Research Article

Method of Profanity Detection Using Word Embedding and LSTM

Table 8

Data sets.

Search keywordsNumber of postsSearch keywordsNumber of postsSearch keywordsNumber of posts

Gaesaekki (son of a bh)853,431Jotna (fking)560,440Sibal (fk)359,837
Byeongsin (dickhead)211,181Jonna (fking)275,631Annyeong (hello)285,554
Saekki (bastard)387,500Ssibal (fk)532,741Eumsik (food)169,428