The proposed algorithmic approach deals with finding the sense of a word inan electronic data. Now a day,in different communication mediums like internet,mobile services etc. people use few words, which are slang in nature. Thisapproach detects those abusive words using supervised learning procedure. Butin the real life scenario, the slang words are not used in complete word formsalways. Most of the times, those words are used in different abbreviated formslike sounds alike forms, taboo morphemes etc. This proposed approach can detectthose abbreviated forms also using semi supervised learning procedure. Usingthe synset and concept analysis of the text, the probability of a suspiciousword to be a slang word is also evaluated.
展开▼
