Sentiment analysis for airline twitter based of machine learning and deep learning

Abstract

The study of public opinion can be beneficial for obtaining certain knowledge. Thus, the sentiment analysis of the social networks, for example, the Twitter or Facebook has grown into an effective way of understanding users’ opinion and has many uses. Nevertheless, the efficiency and accuracy of sentiment analysis seem to be hampered by the problems rising from natural language processing processes that are inherent with the text. Currently the airline sector is considered the significant field of the market. To sustain that sector and constantly update it, mind mining becomes inevitable. This paper, proposed a model for sentiment analysis based on extracting two different features. Term frequency-inverse document frequency and Word2vec. These feature introduced separately to different classifiers to classify the sentences as positive, negative, or neutral. Twitter US Airline dataset used to evaluate the performance of the proposed model. Bi-directional Long short Term memory outperformed others methods with recall, Precision, and F-Score reached to 0.97, 0.98,and 0.97 respectively when using Word2vec feature.