Short Text Emotion Analysis Based on Recurrent Neural Network

In recent years, as a social media, WeChat develops rapidly and popularly. At the same time, with the increase in the number of WeChat users, the number of WeChat Official Accounts is also rising. Faced with a large number of emerging WeChat Official Accounts, how to grasp the user's preferences for the development of the Official Accounts is essential. In this paper, we will use the improved structure of RNN --- --- LSTM to make a short text effective analysis of user comments based on various articles in the Official Accounts, analysis the user's emotional tendencies, so that WeChat Official Accounts can recommend users to different articles and functionality according to the emotional trend of different users.

[1]  Jürgen Schmidhuber,et al.  Long Short-Term Memory , 1997, Neural Computation.

[2]  Jeffrey Dean,et al.  Distributed Representations of Words and Phrases and their Compositionality , 2013, NIPS.

[3]  Yoshua Bengio,et al.  Learning long-term dependencies with gradient descent is difficult , 1994, IEEE Trans. Neural Networks.

[4]  Jürgen Schmidhuber,et al.  Learning to forget: continual prediction with LSTM , 1999 .

[5]  Geoffrey E. Hinton,et al.  Speech recognition with deep recurrent neural networks , 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[6]  Alex Graves,et al.  Supervised Sequence Labelling with Recurrent Neural Networks , 2012, Studies in Computational Intelligence.

[7]  G. Miller.  Learning to Forget , 2004, Science.