Browse > Article
http://dx.doi.org/10.15207/JKCS.2020.11.6.023

Design and implementation of malicious comment classification system using graph structure  

Sung, Ji-Suk (Graduates School of Computer & Information Technology, Korea University)
Lim, Heui-Seok (Department of Computer Science and Engineering, Korea University)
Publication Information
Journal of the Korea Convergence Society / v.11, no.6, 2020 , pp. 23-28 More about this Journal
Abstract
A comment system is essential for communication on the Internet. However, there are also malicious comments such as inappropriate expression of others by exploiting anonymity online. In order to protect users from malicious comments, classification of malicious / normal comments is necessary, and this can be implemented as text classification. Text classification is one of the important topics in natural language processing, and studies using pre-trained models such as BERT and graph structures such as GCN and GAT have been actively conducted. In this study, we implemented a comment classification system using BERT, GCN, and GAT for actual published comments and compared the performance. In this study, the system using the graph-based model showed higher performance than the BERT.
Keywords
GCN; GAT; Text classification; NLP; BERT;
Citations & Related Records
연도 인용수 순위
  • Reference
1 Korea Internet & Security Agency. (2012). Internet Ethics Culture Survey Summary Report. Seoul. Korea Internet & Security Agency.
2 Y. Kim. (2014). Convolutional Neural Networks for Sentence Classification. https://doi.org/10.3115/v1/D14-1181
3 Zhou, C., Sun, C., Liu, Z. & Lau, F. C. M. (2015). A C-LSTM Neural Network for Text Classification. http://arxiv.org/abs/1511.08630
4 Devlin, J., M. W. Chang, K. Lee & Toutanova, K. (2018). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. Mlm. http://arxiv.org/abs/1810.04805
5 Liu, X., You, X., Zhang, X., Wu, J. & Lv, P. (2020). Tensor Graph Convolutional Networks for Text Classification. http://arxiv.org/abs/2001.05313
6 J. J. Hong. (2015). A Malicious Comments Detection Technique on the Internet. Soongsil University.
7 S. H. Kim. (2016). A Malicious Comments Detection Technique on the Internet using Artificial Neural Network. Soongsil University.
8 J. W. Kim, H. I. Jo & B. G. Lee. (2019). A Comparison Study on Performance of Malicious Comment Classification Models Applied with Artificial Neural Network. Journal of Digital Contents Society, 20, 1429-1437.   DOI
9 Kaggle. (2019). jigsaw-unintended-bias-in-toxicity-classification https://www.kaggle.com/c/jigsaw-unintended-bias-in-toxicity-classification
10 Kipf, T. N. & Welling, M. (2017). Semi-supervised classification with graph convolutional networks. 5th International Conference on Learning Representations, ICLR 2017 - Conference Track Proceedings, 1-14.
11 Kipf, T. N. (2016) Multi-layer Graph Convolutional Network (GCN) with first-order filters. https://tkipf.github.io/graph-convolutional-networks/images/gcn_web.png
12 J. R Kim. (2018). A Study on Corporate Reputation and Profitability - Focus on Online News and Comments -. Sungkyunkwan University.
13 Mikolov, T., Chen, K., Corrado, G. & Dean, J. (n.d.). 5021-Distributed-Representations-of-Words-and-Phrases-and-Their-Compositionality. 1-9. https://doi.org/10.1162/jmlr.2003.3.4-5.951
14 Kingma, D. P. & Ba, J. (2014). Adam: A Method for Stochastic Optimization. 1-15. https://doi.org/http://doi.acm.org.ezproxy.lib.ucf.edu/10.1145/1830483.1830503
15 Agarap, A. F. (2018). Deep Learning using Rectified Linear Units (ReLU). 1, 2-8. http://arxiv.org/abs/1803.08375
16 J. W. Kim & J. C. Kim. (2019). A Study on Factors Affecting Intention to Write Malicious Comments of Entertainers-related Post. Korean Association of Addiction Crime Review, 9(3), 1-20.
17 I. K. Jeong & Y. S. Kim. (2006). Impact of "Datgeul" of Online Media on Public Opinion : An Examination of Perception of Public Opinion and Third Person Effect. Korean Journal of Journalism & Communication Studies, 50, 302-327.