Hybrid Feature Model for Emotion Recognition in Arabic Text

Abstract

In recent years, research into developing state-of-the-art models for Arabic natural language processing tasks has gained momentum. These models must address the added difficulties related to the nature and structure of the Arabic language. In this paper, we propose three models, a human-engineered feature-based (HEF) model, a deep feature-based (DF) model, and a hybrid of both models (HEF+DF) for emotion recognition in Arabic text. We evaluated the performance of the proposed models on the SemEval-2018, IAEDS, and AETD datasets by comparing the performances of those models on each emotion label. We also compared the model performances with those of other state-of-the-art models. The results show that the HEF+DF model outperformed the DF and HEF models on all datasets. The DF model performed better than the HEF model on the SemEval-2018 and AETD datasets, while the HEF model performed better than the DF model on the IAEDS dataset. The HEF+DF model outperformed the state-of-the-art models in terms of accuracy, weighted-average precision, weighted-average recall, and weighted-average F-score on the AETD dataset and in terms of accuracy, macro-averaged precision, macro-averaged recall, and macroaveraged F-score on the IAEDS dataset. It also achieved the best macro-averaged F-score and the second-best Jaccard accuracy and micro-averaged F-score on the SemEval-2018 dataset. INDEX TERMS Arabic natural language processing, deep learning, emotion recognition, small dataset.

Combining Context-Aware Embeddings and an Attentional Deep Learning Model for Arabic Affect Analysis on Twitter

“…It achieves significant accuracy (53.82%) compared to 1 st place (48.9%) in the SemEval2018-Task1: (Affect in Tweets) competition. Additionally, it outperforms the best recently reported model in the literature [21] with an enhancement of 2.62% in accuracy on the SemEval2018-Ar dataset. We noticed that investigating deep contextualized language models can significantly improve the performance of Arabic affect analysis.…”

“…In addition, on the SemEval2018-Ar dataset, our proposed model outperforms the current state-of-the-art Alswaidan et al, (2020) [21] model, achieving 2.62% improvement in accuracy. To the best of our knowledge, our model outperforms the best recently reported model in the literature.…”

“…A multilabel classification was employed to detect emotions in Arabic tweets [21]. [43] in the SemEval2018-Task1 competition: (Affect in Tweets) [31].…”

“…Deep learning can be defined as a subfield of machine learning that consists of multiple hidden layers that are designed for complex modelling and feature extraction [19], [20]. Deep learning has led to breakthroughs in many NLP applications, such as Arabic sentiment and affect analysis [21]- [29].…”

The Evolution of Language Models Applied to Emotion Analysis of Arabic Tweets

“…In [41], three models were presented for Arabic emotion recognition: deep featurebased model (DF), human engineered feature-based model (HEF), and the combination of them referred to as (HEF + DF) a hybrid model. The performance of the proposed models were evaluated on the SemEval 2018 [19], Iraqi Arabic Emotion Dataset (IAEDS) [42], and Arabic Emotions Twitter Dataset (AETD) [20] datasets.…”