An emotion tendency analysis method based on environmental element embedding and deep learning

Abstract

The invention provides an emotion tendency analysis method based on environmental element embedding and deep learning, which comprises the following steps: S1, collecting text data for training, and obtaining a word segmentation text; S2, training word vectors of the word segmentation text through Word2vec and Gloss, and then obtaining environment element embedding to serve as word vector representation of text semantics in a mode of expanding word vector characteristics of the word segmentation text; S3, automatically learning contexts to extract emotion comment objects by utilizing a neuralnetwork with BLSTM and a dynamic context window fused; S4, based on a local attention mechanism, training word vectors of the text semantics through BLSTM to obtain sentence-level feature vectors; S5, training sentence-level feature vectors through the convolutional neural network to obtain global text-level feature vectors; and S6, classifying the global text-level feature vector by using the multi-classification function Softmax to obtain the emotional tendency of the text data. According to the method, the text data sentiment tendency judgment accuracy is improved.

Description

technical field [0001] The invention relates to the field of computer text sentiment analysis, in particular to an sentiment tendency analysis method based on environmental element embedding and deep learning. Background technique [0002] In the era of mobile Internet, the network has gradually penetrated into all aspects of people's lives and has become an indispensable application element in life. As the freedom of speech becomes more and more free, people are no longer just passive acquirers of information, but more play the role of information producers. Through various online platforms, people will express their views and insights on popular events, share their feelings, or use evaluations and experiences of certain products. This is followed by the generation of a large amount of commentary information with great analytical value presented in the form of text and containing a large amount of emotional information, and how to extract useful emotional information from ...

AI Technical Summary

Problems solved by technology

[0005] However, since the language of short texts of online comments is mostly irregular, the topics are relatively scattered, and there are many new words on the Internet, facing such a huge amount of text data, it will be a problem to analyze and summarize user emotions only through manual browsing. Very tedious and difficult things, sentiment analysis results are not ideal

Especially for Chinese text sentiment analysis research, the research results at this stage can complete some relatively simple tasks, the accuracy rate is relatively low, there is still a lot of room for exploration and research significance, and it is also an interesting and interesting challenge question

Images