Optimizing Community Report Categorization in Semarang City Through the Naïve Bayes Classifier Method

DOI

10.2991/978-94-6463-764-9_9How to use a DOI?

Keywords

Naïve Bayes Classifier; public complaints; text categorization; digital communication; information retrieval

Abstract

The rapid advancement of digital communication has transformed public service complaint management, enabling citizens to report issues through platforms such as SMS, websites, and social media. In Semarang City, the LAPOR! system facilitates public complaint submission, requiring efficient categorization for prompt resolution. This study developed and evaluated a complaint categorization system using the Naïve Bayes Classifier, targeting three categories: Information Requests, Aspirations, and Complaints. The research utilized 300 manually labeled training documents and 35 test documents, employing preprocessing techniques such as tokenization, stopword removal, and stemming to refine the data. The system’s performance was evaluated using a confusion matrix, achieving an accuracy of 71.45%. While effective, it underperformed compared to benchmarks, such as Multi-Variant Bernoulli Naïve Bayes achieving 97.43% accuracy for authorship attribution and Naïve Bayes delivering 96.60% recall in binary classification tasks. Limitations were attributed to reliance on manually labeled data and challenges in handling informal language and invalid reports. Despite these challenges, the system demonstrated practicality, simplicity, and alignment with governance needs. Recommendations include expanding datasets, incorporating advanced algorithms, and developing a stemming dictionary for informal language. A validation mechanism for invalid reports is also proposed. This research highlights the potential of Naïve Bayes in public service domains, providing a foundation for scalable systems. Future work can leverage hybrid approaches and broader datasets to optimize complaint categorization, enhancing public service delivery and advancing text classification applications.

Copyright

© 2025 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Kilala Mahadewi
AU  - Basirudin Ansor
AU  - Achmad Solichan
AU  - Muhammad Zainudin Amin
AU  - Mustika Restu Nur Asri
PY  - 2025
DA  - 2025/07/30
TI  - Optimizing Community Report Categorization in Semarang City Through the Naïve Bayes Classifier Method
BT  - Proceedings of the 3rd Lawang Sewu International Symposium on Engineering and Applied Sciences (LEWIS-EAS 2024)
PB  - Atlantis Press
SP  - 92
EP  - 99
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6463-764-9_9
DO  - 10.2991/978-94-6463-764-9_9
ID  - Mahadewi2025
ER  -