Article Per Year (5 Year)
p-Index From 2021 - 2026
2.144
P-Index
This Author published in this journals
All Journal INTENSIF: Jurnal Ilmiah Penelitian dan Penerapan Teknologi Sistem Informasi Building of Informatics, Technology and Science Jurnal Tekinkom (Teknik Informasi dan Komputer) JISA (Jurnal Informatika dan Sains) Journal of Telenursing (JOTING) Innovation in Research of Informatics (INNOVATICS) Jurnal Teknik Informatika (JUTIF) Journal of Applied Data Sciences Jurnal Sistem Informasi dan Teknik Informasi DEVICE : JOURNAL OF INFORMATION SYSTEM, COMPUTER SCIENCE AND INFORMATION TECHNOLOGY
Junadhi, Junadhi
Unknown Affiliation
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering Health Professions Medicine & Pharmacology Nursing Other

Published : 14 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 14 Documents
Search

 1   2 
Opinion Mining on TikTok Using Bidirectional Long Short-Term Memory for Enhanced Sentiment Analysis and Trend Prediction Muharnisa Haspin, Wafiq; Junadhi, Junadhi; Susanti, Susanti; Yenni, Helda
Building of Informatics, Technology and Science (BITS) Vol 7 No 2 (2025): September 2025
Publisher : Forum Kerjasama Pendidikan Tinggi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bits.v7i2.8019

Abstract

The widespread use of TikTok has generated a vast number of user reviews, offering a rich dataset for sentiment analysis. This study aims to classify TikTok reviews from the Google Play Store into positive, negative, and neutral categories, a complex task due to the informal and unstructured text. The research seeks to develop a reliable sentiment analysis model using deep learning to understand user perceptions, aiding platform improvements and marketing strategies. We collected 10,000 reviews via web scraping, preprocessed through text cleaning, normalization, tokenization, filtering, and stemming. Sentiment labels were assigned automatically using a lexicon-based approach, showing predominantly positive reviews. Word2Vec transformed text into numerical vectors for feature extraction. The Bidirectional Long Short-Term Memory (Bi-LSTM) model, with Embedding, Bidirectional LSTM, Dropout, and Dense layers, achieved 80% accuracy and an F1-score of 0.78 using a 90:10 train-test split. While effective for positive and negative sentiments, neutral expressions were less accurately detected due to lower recall. Compared to traditional methods like Naive Bayes, Support Vector Machine, and K-Nearest Neighbors, Bi-LSTM offered superior accuracy and better handling of linguistic variability, making it valuable for analyzing social media feedback.
Development of Knowledge Management System to Improve the Performance of the New Student Admission System for Higher Education Anam, M. Khairul; Fitri, Triyani Arita; Zoromi, Fransiskus; Junadhi, Junadhi; Nu'man, Nu'man
JISA(Jurnal Informatika dan Sains) Vol 5, No 2 (2022): JISA(Jurnal Informatika dan Sains)
Publisher : Universitas Trilogi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31326/jisa.v5i2.1443

Abstract

The New Student Admission System (PMB) is the main door or core business of the University and requires a good management system. Every Academic Year STMIK Amik Riau forms a committee to carry out this PMB activity. The PBM committee consists of several parts, namely the promotion section, the registration section and the selection section.  Each section carries out knowledge sharing or knowledge transfer in carrying out its duties. This knowledge sharing is only limited to informal or formal communication through meetings so that the knowledge sharing process has not been carried out optimally. The purpose of this study was (1) to measure the readiness of human resources in the application of knowledge sharing in terms of the dimensions of knowledge, culture, technology and dimensions and (2) to develop knowledge sharing features in the PMB system to support decision making quickly to increase the business value of the institution. The stages used in this KMS were The 10-Step Knowledge Management Roadmap while the evaluation of the application of KMS used the SECI model. The results obtained in this study are a system that helps new PMB officers learn the STMIK Amik Riau PMB system. so that the new PMB officer does not ask the old officer again.
Analisis Sentimen Kesehatan Mental Pemuda di Media Sosial Menggunakan Deep Learning Agustin, Agustin; Junadhi, Junadhi; Zoromi, Fransiskus; Kudadiri, Parlindungan
DEVICE : JOURNAL OF INFORMATION SYSTEM, COMPUTER SCIENCE AND INFORMATION TECHNOLOGY Vol 6, No 2: DESEMBER 2025
Publisher : Universitas Dharmawangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46576/device.v6i2.8112

Abstract

Kesehatan mental merupakan isu yang semakin penting di kalangan pemuda Indonesia, terutama dengan meningkatnya ekspresi emosi negatif seperti stres, kelelahan, dan kecemasan yang sering diungkapkan melalui media sosial. Penelitian ini bertujuan untuk menganalisis sentimen kesehatan mental pemuda menggunakan pendekatan deep learning berbasis Long Short-Term Memory (LSTM) terhadap unggahan publik berbahasa Indonesia di platform X (Twitter). Data dikumpulkan melalui proses web scraping dengan kata kunci yang relevan dan kemudian melalui tahapan pra-pemrosesan, pelabelan manual, serta pembagian data menjadi 80% untuk pelatihan dan 20% untuk pengujian. Model LSTM dibangun dengan arsitektur yang terdiri atas embedding layer, LSTM layer, dropout layer, dense layer, dan output layer beraktivasi Softmax untuk tiga kelas sentimen (positif, negatif, dan netral). Hasil penelitian menunjukkan distribusi sentimen menunjukkan bahwa emosi negatif mendominasi dengan proporsi 45,8%, diikuti oleh sentimen positif sebesar 35,8%, dan netral sebesar 18,4%.Model mampu mencapai akurasi sebesar 87,4% dengan nilai precision dan recall rata-rata sebesar 0,85, yang menandakan kemampuan tinggi dalam mengenali konteks bahasa informal pemuda di media sosial. Analisis distribusi sentimen menunjukkan dominasi emosi negatif yang berkaitan dengan tekanan akademik dan sosial, sementara sentimen positif menggambarkan semangat dan mekanisme adaptasi diri. Temuan ini membuktikan bahwa LSTM efektif untuk deteksi ekspresi emosional berbasis teks serta berpotensi diterapkan sebagai sistem pemantauan digital bagi kesejahteraan mental generasi muda.
Predicting Mental Health Status using a Fine-Tuned CNN-LSTM Hybrid Model Agustin, Agustin; Junadhi, Junadhi; Erlinda, Susi; Arita Fitri, Triyani; Efrizoni, Lusiana
Jurnal Teknik Informatika (Jutif) Vol. 7 No. 3 (2026): JUTIF Volume 7, Number 3, June 2026
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2026.7.3.5882

Abstract

Mental health has become a critical global concern in the digital era, particularly as social media platforms increasingly serve as spaces where users express psychological conditions, emotions, and personal struggles. This study aims to predict mental health status from Twitter text using a fine-tuned hybrid CNN–LSTM deep learning model. A total of 12,214 tweets were collected, cleaned, and labeled into five categories: Normal, Stress, Anxiety, Depression, and High-Risk Condition. The dataset was split using stratified sampling into 70% training, 15% validation, and 15% testing portions. Text was transformed into numerical representations through tokenization, padding, and 100-dimensional word embeddings. The hybrid CNN–LSTM architecture combines the CNN’s ability to extract local linguistic features with the LSTM’s strength in capturing long-term contextual dependencies, supported by dropout, early stopping, and hyperparameter fine-tuning. Experimental results show that the hybrid model achieves superior performance compared to standalone CNN and LSTM architectures, obtaining an overall accuracy of 0.892, macro precision of 0.874, macro recall of 0.861, and a macro F1-score of 0.865. Class-wise evaluation indicates that the Normal category achieves the highest accuracy (0.960), followed by Anxiety (0.884) and High-Risk Condition (0.808). Meanwhile, Stress (0.751) and Depression (0.745) show lower accuracies due to semantic overlap in linguistic expressions commonly found on social media. The training process demonstrates stable convergence without significant overfitting, confirming the effectiveness of the selected architecture and training strategy. Overall, this study highlights the effectiveness of the hybrid CNN–LSTM model for early mental health detection based on text data. The findings provide a strong foundation for developing scalable and data-driven mental health monitoring systems in digital environments and contribute to advancing natural language processing approaches for mental health analysis.
Co-Authors Adyanata Lubis Agustin Agustin Anam, M Khairul Andesa, Khusaeri Arita Fitri, Triyani Asrofiq, Ahmad Desti Puswati Devita, Yeni Edwar Ali Efrizoni, Lusiana Erlinda, Susi Fadliellah, Mardiyat Finanta Okmayura Fransiskus Zoromi, Fransiskus Habibie, Dedi Rahman Hadi Asnal, Hadi Handoko Handoko Helda Yenni, Helda Herwin Herwin Herwin, Herwin Husen, Ratna Andini Kudadiri, Parlindungan Martina Sinta Kristanti Meidina, Mita Muharnisa Haspin, Wafiq Muslim Muslim Negara, Ari Sukma Nita, Yureya Nu'man, Nu'man Perumal, Thinagaran Putra, Jean Riko Kurniawan Rahmiati Rahmiati Retno Sari Sarjon Defit Susanti Susanti SUSI ERLINDA Triyani Arita Fitri Unang Rio Yoyon Efendi Yuda Irawan