Sentiment Detection on Sudanese Political Tweets Using Deep Learning Approach

Fatima Salih Ibrahim, Eltyeb Elsamani, Shazali Siddig

Sudanese revolution, Arabic tweets, convolution neural networks, machine learning, word embedding.

Sentiment detection of Arabic tweets is interesting research topic and it enables scholars to analyze huge resources of shared opinions in social media websites such as Facebook and tweeter. It is one of the more complex natural language processing tasks due to the informal noisy contents and the rich morphology of Arabic language. Many studies have been investigated for Arabic sentiment analysis. However, most of these works ignore analyzing political Arabic tweets, specifically the Sudanese Arabic dialect. In this paper, a deep learning-based approach is proposed for political Arabic Sentiment Analysis (PASA)of tweets. Our approach employed word embedding with convolutional neural network and long short-term memory network techniques to represent the tweets and extract the feature vectors. After that, the feature vectors are fed to the classifier to detect the sentiments. We conducted a number of experiments using a set of performance evaluation metrics on a political twitter dataset to test the proposed PASA approach. Experimental results showed that the proposed approach outperformed the baseline methods in terms of precision, recall and F-score metrics.

https://doi.org/10.31871/IJNTR.7.2.6