SOTAVerified

Aggression Identification

Develop a classifier that could make a 3-way classification in-between ‘Overtly Aggressive’, ‘Covertly Aggressive’ and ‘Non-aggressive’ text data. For this, TRAC-2 dataset of 5,000 aggression-annotated data from social media each in Bangla (in both Roman and Bangla script), Hindi (in both Roman and Devanagari script) and English for training and validation is to be used.

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 21–27 of 27 papers

TitleStatusHype
LSTMs with Attention for Aggression Detection—0
Merging Datasets for Aggressive Text Identification—0
RiTUAL-UH at TRAC 2018 Shared Task: Aggression Identification—0
Scmhl5 at TRAC-2 Shared Task on Aggression Identification: Bert Based Ensemble Learning Approach—0
Aggression Identification in Social Media: a Transfer Learning Based Approach—0
The ComMA Dataset V0.2: Annotating Aggression and Bias in Multilingual Social Media Discourse—0
A Unified System for Aggression Identification in English Code-Mixed and Uni-Lingual Texts—0
Show:102550
← PrevPage 3 of 3Next →

No leaderboard results yet.