Improving Arabic Multi-Label Emotion Classification Using Stacked Embeddings and Hybrid Loss Function
Open Access
- 17 June 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 188939-188954
Abstract
Multi-label emotion classification (MLEC) for low-resource languages like Arabic faces significant challenges due to class imbalance and label correlations, particularly in accurately predicting minority emotions. This study propose a novel framework combining stacked contextual embeddings, meta-learning, and a hybrid loss function to address these issues. First, we generate enriched embeddings by fine-tuning and stacking three Arabic language models (ArabicBERT, MarBERT, AraBERT). These embeddings are processed by a Bi-LSTM meta-learner for sequence learning, followed by a fully connected network for classification. To mitigate class imbalance and leverage label dependencies, we introduce a hybrid loss integrating contrastive learning (CL), label correlation matrices (LCM), and class weighting (CW). Extensive experiments on the SemEval-2018 Task 1-Ec-Ar dataset demonstrate state-of-the-art performance, with a Jaccard accuracy of 0.81, F1-score of 0.67, and Hamming loss of 0.15. Ablation studies confirm the contributions of each component, while class-wise analysis shows our hybrid loss reduces disparities between majority and minority classes by up to 22%. Beyond Arabic MLEC, this work offers a generalizable framework adaptable to other languages and domains, advancing emotion analysis in low-resource settings.Keywords
All Related Versions
Funding Information
- Chinese Academy of Sciences President’s International Fellowship Initiative (2024PVB0036)
- Changchun Institute of Optics, Fine Mechanics, and Physics, Chinese Academy of Sciences, Changchun, China
- School of Information Engineering, Xi’an Eurasia University, Xi’an, Shaanxi, China
This publication has 64 references indexed in Scilit:
- Improved Arabic image captioning model using feature concatenation with pre-trained word embeddingNeural Computing and Applications, 2023
- Impact of word embedding models on text analytics in deep learning environment: a reviewArtificial Intelligence Review, 2023
- Improving the Polarity of Text through word2vec Embedding for Primary Classical Arabic Sentiment AnalysisNeural Processing Letters, 2023
- Employing Contrastive Strategies for Multi-label Textual Emotion Recognition2022
- A survey on sentiment analysis methods, applications, and challengesArtificial Intelligence Review, 2022
- Text‐based emotion detection: Advances, challenges, and opportunitiesEngineering Reports, 2020
- Exploring the Use of Word Embedding and Deep Learning in Arabic Sentiment AnalysisAdvances in Intelligent Systems and Computing, 2020
- A New Arabic Dataset for Emotion Recognition2019
- Combining Lexical Features and a Supervised Learning Approach for Arabic Sentiment Analysis2018
- Three Paradigms of Computer ScienceMinds and Machines, 2007