Method and system for psychological analysis by fusing multiple-view predictions
View Patent ↗One embodiment of the present invention provides a system for predicting a personality trait. During operation, the system initially obtains personality data associated with users. The system collects sample data associated with the users. Next, the system trains a predictor with the collected sample data and the personality data. Then, the system collects data associated with a particular user, and generates a personality trait score for the particular user by using the predictor to analyze the particular user's collected data.
1. A computer-executable method for predicting a personality trait, the method comprising:
obtaining personality data associated with users;
collecting sample data associated with the users, wherein the sample data includes text data;
training a predictor with the collected sample data and the personality data, wherein training the predictor comprises referencing a sentiment dictionary and counting a number of words in the text data with positive sentiment;
collecting data associated with a particular user; and
generating a personality trait score for the particular user by using the predictor to analyze the particular user's collected data.
2. The method of claim 1 , wherein the text data includes one or more of a character name associated with an online game, a username associated with an online account, a writing sample, or an e-mail address.
3. The method of claim 1 , wherein training the predictor further comprises collecting social data; and training the predictor based on the collected social data.
4. The method of claim 3 , wherein the social data includes a social network graph constructed by analyzing one or more of e-mail communication, chat history, and/or participation in game guilds.
5. The method of claim 1 , wherein training the predictor further comprises collecting behavior data; and training the predictor based on the collected behavior data.
6. The method of claim 5 , wherein the behavior data includes one or more of achievement ratio, activity logs from an online game, behavior data from an online dating service, and/or work pattern data of the user.
7. The method of claim 1 , further comprising combining personality trait scores from multiple predictors to generate an overall personality trait score.
8. The method of claim 1 , wherein training the predictor further comprises collecting text, social, and/or behavior data; and training the predictor based on the collected text, social, and/or behavior data.
9. A computing system for predicting a personality trait, the system comprising:
one or more processors,
a computer-readable medium coupled to the one or more processors having instructions stored thereon that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
obtaining personality data associated with users;
collecting sample data associated with the users, wherein the sample data includes text data;
training a predictor with the collected sample data and the personality data, wherein training the predictor comprises referencing a sentiment dictionary and counting a number of words in the text data with positive sentiment;
collecting data associated with a particular user; and
generating a personality trait score for the particular user by using the predictor to analyze the particular user's collected data.
10. The computing system of claim 9 , wherein the text data includes one or more of a character name associated with an online game, a username associated with an online account, a writing sample, or an e-mail address.
11. The computing system of claim 9 , wherein training the predictor further comprises collecting social data; and training the predictor based on the collected social data.
12. The computing system of claim 11 , wherein the social data includes a social network graph constructed by analyzing one or more of e-mail communication, chat history, and/or participation in game guilds.
13. The method of claim 9 , wherein training the predictor further comprises collecting behavior data; and training the predictor based on the collected behavior data.
14. The computing system of claim 13 , wherein the behavior data includes one or more of achievement ratio, activity logs from an online game, behavior data from an online dating service, and/or work pattern data of the user.
15. The computing system of claim 9 , wherein the computer-readable storage medium stores additional instructions that, when executed, cause the one or more processors to perform additional steps comprising:
combining personality trait scores from multiple predictors to generate an overall personality trait score.
16. The computing system of claim 9 , wherein training the predictor further comprises collecting text, social, and/or behavior data; and training the predictor based on the collected text, social, and/or behavior data.
17. A non-transitory computer-readable storage medium storing instructions that when executed by a computer cause the computer to perform a method for predicting a personality trait, the method comprising:
one or more processors;
a computer-readable medium coupled to the one or more processors having instructions stored thereon that, when executed by the one or more processors, cause the one or more processors to perform operations comprising:
obtaining personality data associated with users;
collecting sample data associated with the users, wherein the sample data includes text data;
training a predictor the collected sample data and the personality data, wherein training the predictor comprises referencing a sentiment dictionary and counting a number of words in the text data with positive sentiment;
collecting data associated with a particular user; and
generating a personality trait score for the particular user by using the predictor to analyze the particular user's collected data.
18. The non-transitory computer-readable storage medium of claim 17 , wherein the text data includes one or more of a character name associated with an online game, a username associated with an online account, a writing sample, or an e-mail address.
19. The non-transitory computer-readable storage medium of claim 17 , wherein training the predictor further comprises collecting social data; and training the predictor based on the collected social data.