BFCAI at SemEval-2022 Task 6: Multi-Layer Perceptron for Sarcasm Detection in Arabic Texts

TL;DR

This paper presents a simple multi-layer perceptron model using TF-IDF features for sarcasm detection in Arabic texts, achieving encouraging results without external resources.

Contribution

Introduces a straightforward neural network approach with TF-IDF features for Arabic sarcasm detection, demonstrating effectiveness without external data.

Findings

Encouraging accuracy on Arabic sarcasm detection

Model is simple and resource-efficient

No external resources needed

Abstract

This paper describes the systems submitted to iSarcasm shared task. The aim of iSarcasm is to identify the sarcastic contents in Arabic and English text. Our team participated in iSarcasm for the Arabic language. A multi-Layer machine learning based model has been submitted for Arabic sarcasm detection. In this model, a vector space TF-IDF has been used as for feature representation. The submitted system is simple and does not need any external resources. The test results show encouraging results.