Claim Missing Document
Check
Articles

Found 2 Documents
Search

Klasifikasi Kategori Aduan Masyarakat pada Aplikasi Lapor Gubernur Menggunakan TF-IDF dan Decision Tree Sandi Pradananto; Muksan Junaidi
Jurnal Teknik Mesin, Industri, Elektro dan Informatika Vol. 5 No. 2 (2026): Jurnal Teknik Mesin, Industri, Elektro dan Informatika
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jtmei.v5i2.6176

Abstract

The digitalization of public complaint services through the LaporGub platform in Jawa Tengah has made it easier for citizens to submit aspirations and complaints to local governments. However, the complaint classification process still faces challenges because reports are written in diverse and unstructured free-text formats. This study implements the Decision Tree algorithm to automatically classify public complaint categories in Kabupaten Blora. The dataset consists of 244 complaint records processed using the Term Frequency-Inverse Document Frequency weighting method. To reduce data distribution imbalance, several minority categories were merged, resulting in eight main classes. Model evaluation was conducted using a stratified hold-out method with an 80:20 ratio and 5-fold cross-validation. The testing results achieved an accuracy of 59.18% with a weighted F1-score of 59.79%, while cross-validation produced an average accuracy of 57.35%. In addition, feature importance analysis revealed that words such as “school,” “oil,” “fertilizer,” “agriculture,” and “road” were the dominant factors influencing the classification decisions. Based on these findings, Decision Tree demonstrates good interpretability to support the initial recommendation process for complaint categorization, although its performance is still affected by limited data size and imbalanced class distribution.
Prediksi Engagement Unggahan Media Sosial Pimpinan Daerah Berdasarkan Bentuk Konten dan Tema Menggunakan Regresi Linear Berganda Ragil Setio Atmojo; Muksan Junaidi
Jurnal Teknik Mesin, Industri, Elektro dan Informatika Vol. 5 No. 2 (2026): Jurnal Teknik Mesin, Industri, Elektro dan Informatika
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/jtmei.v5i2.6191

Abstract

Social media has become a strategic channel for regional leaders to communicate public programs and build interaction with citizens. This study aims to predict the engagement level of regional leaders' social media posts by analyzing content format, post theme, Instagram impressions, Facebook impressions, and reached accounts. The research data were obtained from the social media insight dataset of regional leaders in Blora Regency in 2026, consisting of 150 posts from 14 February to 13 April 2026. A quantitative approach was applied using multiple linear regression, while engagement was calculated from likes, comments, shares, and reposts. The categorical variables were transformed using one-hot encoding, and the data were split into 80% training data and 20% testing data. The model evaluation produced Mean Absolute Error (MAE) 163.32, Mean Squared Error (MSE) 43712.84, Root Mean Squared Error (RMSE) 209.08, and R2 Score 0.804. These results indicate that the model explains approximately 80.4% of engagement variation in the test data, although the absolute error remains relatively high because social media responses fluctuate across posts.