New word detection and emotional tendency judgment based on mixed model

The paper studies a new method for Chinese new word detection and emotional tendency judgment based on mixed model and proposes a new word generation framework. First we construct conditional random fields (CRFs) to recognize the new words, lead-in features based on character combined with the crowd sourcing network dictionary. And then express word as a word vector based on neural network language model (NNLM) to judge the new word emotional tendency. The experimental results show that the method can improve the precision and recall of the new word detection with a good system performance, and it also provides a new way for forecasting the public mood.