User real-time viewpoint detection method based on social media content and structure

Abstract

The invention discloses a user real-time viewpoint detection method based on social media content and structure. The method mainly comprises the following steps: crawling microblogs related to an event and social network information of a microblog author in real time based on a microblog API and a Hash label; based on the microblog text and the social network information of the user, generating training data by using a Hash label and a remote supervision technology; and based on the dynamic neural network model training, completing the dynamic viewpoint detection of the user level. According to the method, a lot of tagged corpora are not needed, the standpoint of a user about a certain topic in the next time period can be predicted, and higher accuracy is achieved due to simulation of theuser behavior by the recurrent neural network; the user viewpoints can be predicted by utilizing the social network information under the condition that the user corpora is lost; new microblog data can be obtained, iteration can be dynamically carried out on the trained dynamic neural network, and the problem that time is wasted when training is carried out from the beginning is solved.

Description

technical field [0001] The invention relates to a user's real-time point of view detection method based on social media content and structure, and belongs to the technical field of information processing. Background technique [0002] Social media real-time opinion prediction (Dynamic Opinion Prediction), also known as user-level dynamic position prediction, refers to marking a correct opinion for each user in Weibo. The user's opinion consists of two parts. The first part is user discussion or The second part of the topic of concern is the user's position. Correct, timely and efficient prediction of user opinions not only helps to grasp social public opinion and government decision-making, which has far-reaching social value, but also helps enterprises to formulate appropriate market strategies, which has important market research value. At present, social media has provided the public with unprecedented new means of expression of public opinion and a new space for free di...

AI Technical Summary

Problems solved by technology

[0004] Purpose of the invention: In order to fill the gap in research on user opinion prediction by integrating social network structure and content, the present invention provides a real-time user opinion detection method based on social media content and structure, which can solve the real-time problem of user opinion prediction unique to social networks ; It can integrate the information of the two modalities of user relationship and user microblog text, aiming to improve the accuracy of user opinion detection

Images