purnama Sari; Dito Putro Utomo
Journal of Social Responsibility Projects by Higher Education Forum Vol 7 No 1 (2026): July 2026
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/jrespro.v7i1.10793

Abstract

Grassroots community waste banks play a pivotal role in urban environmental management; however, they frequently face operational bottlenecks due to reliance on conventional paper-based record-keeping. The community partner faced severe challenges, including administrative processing delays, accounting errors in customer balances, and limited market reach for upcycled products. To address these problems, this community service activity aimed to optimize waste bank administration and elevate digital marketing literacy through an integrated hybrid capacity-building framework. The contribution of this initiative lay in deploying a low-latency hybrid learning setup—combining dual-WAN bonding, multi-camera switching, and cloud-accessible digital ledger tools—to deliver interactive training across physical and synchronous online cohorts (). Methodologically, a mixed-methods approach evaluated participant progress using pre- and post-test diagnostic questionnaires and post-event usability surveys. The results of the community service demonstrated a statistically significant increase in participant digital literacy (), with composite cognitive scores improving from a baseline of to , achieving a high normalized Hake gain (). Field execution successfully digitized operational transaction logs, eliminated calculation discrepancies, and enabled digital cataloging on social media platforms for waste-derived products. Overall participant evaluation indicated outstanding satisfaction (), confirming the practical utility and technical reliability of the hybrid delivery system. This activity successfully transformed the partner's operational workflows from manual ledgers to transparent digital management while offering a scalable model for circular economy empowerment.
Co-Authors Dian Purnama Sari Dito Putro Utomo Mesran Mesran Ruziana Mohamad Rasli