Deep learning for emotion analysis in Arabic tweets

Abstract

Currently, expressing feelings through social media requires great consideration as an essential part of our lives; besides sharing ideas and thoughts, we share moments and good memories. Social media such as Facebook, Twitter, Weibo, and LinkedIn, are considered rich sources of opinionated text data. Both organizations and individuals are interested in using social media to analyze people's opinions and extract sentiments and emotions. Most studies on social media analysis mainly classified sentiment as positive, negative, or neutral classes. The challenge in emotion analysis arises because humans can express one or several emotions within one expression. Human beings can recognize these different emotions well; however, it is still not easy for an emotion analysis system. In most cases, the Arabic language used through social media is of a slangy or colloquial form, making it more challenging to preprocess and filter noise since most lemmatization and stemming tools are built on Modern Standard Arabic (MSA). An emotion analysis model has been implemented to categorize emotions. The model is a multiclass and multilabel classification problem. However, few studies have been adapted for this emotion classification problem in Arabic social media. Nearly the only work is the one of SemEval 2018 task1- sub-task E-c. Several machine learning approaches have been implemented in this task; a few studies were based on deep learning. Our model implemented a novel multilayer bidirectional long short term memory (BiLSTM) trained on top of pre-trained word embedding vectors. The model achieved state-of-the-art performance enhancement. This approach has been compared with other models developed in the same tasks using Support Vector Machines (SVM), random forest (RF), and fully connected neural networks. The proposed model achieved a performance improvement over the best results obtained for this task.