Systems and methods for measuring behavior characteristics

• US 20080103721A1
• Filed: 12/20/2006
• Published: 05/01/2008
• Est. Priority Date: 10/30/2006
• Status: Active Grant

• Current Assignee: Institute For Information Industry
• Original Assignee: Institute For Information Industry
• Inventors: Tsai, Tse-Ming, Shih, Chia-Chun
• Granted Patent: US 8,055,663 B2
• Time in Patent Office: Days
• US Class Current: 702/127
• CPC Class Codes: G06Q 10/00 Administration; Management

Abstract

Systems and methods for measuring behavior characteristics. For at least one specific user, a first concern score for respective key terms is calculated according to use frequency of respective key terms of network content corresponding to the specific user and all users. A first relation matrix for at least one specific key term is calculated according to at least two users corresponding to respective interaction behaviors between the key terms and a type weighting corresponding to respective interaction behaviors. A first interaction score for the specific user regarding the specific key term is calculated according to the first relation matrix. A first characteristic score for the specific user regarding the specific key term is calculated according to the first concern score and the first interaction score.

Claims

1. A system for measuring behavior characteristics, comprising:

a database storing network content for a plurality of users, where the network content comprises a plurality of key terms, and a plurality of interaction behaviors therebetween; and

a processing module, for at least one specific user, calculating a first concern score for respective key terms according to use frequency of respective key terms corresponding to the specific user and use frequency of respective key terms corresponding to all users, calculating a first relation matrix for at least one specific key term according to at least two users corresponding to respective interaction behaviors and a type weighting corresponding to respective interaction behaviors, calculating a first interaction score for the specific user regarding the specific key term according to the first relation matrix using an algorithm, and calculating a first characteristic score for the specific user regarding the specific key term according to the first concern score and the first interaction score.

2. The system of claim 1 wherein the network content comprises a plurality of network articles.

3. The system of claim 2 wherein the key terms comprise at least a tag or category of respective network articles.

4. The system of claim 2 wherein the interaction behaviors comprise comments, trackbacks, links, subscriptions, recommendations or blogrolls.

5. The system of claim 1 further comprising:

a domain hierarchy comprising a plurality of concepts and associations therebetween; and

a term-concept association matrix recording association degrees for respective key terms toward respective concepts,

wherein the processing module further calculates a second concern score for the specific user regarding respective concept according to the first concern score for the specific user regarding respective key terms and the term-concept association matrix, calculating a second relation matrix for at least one specific concept according to the first relation matrix and the association degree for at least one key term used in the interaction behaviors toward the specific concept, calculating a second interaction score for the specific user regarding the specific concept according to the second relation matrix using the algorithm, and calculating a second characteristic score for the specific user regarding the specific concept according to the second concern score and the second interaction score.

6. The system of claim 5 wherein the processing module calculates the second concern score according to the formula:

$G_U=\frac{\frac{f_U}{<br><br>f_U<br><br>}}{\frac{F_{\mathrm{ALL}}}{<br><br>F_{\mathrm{ALL}}<br><br>}}\times <br><br>M,$

wherein G_U={G₁, G₂, . . . , G_m}, G_j represents the second concern score for the specific user regarding the jth concept, f_U={f₁, f₂, . . . , f_m}, f_i represents the use frequency of the ith key term corresponding to the specific user, F_ALL={F₁, F₂, . . . , F_m}, F_i represents the use frequency of the ith key term corresponding to all users, and M represents the term-concept association matrix.

7. The system of claim 5 wherein the processing module calculates the second relation matrix according to the formula:

$R_{\mathrm{ij}}=\stackrel{\mathrm{UA}=i<br><br><br><br>\mathrm{UB}=j}{\sum <br><br>S\times <br><br>\mathrm{AD},}$

wherein R_ij represents interaction relation strength for the ith user toward the jth user under the specific concept, respective interaction behavior is represented by (UA, UB, S, AD), where UA and UB represents two users corresponding to one interaction behavior, S represents the type weighting corresponding to the interaction behavior, and AD represents the association degree for the key term used in the interaction behavior toward the specific concept.

8. The system of claim 5 wherein the algorithm comprises a HITS algorithm.

9. The system of claim 8 wherein the processing module calculates the second characteristic score according to the formula:

B_U=G_U+k×

IA_U,

wherein B_U represents the second characteristic score, G_U represents the second concern score, IA_U represents the second interaction score, and k is a participation weighting for the interaction behaviors.

10. The system of claim 9 wherein the second interaction score comprises a hub score or an authority score.

11. A method for measuring behavior characteristics, comprising:

providing network content for a plurality of users, where the network content comprises a plurality of key terms, and a plurality of interaction behaviors therebetween;

for at least one specific user, calculating a first concern score for respective key terms according to use frequency of respective key terms corresponding to the specific user and use frequency of respective key terms corresponding to all users;

calculating a first relation matrix for at least one specific key term according to at least two users corresponding to respective interaction behaviors and a type weighting corresponding to respective interaction behaviors;

calculating a first interaction score for the specific user regarding the specific key term according to the first relation matrix using an algorithm; and

calculating a first characteristic score for the specific user regarding the specific key term according to the first concern score and the first interaction score.

12. The method of claim 11 wherein the network content comprises a plurality of network articles.

13. The method of claim 12 wherein the key terms comprise at least a tag or category of respective network articles.

14. The method of claim 12 wherein the interaction behaviors comprise comments, trackbacks, links, subscriptions, recommendations or blogrolls.

15. The method of claim 11 further comprising:

providing a domain hierarchy comprising a plurality of concepts and associations therebetween; and

providing a term-concept association matrix recording association degrees for respective key terms toward respective concepts,

calculating a second concern score for the specific user regarding respective concept according to the first concern score for the specific user regarding respective key terms and the term-concept association matrix;

calculating a second relation matrix for at least one specific concept according to the first relation matrix and the association degree for at least one key term used in the interaction behaviors toward the specific concept;

calculating a second interaction score for the specific user regarding the specific concept according to the second relation matrix using the algorithm; and

calculating a second characteristic score for the specific user regarding the specific concept according to the second concern score and the second interaction score.

16. The method of claim 15 further comprising calculating the second concern score according to the formula:

$G_U=\frac{\frac{f_U}{<br><br>f_U<br><br>}}{\frac{F_{\mathrm{ALL}}}{<br><br>F_{\mathrm{ALL}}<br><br>}}\times <br><br>M,$

wherein G_U={G₁, G₂, . . . , G_m}, G_j represents the second concern score for the specific user regarding the jth concept, f_U={f₁, f₂, . . . , f_m}, f_i represents the use frequency of the ith key term corresponding to the specific user, F_ALL={F₁, F₂, . . . , F_m}, F_i represents the use frequency of the ith key term corresponding to all users, and M represents the term-concept association matrix.

17. The method of claim 15 further comprising calculating the second relation matrix according to the formula:

$R_{\mathrm{ij}}=\stackrel{\mathrm{UA}=i<br><br><br><br>\mathrm{UB}=j}{\sum <br><br>S\times <br><br>\mathrm{AD},}$

wherein R_ij represents interaction relation strength for the ith user toward the jth user under the specific concept, respective interaction behavior is represented by (UA, UB, S, AD), where UA and UB represents two users corresponding to one interaction behavior, S represents the type weighting corresponding to the interaction behavior, and AD represents the association degree for the key term used in the interaction behavior toward the specific concept.

18. The method of claim 15 wherein the algorithm comprises a HITS algorithm.

19. The method of claim 18 further comprising calculating the second characteristic score according to the formula:

B_U=G_U+k×

IA_U,

wherein B_U represents the second characteristic score, G_U represents the second concern score, IA_U represents the second interaction score, and k is a participation weighting for the interaction behaviors.

20. The method of claim 19 wherein the second interaction score comprises a hub score or an authority score.

21. A machine-readable storage medium comprising a computer program, which, when executed, causes a device to perform a method for measuring behavior characteristics, the method comprising:

providing network content for a plurality of users, where the network content comprises a plurality of key terms, and a plurality of interaction behaviors therebetween;

for at least one specific user, calculating a first concern score for respective key terms according to use frequency of respective key terms corresponding to the specific user and use frequency of respective key terms corresponding to all users;

calculating a first relation matrix for at least one specific key term according to at least two users corresponding to respective interaction behaviors and a type weighting corresponding to respective interaction behaviors;

calculating a first interaction score for the specific user regarding the specific key term according to the first relation matrix using an algorithm; and

calculating a first characteristic score for the specific user regarding the specific key term according to the first concern score and the first interaction score