Sentiment Analysis for Mongolian Tweets with RNN

As information flow in the electronic online environment is increasing, the need for automated processing is increasing. Every minute, 456,000 tweets were written on Twitter. The data in the Mongolian language is already joined in that stream and created their own space since a long time ago. However, in the Mongolian language, there is a lack of research, language resources, and an implemented system by now. In this work, we tried to classify the document level sentiment polarity of Mongolian tweets based on the RNN method of deep learning. The model was tested at the 62,917 SemEval English data, the highest F1 score of 64.7.