SemEval-2019-task-6-HAD

Evaluation of Offensive Tweets with target Classification. For more details: Coda Lab_OffensEval 2019 (SemEval 2019 - Task 6)

Sub-tasks

Sub-task A - Offensive language identification (Offensive / Not Offensive)

• 15 Jan 2019: A test data release - 17 Jan 2019: Submission deadline
  

Sub-task B - Automatic categorization of offense types (Targeted Insult and Threats / Untargeted)

• 22 Jan 2019: A test data release - 24 Jan 2019: Submission deadline
  

Sub-task C - Offense target identification (Target: Individual / Group / Other)

• 29 Jan 2019: A test data release - 31 Jan 2019: Submission deadline
  

Contributors

Himanshu Bansal Univesity of Tübingen
Daniel Nagel University of Tübingen
Anita Soloveva Lomonosov MSU, University of Tübingen

Preprocessing

1. Removing URLs and @USER
   
2. Parsing hashtags (See Christos Baziotis et. al. 2017)
   

Our approaches

1. We are using Long short-term memory network (LSTM) model.
   
2. LSTM with fasttext vectors
   

Sub-task A

1. Using an additional preprocessed training set of tweets
   
2. Postprocessing with emojis set and an offensive word list

Sub-task B & Sub-task C

1. Using a list of ethnic slurs
2. Using a list of top twitter profiles from United States, United Kindom, Saudi Arabia, Brazil and Spain