Emotion assessment method and device based on mass sample data

Abstract

The invention provides an emotion assessment method and an emotion assessment device based on mass sample data. The emotion assessment method based on the mass sample data comprises the steps of determining feature information of products in any appointed field in sample information; generating training data according to the feature information and a preset sample information training model; generating assessment information of the products in any appointed field within different time slots according to the training data and a preset increment-based text classification model; using word2vec toperform vectorization treatment on assessment information to generate a vector matrix to be assessed; inputting the vector matrix to be assessed into a convolutional neural network, and thus acquiring an emotion value of the assessment information according to an output result of the convolutional neural network. According to the technical scheme of the method and device provided by the invention, the accuracy and effectiveness of the user for acquiring the emotion value of the assessment information for the products in the specific field are improved, and according to the acquired assessmentanalysis results of the different products, the user can better select the product or make the more reasonable product marketing method.

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