Processing system and method for extracting fine-grained typical opinion data of user

Abstract

The invention belongs to the technical field of data processing, and discloses a processing system and method for extracting fine-grained typical opinion data of a user, which are used for cleaning the data and filtering out noise data. Performing character segmentation and word segmentation on the cleaned data; a word embedding model is used for training word vectors, word vector representation is carried out, and a corresponding file is generated; defining common attributes of the product; extracting attributes related to the product in the user comments; converting all the extracted attribute texts into vector representation by adopting a word vector weighted averaging method; clustering the texts; and obtaining user typical opinions of different attributes of the product. According tothe method, the attribute texts related to the product in the user comments are extracted, the texts with the same attribute and the same emotional tendency are clustered into the same cluster as muchas possible, and the user typical opinions with different attributes are obtained. The accuracy of the clustering result is effectively improved, the granularity of the clustering result is smaller,and the typical opinions of the user for different attributes of the product are quickly obtained.

Description

technical field [0001] The invention belongs to the technical field of data processing, and in particular relates to a data processing system and method for extracting user fine-grained typical opinion data. Background technique [0002] At present, the closest existing technology: With the continuous development of Internet technology, online shopping has changed our way of life and provided great convenience for our life. Usually when we buy a certain product on a certain e-commerce platform, we will publish our shopping experience and usage experience to express our views on the product. And these points of view are very important for merchants and users who want to buy the product. By analyzing a large number of user reviews, merchants can understand users' opinions on the product, and improve the points that users are not satisfied with, so as to help optimize the product. Users who want to buy the product can refer to the experience of users who have already purchase...

AI Technical Summary

Problems solved by technology

Because there will be descriptions that are not related to the product in the text reviews, the result of clustering is not ideal; in addition, by directly clustering the reviews, the user's overall view of the product can be obtained, but the user's different views on the product cannot be obtained. attribute point of view

[0004] To sum up, the problems existing in the existing technology are: the existing technology directly clusters the text data, resulting in unsatisfactory clustering results; in addition, by directly clustering the comments, the user's overall information about the product can be obtained. Opinions, but cannot get users' opinions on different attributes of the product

At present, the extraction of fine-grained typical user opinions is usually achieved by multi-label classification, but this method can only obtain the overall opinions of users on different attributes of the product, and cannot obtain specific descriptions of user opinions. Through the above technical problems. Solving, It can not only get the user's general opinion on different attributes of the product, but also get the specific description of the opinion

Images