Claim Missing Document
Check
Articles

Found 32 Documents
Search

IKN News Topic Analysis of Nusantara Capital City using Frobenius Norm and Non-negative Matrix Factorization Kartika, Luh Gede; Rinartha, Komang; Putra, Anggara Putu Dharma; Agung, I Gusti Ngurah Pertu
Samā Jiva Jnānam (International Journal of Social Studies) Vol. 2 No. 2 (2024): Vol. 2 No. 2 2024
Publisher : Fakultas Dharma Duta UHN IGB Sugriwa Denpasar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25078/ijoss.v2i2.4342

Abstract

This research leverages Non-negative Matrix Factorization (NMF) with the Frobenius norm to analyze news articles from Kompas about the relocation of Indonesia's capital to Nusantara. The study is significant as it provides insights into public and media perceptions documented by Kompas, identifies critical issues surrounding this transformative national project, and demonstrates the utility of NMF in analyzing Indonesian-language news texts, particularly in the context of public policy and media discourse. A dataset of news articles related to Ibu Kota Nusantara was preprocessed through cleaning, normalization, stemming/lemmatization, and tokenization to prepare it for topic modeling. Using TF-IDF for feature extraction, Non-Negative Matrix Factorization (NMF) with Frobenius norm as the loss function was applied to generate topics, which were evaluated based on coherence scores and manual analysis for relevance and interpretability. This study identified five distinct topics related to Ibu Kota Nusantara (IKN) from Kompas news articles during January-March 2024, covering community preparations, toll road developments, buffer zone status, groundbreaking events, and ASN housing. Using the NMF model and c_uci coherence scoring, the study achieved a high coherence score of 0.991, indicating semantically connected terms that facilitate topic interpretation. The alignment between Wordcloud and NMF results demonstrates both methods' focus on significant terms, with Wordcloud highlighting key words and NMF providing a deeper structural analysis of topic interrelations.
Evaluation of the Latent Dirichlet Allocation for Modeling News Topics of Nusantara Capital City Kartika, Luh Gede Surya; Putra, Anggara Putu Dharma; Rinartha, Komang; Megawati, Megawati
Jurnal CoreIT: Jurnal Hasil Penelitian Ilmu Komputer dan Teknologi Informasi Vol 11, No 2 (2025): December 2025
Publisher : Fakultas Sains dan Teknologi, Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/coreit.v11i2.33397

Abstract

Research regarding topic modeling on the coverage of the Nusantara Capital City (IKN) in national mass media remains limited. This study aims to not only model IKN-related topics but also rigorously evaluate the Latent Dirichlet Allocation (LDA) model to ensure its robustness for future implementation. The dataset comprises 1,498 news articles gathered from prominent Indonesian online media, specifically Detik (1,050 articles) and Kompas (448 articles). The methodology involves experimental variations of LDA parameters, including document volume, maximum features, and topic count, utilizing the Scikit-learn library. The results indicate that an increase in data volume and feature dimensions significantly correlates with longer computation times and a higher number of epochs required for convergence. Furthermore, the expansion of variables and data volume resulted in more negative log-likelihood values and increased perplexity, suggesting that model complexity challenges predictive precision. A convergence threshold of $1e^{-2}$ was applied to optimize the training cessation point. While this study establishes a baseline for static topic modeling, future research implies the necessity of Dynamic Topic Modeling (DTM) to capture the temporal evolution of topics, a dimension not addressed by the standard LDA model.