EUVIMEDScopri EUVIMED
Open access · CC BY 4.0

A Directional Semantic Enhancement Approach with Gated Fusion for Multimodal Arabic Sentiment Analysis

Ayoub Ben Cheikhi, El Habib Nfaoui, Oumayma Elbiach

Machine Learning and Knowledge Extraction · 2026-05-21 · 8 (5) · 139

DOI: 10.3390/make8050139 ↗

At a glance

Journal article in Machine Learning and Knowledge Extraction, published online on 2026-05-21. Written by Ayoub Ben Cheikhi and 2 co-authors. 47 references. The full text is freely available (open access, CC BY 4.0).

AbstractDati bibliograficiCiteRelated studies

Abstract (original language)

Multimodal Arabic sentiment analysis has gained increasing attention due to the growing volume of user-generated multimedia content. However, effectively integrating textual, acoustic, and visual modalities remains challenging because of modality imbalance and weak cross-modal alignment. This study proposes a Directional Semantic Enhancement approach with Gated Fusion to address these limitations. The objective is to explicitly model similarity-guided semantic transfer between modalities while adaptively regulating information flow during fusion. The proposed architecture consists of four main stages: modality encoding, directional semantic enhancement, gated fusion, and classification. Directional semantic interactions enable structured cross-modal knowledge exchange, while adaptive gating mechanisms balance original and enhanced representations to mitigate modality-specific noise. Extensive experiments are conducted on the Ar-MuSA benchmark dataset, which contains 8700 multimodal samples. The proposed approach achieves 89.89% accuracy and an F1-score of 0.8989 with a latent dimension of 1024, outperforming early fusion, late fusion, and recent state-of-the-art methods. The study highlights the importance of controlled cross-modal alignment and provides a scalable approach for robust multimodal sentiment understanding in Arabic multimedia environments.

Cite

APA

Cheikhi, A. B., Nfaoui, E. H., & Elbiach, O. (2026). A Directional Semantic Enhancement Approach with Gated Fusion for Multimodal Arabic Sentiment Analysis. Machine Learning and Knowledge Extraction, 8(5), 139. https://doi.org/10.3390/make8050139

Vancouver

Cheikhi AB, Nfaoui EH, Elbiach O. A Directional Semantic Enhancement Approach with Gated Fusion for Multimodal Arabic Sentiment Analysis. Machine Learning and Knowledge Extraction. 2026;8(5):139. doi:10.3390/make8050139

BibTeX
@article{Cheikhi2026,
  author = {Cheikhi, Ayoub Ben and Nfaoui, El Habib and Elbiach, Oumayma},
  title = {A Directional Semantic Enhancement Approach with Gated Fusion for Multimodal Arabic Sentiment Analysis},
  journal = {Machine Learning and Knowledge Extraction},
  year = {2026},
  volume = {8},
  number = {5},
  pages = {139},
  doi = {10.3390/make8050139}
}
Start for free →