ANALISA PERFORMA METODE LIGHTGBM UNTUK PREDIKSI KECANDUAN MEDIA SOSIAL 322 302
DOI:
https://doi.org/10.26623/transformatika.v23i2.13165Abstrak
Media sosial kini telah menjadi bagian yang tidak terpisahkan dari aktivitas sehari-hari, didorong oleh perkembangan teknologi digital yang semakin cepat. Penggunaan media sosial yang berlebihan dapat memicu dampak negatif seperti gangguan psikologis, kurang tidur, dan konflik sosial. Penelitian ini menilai efektivitas Light Gradient Boosting Machine (LightGBM) dalam memprediksi kecanduan media sosial menggunakan data 705 responden dari Kaggle. Tahapan analisis mencakup pembersihan data, transformasi variabel kategorikal, dan seleksi fitur berbasis korelasi Pearson. Model dilatih dengan rasio 70:30 dan dievaluasi menggunakan akurasi, presisi, recall, serta f1-score. Hasil menunjukkan akurasi 98%, sehingga LightGBM dinilai sangat efektif sebagai model prediksi kecanduan media sosial.
Unduhan
Referensi
Unduhan
Diterbitkan
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2025 Roudhotul Jannah, Rastri Prathivi
Artikel ini berlisensi 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.
