Abstract
In recent years, with the continuous recognition of the value of data, text sentiment analysis in natural language processing has gradually become a research hotspot in the field of artificial intelligence. In this article, we propose a multi-channel parallel algorithm. First, train the entire network by constructing a word embedding layer, map the vocabulary to a higher-dimensional space through word2vec. Then the generated embedding matrix is integrated with the parallel classifier model based on TextCNN, LSTM and Transformer. We use web crawler technology to extract sentiment classification data set from various industries and multiple fields, and conduct comparative experiments on this data set. Experimental results show that the effect of this model is better than that of a single-kernel classifier model.
Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
