Analisa Performa Metode LightGBM untuk Prediksi Kecanduan Media Sosial
DOI:
https://doi.org/10.26623/transformatika.v23i2.13165Abstract
Social media has now become an integral part of daily activities, driven by the increasingly rapid development of digital technology. Excessive social media use can trigger negative impacts such as psychological disorders, sleep deprivation, and social conflict. This study assesses the effectiveness of the Light Gradient Boosting Machine (LightGBM) in predicting social media addiction using data from 705 respondents from Kaggle. The analysis stages included data cleaning, categorical variable transformation, and feature selection based on Pearson correlation. The model was trained with a 70:30 ratio and evaluated using accuracy, precision, recall, and f1-score. The results showed 98% accuracy, thus LightGBM is considered highly effective as a social media addiction prediction model.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Roudhotul Jannah, Rastri Prathivi
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work.
Transformatika is licensed under a Creative Commons Attribution 4.0 International License.
