Text Clustering as A Computational Approach for Analyzing the Framing of Election News on Detik.com

DOI

10.2991/978-94-6239-636-4_18How to use a DOI?

Keywords

text clustering; media framing; election; k-means; web application

Abstract

This research develops a computational approach based on text clustering to analyze election news framing on the Detik.com portal. In the context of elections, media framing becomes an essential instrument in shaping public opinion towards political issues and actors. This research applies the K-Means algorithm to group news based on the similarity of text patterns in news titles, using TF-IDF weighting for feature representation. Data were collected through web scraping from the news.detik.com/pemilu channel between June 2023 and January 2024, resulting in more than 16,000 news items for analysis. This research also includes the development of a web application prototype using the Flask framework, which automates the text clustering process and supports framing analysis. This application offers features for exploring clustering results and word cloud visualization, enabling researchers to identify framing elements based on Entman’s theory—specifically, defining problems, diagnosing causes, making moral judgments, and recommending treatments. Cluster quality evaluation was conducted using the Davies-Bouldin Index (DBI), which yielded consistent cluster results and warranted further analysis. The results indicate that the clusters formed represent various news patterns, such as candidate support narratives, coalition dynamics, and election regulations. This research not only offers a quantitative approach to media framing analysis but also produces an intelligent system-based tool that can be replicated in other political text studies. The findings broaden the understanding of the application of text mining techniques for media framing analysis in the realm of digital political communication.

Copyright

© 2026 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  - Atik Ariesta
PY  - 2026
DA  - 2026/04/28
TI  - Text Clustering as A Computational Approach for Analyzing the Framing of Election News on Detik.com
BT  - Proceedings of the International Conference on Cross- Disciplinary Academic Research 2025 - Track 1 Advances in Computing, Electronics, Engineering, and Mathematics (ICAR-T1 2025)
PB  - Atlantis Press
SP  - 226
EP  - 245
SN  - 2352-5401
UR  - https://doi.org/10.2991/978-94-6239-636-4_18
DO  - 10.2991/978-94-6239-636-4_18
ID  - Ariesta2026
ER  -