Personalized recommendation method based on OCEAN model

Abstract

The invention discloses a personalized recommendation method based on an OCEAN model, and a personalized recommendation method based on a user OCEAN model is implemented by establishing an OCEAN modelof a microblog user. When the OCEAN model of a user is established, a microblog text of the user is imported into an LDA model, the implied meaning is discovered from the text in an unguided manner,and the accuracy of the prediction is improved. At the same time, the personalized recommendation is built on the basis of user clustering, the search scope of the user is narrowed and the calculationamount of real-time recommendation is reduced. The OCEAN model of the user is combined with the personalized recommendation, an in-depth study is conducted on personality traits of the user, the personalized recommendation process is more in line with the psychology of the user, and the accuracy is higher.

Description

technical field [0001] The invention belongs to the technical field of personality prediction and personalized recommendation, and more specifically, relates to a method for personalized recommendation based on an OCEAN model. Background technique [0002] In psychology, the OCEAN model is used to describe five broad dimensions of human personality. This theory is based on the Big Five personality factor model. The five categories of factors in the OCEAN model include: Conscientiousness, Extraversion, Openness, Agreeableness, and Neuroticism. O stands for Openness to experience, C stands for Conscientiousness, E stands for Extraversion, A stands for Agreeableness, and N stands for Neuroticism. These five factors provide a rich conceptual framework. And previous studies have found that there is a strong correlation between the Big Five personality theory model and people's behavior on social networking sites. [0003] The current personalized recommendation algorithms can ...

AI Technical Summary

Problems solved by technology

[0008] However, the current personalized recommendation methods are basically based on the above four categories, and do not combine the user's personality characteristics for marketing.

Images