EUVIMEDEUVIMED entdecken
Open Access · CC BY-NC-ND 4.0

Routed Expert-Based Emotion Detector for Multi-Label Emotion Classification

Abu Zahid Md Jalal Uddin, Md. Mithun Hossain, A. S. M. Ahsanul Sarkar Akib, M. F. Mridha, Md. Jakir Hossen

IEEE Open Journal of the Computer Society · 2026 · 7 · 876-888

DOI: 10.1109/ojcs.2026.3688524 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Open Journal of the Computer Society, 2026. Verfasst von Abu Zahid Md Jalal Uddin und 4 weiteren Autor:innen. Die Arbeit nennt 33 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY-NC-ND 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Multi-label emotion detection aims to identify multiple emotions that may co-occur in short, informal texts, such as tweets. Real-world data present challenges due to overlapping emotional cues, complex inter-label dependencies, and severe imbalance between frequent and rare emotions. Existing transformer-based approaches typically rely on fixed thresholds and a single inductive bias, such as conditional prediction, graph reasoning, or flat classification, which often lead to overfitting on majority labels and poorly calibrated probability estimates. To address these limitations, we propose RoutED (Routed Expert-based Emotion Detector), a routed mixture-of-experts framework that adaptively selects the most appropriate reasoning strategy for each input instance. RoutED integrates three complementary experts: a label-graph expert that models emotion co-occurrence using a PPMI-based graph, a classifier-chain expert that captures directional dependencies among labels, and a lightweight MLP expert for order-free scoring. A compact router assigns instance-specific mixture weights through a temperature-scaled softmax with entropy-based load balancing to prevent expert collapse. Training combines binary cross-entropy and focal loss to mitigate class imbalance, incorporates Laplacian graph regularization to enforce correlation consistency, and applies per-label threshold tuning for calibrated inference. Experiments on SemEval-2018 Task 1 (EC, English) and REN-CE-cps (Chinese) demonstrate consistent macro-F1 improvements over strong baselines, particularly for rare emotions, while providing interpretable attention patterns and expert-usage analyzes that reveal the model's adaptive reasoning behavior.

Zitieren

APA

Uddin, A. Z. M. J., Hossain, M. M., Akib, A. S. M. A. S., Mridha, M. F., & Hossen, M. J. (2026). Routed Expert-Based Emotion Detector for Multi-Label Emotion Classification. IEEE Open Journal of the Computer Society, 7, 876-888. https://doi.org/10.1109/ojcs.2026.3688524

Vancouver

Uddin AZMJ, Hossain MM, Akib ASMAS, Mridha MF, Hossen MJ. Routed Expert-Based Emotion Detector for Multi-Label Emotion Classification. IEEE Open Journal of the Computer Society. 2026;7:876-888. doi:10.1109/ojcs.2026.3688524

BibTeX
@article{Uddin2026,
  author = {Uddin, Abu Zahid Md Jalal and Hossain, Md. Mithun and Akib, A. S. M. Ahsanul Sarkar and Mridha, M. F. and Hossen, Md. Jakir},
  title = {Routed Expert-Based Emotion Detector for Multi-Label Emotion Classification},
  journal = {IEEE Open Journal of the Computer Society},
  year = {2026},
  volume = {7},
  pages = {876--888},
  doi = {10.1109/ojcs.2026.3688524}
}
Kostenlos starten →