natural language processing, unstructured data, comments, classification, logistic regression, support vector ma-chine, stochastic gradient descent, random forest, strengthening the gradient, cross-validation


Purpose. Detecting toxic comments on YouTube video hosting under training videos by classifying unstructured text using a combination of machine learning methods. Methodology. To work with the specified type of data, machine learning methods were used for cleaning, normalizing, and presenting textual data in a form acceptable for processing on a computer. Directly to classify comments as “toxic”, we used a logistic regression classifier, a linear support vector classification method without and with a learning method – stochastic gradient descent, a random forest classifier and a gradient enhancement classifier. In order to assess the work of the classifiers, the methods of calculating the matrix of errors, accuracy, completeness and F-measure were used. For a more generalized assessment, a cross-validation method was used. Python programming language. Findings. Based on the assessment indicators, the most optimal methods were selected – support vector machine (Linear SVM), without and with the training method using stochastic gradient descent. The described technologies can be used to analyze the textual comments under any training videos to detect toxic reviews. Also, the approach can be useful for identifying unwanted or even aggressive information on social networks or services where reviews are provided. Originality. It consists in a combination of methods for preprocessing a specific type of text, taking into account such features as the possibility of having a timecode, emoji, links, and the like, as well as in the adaptation of classification methods of machine learning for the analysis of Russian-language comments. Practical value. It is about optimizing (simplification) the comment analysis process. The need for this processing is due to the growing volumes of text data, especially in the field of education through quarantine conditions and the transition to distance learning. The volume of educational Internet content already needs to automate the processing and analysis of feedback, over time this need will only grow.


Russell, M., & Klassen, M. (2020). Data Mining. Extracting information from Facebook, Twitter, Linkedln, Instagram, GitHub. St. Petersburg: Piter. (in Russan)

Anand, M., & Eswari, R. (2019). Classification of Abusive Comments in Social Media using Deep Learning. In 2019 3rd International Conference on Computing Methodologies and Communication (ICCMC) (pp. 974-977). Erode, India. DOI: (in English)

Andročec, D. (2020). Machine learning methods for toxic comment classification: a systematic review. Acta Univ. Sapientiae Informatica, 12(2), 205-216. (in English)

Casselman, I., & Heinrich, M. (2011). Novel use patterns of Salvia divinorum: Unobtrusive observation using YouTube™. Journal of Ethnopharmacology, 138(3), 662-667. DOI: (in English)

Chakrabarty, N. (2019). A Machine Learning Approach to Comment Toxicity Classification. Advances in Intelli-gent Systems and Computing (pp. 183-193). DOI: (in English)

Chary, M., Park, E. H., McKenzie, A., Sun, J., Manini, A. F., & Genes, N. (2014). Signs & Symptoms of Dextrome-thorphan Exposure from YouTube. PLoS ONE, 9(2), 1-10. DOI: (in English)

Hsu, C.-F., Caverlee, J., & Khabiri, E. (2011). Hierarchical comments-based clustering. SAC'11: Proceedings of the 2011 ACM Symposium on Applied Computing (рр. 1130-1137). DOI: (in English)

Jiang, M., Liang, Y., Feng, X., Fan, X., Pei, Z., Xue, Y., & Guan, R. (2016). Text classification based on deep belief network and softmax regression. Neural Computing and Applications, 29(1), 61-70. DOI: (in English)

Khabiri, E., Caverlee, J., & Hsu, C.-F. (2011). Summarizing User-Contributed Comments. Proceedings of the Fifth International AAAI Conference on Weblogs and Social Media (рр. 354-357). (in English)

Srivastava, S., Khurana, P., & Tewari, V. (2018). Identifying Aggression and Toxicity in Comments using Capsule Network. Proceedings of the First Workshop on Trolling, Aggression and Cyberbullying (TRAC-2018) (рр. 98-105). (in English)

Sun, C., Qiu, X., Xu, Y., & Huang, X. (2019). How to Fine-Tune BERT for Text Classification? In Lecture Notes in Computer Science (pp. 194-206). DOI: (in English)

Zaheri, S. Leath, J., & Stroud, D. (2020). Toxic Comment Classification. SMU Data Science Review, 3(1), 1-13. (in English)



How to Cite

Koriashkina, L. S. ., & Symonets, H. V. . (2021). APPLICATION OF MACHINE LEARNING ALGORITHMS FOR PROCESSING COMMENTS FROM THE YOUTUBE VIDEO HOSTING UNDER TRAINING VIDEOS. Science and Transport Progress. Bulletin of Dnipropetrovsk National University of Railway Transport, (6(90), 33–42. Retrieved from