A method of personalized recommendation based on ocean model

Abstract

The invention discloses a method for personalized recommendation based on an OCEAN model. By establishing the OCEAN model of microblog users, the method for personalized recommendation based on the user OCEAN model is realized. When building the user's OCEAN model, the user's microblog text is imported into the LDA model, and the implicit meaning is found from the text in an unguided way to improve the accuracy of prediction. At the same time, the personalized recommendation is based on user clustering, which narrows the user's search range and reduces the calculation amount of real-time recommendation. Combining the user's OCEAN model with personalized recommendation, and in-depth research on the user's personality characteristics, the personalized recommendation process is more in line with the user's psychology and has higher accuracy.

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, and 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 neurotic personality traits. 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 architecture. And previous studies have found that there is a strong correlation between the Big Five personality model and people's behavior on social networking sites. [0003] The current personalized recommendation...

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