Work

A Multi-Task Learning Framework for Modeling Engagement and Topic-Sensitive Responses in Arabic Women’s Discourse

Year: 2026

Type: conference-paper

Abstract: Predicting how audiences react to Arabic social media posts requires reasoning beyond textual sentiment: reactions emerge from collective interpretation moderated by engagement dynamics and topical context.We present a multi-task learning framework that jointly learns (i) audience reaction classification (Love, Haha, Angry, Sad, Care, Wow), (ii) engagement magnitude regression (six reactions, comments, shares), and (iii) non-engagement detection.On a corpus of 158k Arabic Facebook posts spanning women's rights, gender debates, and economic empowerment, our model achieves a test macro-F1 of 72.4 and weighted-F1 of 89.1.

Source: Findings of the Association for Computational Linguistics: EACL

DOI: 10.18653/v1/2026.findings-eacl.253

Authors: Mabrouka Bessghaier, Md. Rafiul Biswas, Shimaa Ibrahim, Wajdi Zaghouani

Institution: Northwestern University in Qatar

Language: English

Topic: Sentiment Analysis and Opinion Mining

Subfield: Artificial Intelligence

Field: Computer Science

Domain: Physical Sciences

Open Access status: hybrid

OpenAlex ID: W7140109497

FWCI: 17.87

Cites:

Cited by: 2

Related to: 10