Detailed Information

Cited 0 time in webofscience Cited 0 time in scopus
Metadata Downloads

Profane or Not: Improving Korean Profane Detection using Deep Learning

Authors
Woo, JiyoungPark, Sung HeeKim, Huy Kang
Issue Date
31-1월-2022
Publisher
KSII-KOR SOC INTERNET INFORMATION
Keywords
Profanity; deep learning; convolutional neural network; text mining; natural language processing
Citation
KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS, v.16, no.1, pp.305 - 318
Indexed
SCIE
SCOPUS
KCI
Journal Title
KSII TRANSACTIONS ON INTERNET AND INFORMATION SYSTEMS
Volume
16
Number
1
Start Page
305
End Page
318
URI
https://scholar.korea.ac.kr/handle/2021.sw.korea/137518
DOI
10.3837/tiis.2022.01.017
ISSN
1976-7277
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.
Files in This Item
There are no files associated with this item.
Appears in
Collections
School of Cyber Security > Department of Information Security > 1. Journal Articles

qrcode

Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.

Altmetrics

Total Views & Downloads

BROWSE