Melola Discovery

← Melola Discovery

Akses terbuka Jurnal SINTA 2

Gambling Comments Detection on Youtube: A Comparative Study of Tree-Based Boosting, LSTM and GRU Models

JUTI: Jurnal Ilmiah Teknologi Informasi · Vol. 23 No. 2 (2025) · hlm. 144–160

DOI
10.12962/j24068535.v23i2.a1305
ISSN
2406-8535, 1412-6389
Terbit
2025-07-08
Penerbit
Institut Teknologi Sepuluh Nopember
Bahasa
eng
Lisensi
creativecommons.org/licenses/by-sa/4.0

Abstrak

The exponential growth of online gambling in Indonesia poses significant socio-economic challenges, particularly affecting vulnerable populations through sophisticated digital marketing strategies targeting social media platforms. This study addresses the critical need for automated detection systems to identify gambling-related content in YouTube comments. We scraped and manually labeled 11,673 comments from diverse YouTube videos, creating an extremely imbalanced dataset with gambling comments representing only 10% of the total data. Multiple machine learning approaches were developed and evaluated, comparing traditional gradient boosting methods (LightGBM, XGBoost, CatBoost) using TF-IDF features against deep learning models (LSTM & GRU) with Word2Vec embeddings. The experimental results demonstrate that gradient boosting methods significantly outperform deep learning approaches in generalization capability. LightGBM achieved the highest holdout F1-score with balanced precision (0.8912) and recall (0.8886), while XGBoost followed closely with comparable performance. In contrast, deep learning models exhibited severe overfitting, with GRU and LSTM showing excellent test performance but drastically reduced holdout recall (0.5022 and 0.4844, respectively). The findings indicate that the dataset size was insufficient for deep learning approaches to learn generalizable representations effectively. For practical deployment in YouTube gambling content detection, gradient boosting methods are recommended due to their superior performance with limited, imbalanced datasets.

Jaringan kolaborasi para penulis

3 penulis · 3 tautan kepenulisan bersama

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Afiliasi tidak diketahui
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OAI-PMH (metadata jurnal) https://juti.if.its.ac.id/index.php/juti/oai, pertama di-harvest 26 Okt 2026, terakhir terlihat 15 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en">Gambling Comments Detection on Youtube: A Comparative Study of Tree-Based Boosting, LSTM and GRU Models</dc:title>
	<dc:creator xml:lang="en">Widiyanto, Agung</dc:creator>
	<dc:creator xml:lang="en">Prameswari, Mayesq</dc:creator>
	<dc:creator xml:lang="en">Abdul Latief, Muhammad</dc:creator>
	<dc:description xml:lang="en">The exponential growth of online gambling in Indonesia poses significant socio-economic challenges, particularly affecting vulnerable populations through sophisticated digital marketing strategies targeting social media platforms. This study addresses the critical need for automated detection systems to identify gambling-related content in YouTube comments. We scraped and manually labeled 11,673 comments from diverse YouTube videos, creating an extremely imbalanced dataset with gambling comments representing only 10% of the total data. Multiple machine learning approaches were developed and evaluated, comparing traditional gradient boosting methods (LightGBM, XGBoost, CatBoost) using TF-IDF features against deep learning models (LSTM &amp;amp; GRU) with Word2Vec embeddings. The experimental results demonstrate that gradient boosting methods significantly outperform deep learning approaches in generalization capability. LightGBM achieved the highest holdout F1-score with balanced precision (0.8912) and recall (0.8886), while XGBoost followed closely with comparable performance. In contrast, deep learning models exhibited severe overfitting, with GRU and LSTM showing excellent test performance but drastically reduced holdout recall (0.5022 and 0.4844, respectively). The findings indicate that the dataset size was insufficient for deep learning approaches to learn generalizable representations effectively. For practical deployment in YouTube gambling content detection, gradient boosting methods are recommended due to their superior performance with limited, imbalanced datasets.</dc:description>
	<dc:publisher xml:lang="en">Institut Teknologi Sepuluh Nopember</dc:publisher>
	<dc:date>2025-07-08</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en">Peer-reviewed Article</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://juti.if.its.ac.id/index.php/juti/article/view/1305</dc:identifier>
	<dc:identifier>10.12962/j24068535.v23i2.a1305</dc:identifier>
	<dc:source xml:lang="en">JUTI: Jurnal Ilmiah Teknologi Informasi; Vol.23, No.2, July 2025; 144-160</dc:source>
	<dc:source>2406-8535</dc:source>
	<dc:source>1412-6389</dc:source>
	<dc:source>10.12962/j24068535.v23i2</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://juti.if.its.ac.id/index.php/juti/article/view/1305/561</dc:relation>
	<dc:rights xml:lang="en">Copyright (c) 2025 Agung Widiyanto, Mayesq Prameswari, Muhammad Abdul Latief</dc:rights>
	<dc:rights xml:lang="en">https://creativecommons.org/licenses/by-sa/4.0</dc:rights>
</oai_dc:dc>