GTHL-Emo: Adaptive Imbalance-Aware and Correlation-Aligned Training for Arabic Multi-Label Emotion Detection
Electronics · 11.03.2026 · 15 (6) · 1169
DOI: 10.3390/electronics15061169 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 11.03.2026. Verfasst von Mashary N. Alrasheedy und 2 weiteren Autor:innen. Die Arbeit wurde bisher 2-mal zitiert (Crossref) und nennt 56 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Multi-label emotion detection (MLED) suffers from long-tailed label distributions and structured inter-label correlations, which jointly suppress rare label recall and yield incoherent predictions. We present Graph Neural Network-Enhanced Transformer with Hybrid Loss Weighting (GTHL-Emo), a unified framework that addresses both challenges without heavy additional machinery. First, an adaptive imbalance-aware training scheme combines binary cross-entropy, asymmetric focal, and pairwise ranking losses under a learned batch-wise controller, emphasizing rare labels while stabilizing thresholding. Second, a lightweight correlation alignment module learns transformer-based label embeddings and aligns their predicted affinities with empirical co-occurrence via Kullback–Leibler (KL) regularization, smoothing rare label predictions through correlated frequent labels. A transformer encoder with learnable attention pooling provides semantic representations, and a dynamic GraphSAGE layer captures inter-instance structural dependencies. Comprehensive evaluation across three Arabic benchmarks—SemEval-2018-Ec-Ar, ExaAEC, and SemEval-2025 (Track A, Arq)—demonstrates competitive or leading performance. On SemEval-2018-Ec-Ar, GTHL-Emo attained a Jaccard accuracy of 58.70%, micro-F1 score of 71.02%, and macro-F1 score of 60.48%. On ExaAEC, it achieved a Jaccard accuracy of 65.99%, micro-F1 score of 70.72%, and macro-F1 score of 68.71%. On SemEval-2025-Arq, it obtained a Jaccard accuracy of 41.47%, micro-F1 score of 56.78%, and macro-F1 score of 56.69%. Ablation studies revealed that the GraphSAGE structure and ranking loss contributed most significantly (1.45% and 1.46% Jaccard accuracy drops, respectively), while label correlation alignment provided consistent improvements across the scales. These findings demonstrate that jointly optimizing imbalance-aware objectives and label dependencies yields robust Arabic MLED with minimal overhead.
Zitieren
APA
Alrasheedy, M. N., Tiun, S., & Fauzi, F. (2026). GTHL-Emo: Adaptive Imbalance-Aware and Correlation-Aligned Training for Arabic Multi-Label Emotion Detection. Electronics, 15(6), 1169. https://doi.org/10.3390/electronics15061169
Vancouver
Alrasheedy MN, Tiun S, Fauzi F. GTHL-Emo: Adaptive Imbalance-Aware and Correlation-Aligned Training for Arabic Multi-Label Emotion Detection. Electronics. 2026;15(6):1169. doi:10.3390/electronics15061169
BibTeX
@article{Alrasheedy2026,
author = {Alrasheedy, Mashary N. and Tiun, Sabrina and Fauzi, Fariza},
title = {GTHL-Emo: Adaptive Imbalance-Aware and Correlation-Aligned Training for Arabic Multi-Label Emotion Detection},
journal = {Electronics},
year = {2026},
volume = {15},
number = {6},
pages = {1169},
doi = {10.3390/electronics15061169}
}
EUVIMED