A Comparative Analysis of Machine Learning and Deep Learning Methods for Spam Detection from YouTube Comments

Anıl Utku

Makale detayları

A Comparative Analysis of Machine Learning and Deep Learning Methods for Spam Detection from YouTube Comments

Yazarlar:

Anıl Utku

Yayıncı:

Bingol University

Ana Başlıklar:

Doğal Dil İşleme

Dergi:

Bingöl Üniversitesi Teknik Bilimler Dergisi Vol.6 Issue 1, pp.30-50

Belge Tipi:

Makale

Yayın Tarihi:

6/2025

Belge Dili:

Türkçe

Document ID (Org No.):

2001348174

pISSN:

2757-6884

Anahtar kelimeler:

Özet:

 Since spam content threatens information security on social media platforms and manual detection methods are inadequate, the development of automatic spam detection systems is of great importance. Machine learning and deep learning techniques offer great advantages in classifying spam comments not only based on keywords but also by taking into account contextual relationships and language meaning. In this study, a comparative analysis of different machine learning and deep learning models is presented to automatically perform spam detection in YouTube comments. In the study, comprehensive analyses were performed to detect spam comments using LR, RF, SVM, XGBoost and Bi-LSTM. The texts were digitized using the TF-IDF vectorization method and a suitable data representation was created for training the models. Experimental results showed that Bi-LSTM outperformed the compared models with 97.1 classification accuracy thanks to its ability to learn long-term dependencies in text-based data.

 Since spam content threatens information security on social media platforms and manual detection methods are inadequate, the development of automatic spam detection systems is of great importance. Machine learning and deep learning techniques offer great advantages in classifying spam comments not only based on keywords but also by taking into account contextual relationships and language meaning. In this study, a comparative analysis of different machine learning and deep learning models is presented to automatically perform spam detection in YouTube comments. In the study, comprehensive analyses were performed to detect spam comments using LR, RF, SVM, XGBoost and Bi-LSTM. The texts were digitized using the TF-IDF vectorization method and a suitable data representation was created for training the models. Experimental results showed that Bi-LSTM outperformed the compared models with 97.1 classification accuracy thanks to its ability to learn long-term dependencies in text-based data.

 Since spam content threatens information security on social media platforms and manual detection methods are inadequate, the development of automatic spam detection systems is of great importance. Machine learning and deep learning techniques offer great advantages in classifying spam comments not only based on keywords but also by taking into account contextual relationships and language meaning. In this study, a comparative analysis of different machine learning and deep learning models is presented to automatically perform spam detection in YouTube comments. In the study, comprehensive analyses were performed to detect spam comments using LR, RF, SVM, XGBoost and Bi-LSTM. The texts were digitized using the TF-IDF vectorization method and a suitable data representation was created for training the models. Experimental results showed that Bi-LSTM outperformed the compared models with 97.1 classification accuracy thanks to its ability to learn long-term dependencies in text-based data.

 Spam içeriklerin sosyal medya platformlarındaki bilgi güvenliğini tehdit etmesi ve manuel tespit yöntemlerinin yetersiz kalması nedeniyle, otomatik spam tespit sistemlerinin geliştirilmesi büyük önem taşımaktadır. Makine öğrenmesi ve derin öğrenme teknikleri, spam yorumları yalnızca anahtar kelimelere dayanarak değil, bağlamsal ilişkileri ve dilin anlamını dikkate alarak sınıflandırmada büyük avantajlar sunmaktadır. Bu çalışmada, YouTube yorumlarında spam tespitini otomatik olarak gerçekleştirmek için farklı makine öğrenmesi ve derin öğrenme modellerinin karşılaştırmalı bir analizi sunulmuştur. Çalışmada, LR, RF, SVM, XGBoost ve Bi-LSTM kullanılarak spam yorumları tespit etmek için kapsamlı analizler yapılmıştır. TF-IDF vektörleştirme yöntemi kullanılarak metinler sayısal hale getirilmiş ve modellerin eğitimi için uygun bir veri temsili oluşturulmuştur. Deneysel sonuçlar, metin tabanlı verilerde uzun vadeli bağımlılıkları öğrenme yeteneği sayesinde Bi-LSTMin 97,1 sınıflandırma doğruluyla karşılaştırılan modellerden daha başarılı olduğunu göstermiştir.

Makale detayları

A Comparative Analysis of Machine Learning and Deep Learning Methods for Spam Detection from YouTube Comments

Yazarlar:

Anıl Utku

Yayıncı:

Bingol University

Ana Başlıklar:

Doğal Dil İşleme

Dergi:

Bingöl Üniversitesi Teknik Bilimler Dergisi Vol.6 Issue 1, pp.30-50

Belge Tipi:

Makale

Yayın Tarihi:

6/2025

Belge Dili:

Türkçe

Document ID (Org No.):

2001348174

pISSN:

2757-6884

Spam Detection

Machine Learning

Deep Learning

Bi-LSTMSpam Tespiti

Makine Öğrenmesi

Derin Öğrenme

Bi-LSTM

Sayı

Makale detayları

Yazarlar: Anıl Utku

Yayıncı: Bingol University

Ana Başlıklar: Doğal Dil İşleme

Dergi: Bingöl Üniversitesi Teknik Bilimler Dergisi Vol.6 Issue 1, pp.30-50

Belge Tipi: Makale

Yayın Tarihi: 6/2025

Belge Dili: Türkçe

Document ID (Org No.): 2001348174

pISSN: 2757-6884

Sayı

Yazarlar:

Anıl Utku

Yayıncı:

Bingol University

Ana Başlıklar:

Doğal Dil İşleme

Dergi:

Bingöl Üniversitesi Teknik Bilimler Dergisi Vol.6 Issue 1, pp.30-50

Belge Tipi:

Makale

Yayın Tarihi:

6/2025

Belge Dili:

Türkçe

Document ID (Org No.):

2001348174

pISSN:

2757-6884