Emotional evaluation method and device based on a large number of sample data

Abstract

The present invention provides an emotional evaluation method and device based on a large amount of sample data, wherein the emotional evaluation method based on a large amount of sample data includes: determining the characteristic information of products in any specified field in the sample information; Train the model to generate training data; generate evaluation information of products in any specified field within different time periods according to the training data and the preset increment-based text classification model; use word2vec to vectorize the evaluation information to generate evaluation information The vector matrix of ; input the vector matrix to be evaluated into the convolutional neural network, so as to obtain the emotional value of the evaluation information according to the output result of the convolutional neural network. Through the technical solution of the present invention, the accuracy and effectiveness of the user in obtaining the emotional value of product evaluation information in a specific field are improved, and according to the obtained evaluation and analysis results of different products, the user can better select products or formulate more reasonable product marketing means.

Description

technical field [0001] The present invention relates to the field of emotion evaluation, in particular to an emotion evaluation method based on a large amount of sample data and an emotion evaluation device based on a large amount of sample data. Background technique [0002] With the rapid development of social networks, more and more people use social network platforms to publish a large amount of information, whether it is national events or personal daily life information, they will be transmitted through this platform. According to the "Statistical Report on Internet Development in China" in June 2015, the number of Internet users reached 668 million. Among them, the most typical one is Sina Weibo, which has more than 200 million monthly active users and involves all aspects of life, including product evaluation information in different fields. Therefore, a large amount of microblog data provides data support for us to study product evaluation methods based on microblo...

AI Technical Summary

Problems solved by technology

[0003] Sentiment analysis is a hot topic in natural language processing. At present, people usually focus on sentiment classification in specific fields. In related technologies, product evaluation information in different fields has different emotional characteristics. On the one hand, only by extracting Emotional words in product evaluation information cannot effectively determine their emotional categories. On the other hand, due to the short and concise features of Weibo, it is also difficult to effectively extract product information features.

Images