• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권1호
• /
• pp.305-318
• /
• 2022

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.

• 창의정보문화연구
• /
• 제7권2호
• /
• pp.91-98
• /
• 2021

코로나19로 인해 초등학생이 온라인 환경에 머무는 시간이 증가함에 따라 작성하는 게시글, 댓글, 채팅의 양이 증가하였고, 타인의 감정을 상하게 하거나 욕설을 하는 등의 문제가 발생하고 있다. 네티켓을 초등학교에서 교육하고 있지만, 교육시간이 부족할 뿐 아니라 행동의 변화까지 기대하기는 어려움이 있어 자연어처리를 통한 기술적인 지원이 필요한 상황이다. 본 연구는 초등학생이 작성하는 문장에 사전언어학습 모델에 적용하여 자동으로 욕설문장을 필터링하는 실험을 진행하였다. 실험은 온라인 학습 플랫폼에서 초등학교 4-6학년의 채팅내역을 수집하였고, 채팅 내역중에 욕설로 신고되어 판정된 욕설문장을 함께 수집하여 사전학습된 언어모델을 통해 훈련하였다. 실험결과, 욕설문장을 분류한 결과 75%의 정확률을 보이는 것으로 분석되어 학습 데이터가 충분히 보완된다면, 초등학생이 사용하는 온라인 플랫폼에서 적용할 수 있음을 보여주었다.

• 반도체디스플레이기술학회지
• /
• 제20권1호
• /
• pp.83-87
• /
• 2021

By the increase of internet usage, communicating online became an everyday thing. Thereby various people have experienced profanity by anonymous users. Nowadays lots of studies tried to solve this problem using artificial intelligence, but most of the solutions were for non-real time situations. In this paper, we propose a Telegram plugin that detects swear words using word2vec, and an algorithm to find the target of the sentence. We vectorized the input sentence to find connections with other similar words, then inputted the value to the pre-trained CNN (Convolutional Neural Network) model to detect any swears. For target recognition we proposed a sequential algorithm based on KoNLPY.