Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Journal of Education Technology and Information System

Public Complaint Text Classification in the Wargaku Application Using Natural Language Processing Alfina Dian Febyani; I Kadek Dwi Nuryana
Journal of Education Technology and Information System Vol. 2 No. 02 (2026): Journal of Education Technology and Information System (JETIS)
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The Wargaku application is utilized by Surabaya residents to submit complaints concerning population administration services. With the increasing number of complaints, manual categorization becomes inefficient and susceptible to errors. This research aims to create an automatic classification system utilizing Natural Language Processing (NLP) and machine learning techniques. The dataset comprises 2,303 complaints divided into 18 categories. During preprocessing, text data was converted into numerical form using the Term Frequency–Inverse Document Frequency (TF-IDF) approach. Three machine learning models were tested: Support Vector Machine (SVM), Random Forest (RF), and Neural Network (NN), with evaluations based on accuracy and F1-score. Hyperparameter tuning was applied to enhance model performance. The SVM model yielded the best outcome with a training-to-testing data ratio of 85:15, resulting in a training accuracy of 93.96%, an F1-score of 96.08%, and a testing F1-score of 94.15%. This model was deployed in a web-based application via Streamlit to automatically categorize public complaints. The findings confirm the effectiveness of combining NLP and SVM in improving the efficiency of digital public service systems.
Article Reviewer Recommendation System Using Euclidean Distance Similarity with Content-Based Collaborative Filtering (Case Study: ICVEE) wilda; I Kadek Dwi Nuryana
Journal of Education Technology and Information System Vol. 3 No. 01 (2027): Journal of Education Technology and Information System (JETIS)
Publisher : Universitas Negeri Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

The growth of research publications in academic environments has resulted in large volumes of unstructured data, particularly in the form of article titles and abstracts. However, the majority of educational institutions still manage these resources manually, without optimizing them for academic decision-making. This study proposes an article reviewer recommendation system using a content-based filtering method with TF-IDF for text representation and Euclidean Distance as the similarity measure. Reviewer profiles are constructed based on previously reviewed articles. A new article is represented as a vector and compared against reviewer profiles to determine relevance. The system was evaluated using 20 articles as ground truth. Results show that the Euclidean Distance approach outperformed Cosine Similarity, achieving an accuracy of 55%, precision of 0.2333, recall of 0.2121, and F1-score of 0.222. This study demonstrates the potential of content-based filtering in enhancing reviewer assignment efficiency for academic conferences such as ICVEE.