This repository contains Keras implementation for Context Integrated Model for Multi-label Emotion Detection, paper in Procedia computer science. 2018.
This repository includes:
- Arabic tweets dataset from SemEval 2018 competition.
- Code to train and run Emotion Classification.
- Code to train and run Topic-aware Emotion Classification.
- Code to evaluate the micro and macro F1 scores on the multi-label emotion classification task defined by the labels in the datasets
Samy, Ahmed E., Samhaa R. El-Beltagy, and Ehab Hassanien. "A context integrated model for multi-label emotion detection." Procedia computer science 142 (2018): 61-71.
The word embeddings used from the following paper: Soliman, Abu Bakr, Kareem Eissa, and Samhaa R. El-Beltagy. "Aravec: A set of arabic word embedding models for use in arabic nlp." Procedia Computer Science 117 (2017): 256-265.