Multilabel Classification for Toxic Comments in Indonesian
DOI:
https://doi.org/10.21512/emacsjournal.v2i1.6256Keywords:
Classification, toxic comment, deep learning architecturesAbstract
The more rapid development of the internet world, users can make comments on a variety of content on social networks, such as social media, blogs and others. Free users make comments triggering negative comments, making insults and incitement. By classifying user comments it is hoped that the system can be smarter to be able to distinguish threat, insult and incitement comments. The technique for classifying user comments uses deep learning, consisting of 6 classes. The results of experiments that have been conducted show that deep learning models produce an accuracy rate above 98%.References
Aken, B. Van, Risch, J., Krestel, R., & Alexander, L. (2018). Challenges for Toxic Comment Classification : An In-Depth Error Analysis Challenges for Toxic Comment Classification : An In-Depth Error Analysis, (August). https://doi.org/10.18653/v1/W18-5105
Georgakopoulos, S. V, Vrahatis, A. G., Tasoulis, S. K., & Plagianakos, V. P. (2018). Convolutional Neural Networks for Toxic Comment Classification. SETN.
Google, J. (2018). Toxic Comment Classification. Retrieved from https://www.kaggle.com/c/jigsaw-toxic-comment-classification-challenge/overview
Kallas, P. (2019). Top 15 Most Popular Social Networking Sites and Apps [2019]. Retrieved from https://www.dreamgrow.com/top-15-most-popular-social-networking-sites/
Mestry, S., Bisht, V., Chauhan, R., Tiwari, K., & Singh, H. (2019). MULTI-LABEL CLASSIFICATION OF TOXIC COMMENTS USING FAST-TEXT AND CNN, 18–21.
Ozoh, P., M O, O., & Adigun, A. A. (2019). Identification and Classification of Toxic Comments on Social Media using Machine Learning Techniques. International Journal of Research and Innovation in Applied Science (IJRIAS), (December).
Rumagit, R. Y., & Girsang, A. S. (2018). Prediction Personality Traits of Facebook Users Using Text Mining. Journal of Theoretical and Applied Information Technology, 96(20), 6877–6888.
Rumagit, R. Y., Setiyawati, N., & Bangkalang, D. H. (2019). Comparison of Graph-based and Term Weighting Method for Automatic Summarization of Online News. 4th International Conference on Computer Science and Computational Intelligence 2019 (ICCSCI), 0–9. https://doi.org/10.1016/j.procs.2019.08.220
Saif, M. A., Medvedev, A. N., & Medvedev, M. A. (2018). Classification of online toxic comments using the logistic regression and neural networks models Classification of Online Toxic Comments Using the Logistic Regression and Neural Networks Models. AIP Conference Proceedings 2048, 60011. https://doi.org/10.1063/1.5082126
Sharma, R., & Patel, M. (2018). Toxic Comment Classification Using Neural Networks and Machine Learning, 5(9), 47–52. https://doi.org/10.17148/IARJSET.2018.597
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, 98–105.
Tala, F. Z. (n.d.). A Study of Stemming Effects on Information Retrieval in Bahasa Indonesia.
Wiraguna, A., Faraby, S. Al, Sc, M., Adiwijaya, P., Si, S., & Si, M. (2019). Klasifikasi Topik Multi Label pada Hadis Bukhari dalam Terjemahan Bahasa Indonesia Menggunakan Random Forest. E-Proceeding of Engineering, 6(1), 2144–2153.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2020 Reinert Yosua Rumagit

This work is licensed under a Creative Commons Attribution-ShareAlike 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 - Share Alike that allows others to share the work with an acknowledgment 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 acknowledgment 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.
USER RIGHTS
All articles published Open Access will be immediately and permanently free for everyone to read and download. We are continuously working with our author communities to select the best choice of license options, currently being defined for this journal as follows: Creative Commons Attribution-Share Alike (CC BY-SA)


