TY - GEN
T1 - Learning to Engage
T2 - 19th Conference of the European Chapter of the Association for Computational Linguistics, Findings of EACL 2026
AU - Bessghaier, Mabrouka
AU - Biswas, Md R.
AU - Ibrahim, Shimaa Amer
AU - Zaghouani, Wajdi
N1 - Publisher Copyright:
©2026 Association for Computational Linguistics.
PY - 2026/3/29
Y1 - 2026/3/29
N2 - 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 macroF1 of 72.4 and weighted-F1 of 89.1.
AB - 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 macroF1 of 72.4 and weighted-F1 of 89.1.
UR - https://www.scopus.com/pages/publications/105038967844
U2 - 10.18653/v1/2026.findings-eacl.253
DO - 10.18653/v1/2026.findings-eacl.253
M3 - Conference contribution
AN - SCOPUS:105038967844
T3 - 19th Conference of the European Chapter of the Association for Computational Linguistics, Findings of EACL 2026
SP - 4846
EP - 4854
BT - 19th Conference of the European Chapter of the Association for Computational Linguistics, Findings of EACL 2026
PB - Association for Computational Linguistics (ACL)
Y2 - 24 March 2026 through 29 March 2026
ER -