Personality prediction method based on microblog user behaviors

Abstract

The invention provides a personality prediction method based on microblog user behaviors. The method comprises the steps that first, an id list of microblog active users is acquired, personality questionnaires filled on line by tested users are acquired according to the id list of the active users through a 'talk to him' function of the microblog; second, according to the list of the tested users who fill the personality questionnaires, microblog data of the users are downloaded, and according to an established microblog network behavior system, corresponding static behavior features and dynamic behavior features are extracted from the microblog data; third, numeralization is conducted on the extracted dynamic behavior features of the users according to a time sequence analysis method to achieve a complete microblog feature set; fourth, according to a stepwise regression algorithm, a biggest obvious feature set is extracted from the microblog feature set to achieve feature selection; a personality prediction regression model is established for the selected features, and personality psychology indexes of the users are predicted.

Description

technical field [0001] The present invention relates to personality prediction technology, more specifically, to a personality prediction method based on microblog user behavior. Background technique [0002] Personality is a stable psychological variable that can predict a variety of valuable outcome variables, such as: individual variables (job performance, mental health), interpersonal variables (intimate relationships), and social variables (criminal behavior, social ideology). Therefore, personality is an important topic in psychological research. [0003] At present, the main means of traditional personality prediction are divided into: self-report personality questionnaire and projection technology. The prototype of the self-report personality questionnaire is the Woodworth Personal Data Sheet (Woodworth Personal Data Sheet). By purposefully summarizing and collecting the daily behaviors of users, and then selecting and grouping the collected behaviors, it forms a fo...

AI Technical Summary

Problems solved by technology

[0005] However, these two methods have their own shortcomings in practical application: the self-report personality questionnaire is a self-measurement form. The defensive psychology of the subjects has an impact on the results of the self-test

Scholars use the knowledge of data mining to study the association between users' complex network data and user personality, trying to find different network behaviors displayed by different personalities, so as to use network behaviors to predict users' personality and overcome the traditional Psychological questionnaires rely on users' subjective consciousness, which has the disadvantages of long user experiment cycle and high cost

However, this kind of research has spread widely. Although some network behaviors related to personality have been obtained, due to the complexity and effectiveness of the mutual understanding network, it is technically difficult to establish a universal network behavior personality prediction model, and it will take a long time. accumulation

Images