Word and Character Information Aware Neural Model for Emotional Analysis

Background: Social media texts are often highly unstructured in accordance with the presence of hashtags, emojis and URLs occurring in abundance. Thus, a sentiment or emotion analysis on these kinds of texts becomes very difficult. The difficulty increases even more when such texts are in local languages like Arabic. Methods: This work utilizes novel deep learning architectures in the form of character-level Convolutional Neural Network (CNN) module and the word-level Recurrent Neural Network (RNN) module to produce a hybrid architecture that makes use of the character level analysis and the word level analysis to obtain state-of-the-art results on a totally new Arabic Emotions dataset. Results: The proposed method works the best among the traditional bag-of-words and Term Frequency and Inverse Document Frequency methods for emotion analysis. It also outperforms the state-of-the-art deep learning methods which are known to perform very well in an English corpus. Conclusion: The proposed deep end-to-end architecture utilizes the character level information from a text through the Character CNN Module and the word level information from a text through the Word-Level RNN Module.