Skip to content
conftrace_
2021 EACL EACL 2021

Sarcasm and Sentiment Detection in Arabic language A Hybrid Approach Combining Embeddings and Rule-based Features

Abstract

AbstractThis paper presents the ArabicProcessors team’s system designed for sarcasm (subtask 1) and sentiment (subtask 2) detection shared task. We created a hybrid system by combining rule-based features and both static and dynamic embeddings using transformers and deep learning. The system’s architecture is an ensemble of Naive bayes, MarBERT and Mazajak embedding. This process scored an F1-score of 51% on sarcasm and 71% for sentiment detection.

Authors

Kamel Gaanoun, Imade Benelallam

Topics

Machine Learning > Core Methods > Classification Machine Learning > Learning Types > Weakly Supervised Learning Deep Learning > Architectures > Transformers

Keywords

ensemble learning sentiment classification sarcasm detection arabic language transformer embedding
Download PDF

More from EACL 2021

All EACL 2021 papers →
Deep Multi-Task Model for Sarcasm Detection and Sentiment Analysis in Arabic Language
A Contextual Word Embedding for Arabic Sarcasm Detection with Random Forests
SarcasmDet at Sarcasm Detection Task 2021 in Arabic using AraBERT Pretrained Model
Combining Context-Free and Contextualized Representations for Arabic Sarcasm Detection and Sentiment Identification
Leveraging Offensive Language for Sarcasm and Sentiment Detection in Arabic
The IDC System for Sentiment Classification and Sarcasm Detection in Arabic