• KSII Transactions on Internet and Information Systems
    Monthly Online Journal (eISSN: 1976-7277)

Profane or Not: Improving Korean Profane Detection using Deep Learning

Vol. 16, No. 1, January 31, 2022
10.3837/tiis.2022.01.017, Download Paper (Free):

Abstract

Abusive behaviors have become a common issue in many online social media platforms. Profanity is common form of abusive behavior in online. Social media platforms operate the filtering system using popular profanity words lists, but this method has drawbacks that it can be bypassed using an altered form and it can detect normal sentences as profanity. Especially in Korean language, the syllable is composed of graphemes and words are composed of multiple syllables, it can be decomposed into graphemes without impairing the transmission of meaning, and the form of a profane word can be seen as a different meaning in a sentence. This work focuses on the problem of filtering system mis-detecting normal phrases with profane phrases. For that, we proposed the deep learning-based framework including grapheme and syllable separation-based word embedding and appropriate CNN structure. The proposed model was evaluated on the chatting contents from the one of the famous online games in South Korea and generated 90.4% accuracy.


Statistics

Show / Hide Statistics

Statistics (Cumulative Counts from December 1st, 2015)
Multiple requests among the same browser session are counted as one view.
If you mouse over a chart, the values of data points will be shown.


Cite this article

[IEEE Style]
J. Woo, S. H. Park, H. K. Kim, "Profane or Not: Improving Korean Profane Detection using Deep Learning," KSII Transactions on Internet and Information Systems, vol. 16, no. 1, pp. 305-318, 2022. DOI: 10.3837/tiis.2022.01.017.

[ACM Style]
Jiyoung Woo, Sung Hee Park, and Huy Kang Kim. 2022. Profane or Not: Improving Korean Profane Detection using Deep Learning. KSII Transactions on Internet and Information Systems, 16, 1, (2022), 305-318. DOI: 10.3837/tiis.2022.01.017.

[BibTeX Style]
@article{tiis:25259, title="Profane or Not: Improving Korean Profane Detection using Deep Learning", author="Jiyoung Woo and Sung Hee Park and Huy Kang Kim and ", journal="KSII Transactions on Internet and Information Systems", DOI={10.3837/tiis.2022.01.017}, volume={16}, number={1}, year="2022", month={January}, pages={305-318}}