natural-language-processing-5
Aggression Identification
3260 papers • 126 benchmarks • 313 datasets
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.
(Image credit: Papersgraph)
Benchmarks
These leaderboards are used to track progress in aggression-identification-5
Trend
Dataset
Best Model
Actions
No benchmarks available.
Libraries
iUse these libraries to find aggression-identification-5 models and implementations
Datasets
Subtasks
No subtasks available.
Most implemented papers
Aggressive Language Identification Using Word Embeddings and Sentiment Features
Constantin Orasan•Sun Jun 24 2018
The main features employed by the method are information extracted from word embeddings and the output of a sentiment analyser and it shows that despite its simplicity the method performs well when compared with more elaborated methods.
33