Dynamic user attribute extraction method based on social media

Abstract

The invention discloses a dynamic user attribute extraction method based on social media. The dynamic user attribute extraction method includes the steps: firstly, performing text preprocessing for an acquired training sample set and extracting subject terms to obtain K subjects and m subject terms of each subject; secondly, extracting short texts of a user to be processed, dividing time sub-segments, filling data through a time sliding window to obtain text data of the time sub-segments, counting the occurrence frequency of the subject terms after text preprocessing to obtain attribute weight information of the subjects, introducing time attenuation coefficient, sequentially acquiring user attribute features associated with time attributes in time sequence, extracting the user attribute features of the latest time sub-segment as current user attribute features and outputting the current user attribute features. Without external knowledge, the short texts of the social media are semantically expanded by disordered words in the texts, and dynamic user attributes can be extracted from micro-blog texts released or forwarded by users.

Description

technical field [0001] The invention belongs to the field of computers, and in particular relates to a method for extracting dynamic user attributes based on social media. Background technique [0002] Social media services define a whole new way for users to communicate with each other, express themselves and share on the web. With the continuous development of social media, more and more people publish and share instant messages on social media platforms, common social media such as Sina Weibo, Twitter, Facebook and LinkedIn. For example: on the Sina Weibo platform, users can publish microblog information within 140 characters, and these microblogs can be composed of Chinese and English, custom characters, external links, etc. Therefore, effectively analyzing microblog short text streams to detect users' dynamic attributes is of great significance to the research and application of related fields, such as social recommendation, personalized retrieval, online promotion, et...

AI Technical Summary

Problems solved by technology

[0006] The purpose of the invention of the present invention is: in order to solve the sparsity problem of short text, overcome the disadvantages such as inaccurate user attribute mining of the prior art and can not update in time, the present invention is based on the new dynamic user attribute model constructed (can be automatically obtained from text Mining the user’s dynamic attributes and showing the changes of user attributes), without the need to use external knowledge, realize the semantic expansion of short texts in social media through disordered words in the text, and smooth the data through time windows, Introduce a decay function to represent the influence of past attributes on current attributes

Images