Identification of hate speech and abusive language on indonesian Twitter using the Word2vec, part of speech and emoji features.
Muhammad Okky IbrohimMuhammad Akbar SetiadiIndra BudiPublished in: AISS (2019)
Keyphrases
- part of speech
- syntactic categories
- linguistic information
- lexical information
- n gram
- word sense disambiguation
- linguistic knowledge
- lexical features
- syntactic features
- co occurrence
- chinese word segmentation
- pos taggers
- english text
- syntactic information
- pos tagging
- noun phrases
- multiword
- machine translation
- feature vectors
- feature extraction
- unknown words
- natural language
- training corpus
- target language
- feature space
- language processing
- natural language processing
- image classification