Skip to content

quaziadib/Identifying-Offensive-Language-in-Social-Media

Repository files navigation

Identifying Offensive Language in Social Media

Dataset: OLID

Experiments:

Machine Learning

  • Unigram + TF-IDF + Linear SVC
  • Bi-gram + TF-IDF + Linear SVC
  • Tri-gram + TF-IDF + Linear SVC
  • Unigram and Bi-gram + TF-IDF + Linear SVC
  • Bi-gram and Tri-gram + TF-IDF + Linear SVC
  • Unigram, Bi-gram and Tri-gram + TF-IDF + Linear SVC
  • Unigram + Count Vectorizer + Linear SVC
  • Bi-gram + Count Vectorizer + Linear SVC
  • Tri-gram + Count Vectorizer + Linear SVC
  • Unigram and Bi-gram + Count Vectorizer + Linear SVC
  • Bi-gram and Tri-gram + Count Vectorizer + Linear SVC
  • Unigram, Bi-gram and Tri-gram + Count Vectorizer + Linear SVC

Deep Learning

  • Embedding + BiLSTM + Dense

Deep Hybird Learning