Enhancing Arabic aspect-based sentiment analysis using deep learning models

•Aspect-Based Sentiment Analysis is a special type of sentiment analysis whose aim is to uncover the aspects discussed in the review and identify sentiment.•In this paper, the authors propose deep learning models to address two core Aspect-Based Sentiment Analysis tasks; aspect-category identification and aspect-sentiment classification.•In relation to the aspect-category identification task, the paper proposes an identification model using Convolutional Neural Network and stacked Independent Long-Short Term Memory.•For the second task, the paper proposes classification model that uses stacked Bidirectional Independent Long-Short Term Memory, position-weighting mechanism, and multiple attention mechanism layers.•For evaluation purposes, the Arabic SemEval-2016 annotated dataset for the hotels' domain was utilized. Experimental results show that the proposed models outperform the baseline and the prior works; where the first model, achieved an F1 measure of 58.08% and the second model, achieved an accuracy measure of 87.31% . Aspect-based sentiment analysis is a special type of sentiment analysis that aims to identify the discussed aspects and their sentiment polarities in a given review. In this paper, two deep learning models are proposed to address essential aspect-based sentiment analysis tasks: aspect-category identification and aspect-sentiment classification. For the first task, an identification model is proposed based on a convolutional neural network and stacked independent long-short term memory. For the second task, a classification model is proposed based on stacked bidirectional independent long-short term memory, a position-weighting mechanism, and multiple attention mechanism layers. The proposed models are evaluated using the Arabic SemEval-2016 dataset for the Hotels domain. Experimental results demonstrate that the proposed models outperform the baseline and other models, where the first model, C-IndyLSTM, achieves an F1 measure of 58.08%, and the second model, MBRA, achieves an accuracy measure of 87.31%.