Resumen de YNU-HPCC at EmoInt-2017: Using a CNN-LSTM Model for Sentiment Intensity Prediction

You Zhang, Hang Yuan, Jin Wang, Xuejie Zhang

• The sentiment analysis in this task aim- s to indicate the sentiment intensity of the four emotions (e.g. anger, fear, joy, and sadness) expressed in tweets. Com- pared to the polarity classification, such intensity prediction can provide more fine- grained sentiment analysis. In this paper, we present a system that uses a convolu- tional neural network with long short-term memory (CNN-LSTM) model to complete the task. The CNN-LSTM model has t- wo combined parts: CNN extracts local n-gram features within tweets and LST- M composes the features to capture long- distance dependency across tweets. Our submission ranked tenth among twenty t- wo teams by average correlation scores on prediction intensity for all four types of e- motions.