Emojis-Based Sentiment Classification of Arabic Microblogs Using Deep Recurrent Neural Networks

Machine-learning based sentiment classification has gained increasing popularity for analyzing online content in social media. A new generation of artificial neural networks is deep learning, which has been successfully applied in several domains. In this study, we empirically evaluate two state-of-the-art models of deep recurrent neural networks to detect sentiment polarity of Arabic microblogs. We considered both unidirectional and bidirectional Long Short-Term Memory (LSTM) and its simplified variant Gated Recurrent Unit (GRU). Moreover, due to the complexities and challenges facing the Arabic language to model short dialectical text, which is commonly used in microblogs, we aim to assess non-verbal features extracted from a dataset of 2091 microblogs. We also compared the performance to baseline traditional learning methods and deep neural networks. The experimental results reveal that LSTM and GRU based models significantly outperform other classifiers with a slight difference between them with best results attained when using bidirectional GRU.