Action Based Trust Modeling

• US 20160150037A1
• Filed: 11/26/2014
• Published: 05/26/2016
• Est. Priority Date: 11/26/2014
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Hu, Mengdie, MAHMUD, JALAL U., Pal, Aditya, Yang, Huahai, Zhou, Michelle X.
• Granted Patent: US 10,051,069 B2
• Time in Patent Office: Days
• CPC Class Codes: G06F 21/554 involving event detection and direct action
• CPC Class Codes: G06F 21/57 Certifying or maintaining trusted computer platforms, e.g. secure boots or power-downs, version controls, system software checks, secure updates or assessing vulnerabilities
• CPC Class Codes: G06F 2221/2145 Inheriting rights or properties, e.g., propagation of permissions or restrictions within a hierarchy
• CPC Class Codes: H04L 51/52 for supporting social networking services
• CPC Class Codes: H04L 67/306 User profiles
• CPC Class Codes: H04L 67/535 Tracking the activity of the user network monitoring arrangements H04L43/00; recording of computer activity G06F11/34

Abstract

Embodiments of the invention relate to assessing characteristics of a message and a message recipient. A trust model is established to take into account a set of trust antecedents, including characteristics of the messages and properties of the recipients, a set of action motivations, and their contribution to the action-based trust measurement. The assessment(s) is utilized to produce a tangible trust measurement that is employed to gauge the recipient'"'"'s perception of credibility towards the received message.

Claims

1. A method comprising:

computing a trust antecedent from a message;

computing a recipient antecedent from recipient social media information;

combining the computed trust antecedent and computed recipient antecedent, and predicting a perception of credibility towards the message with the combined antecedents;

computing one or more motivators from one or more message recipients;

returning an action propensity prediction measurement from the motivator computation as a trust measurement for the message, the prediction measurement including a combination of the predicted perception of credibility and the motivator computation; and

identifying a message recipient from the returned prediction measurement, and sending the message to the identified recipient.

2. The method of claim 1, wherein the action propensity is a sum of available actions advocated by the message weighted by an importance of the actions.

3. The method of claim 1, wherein the computation of the trust antecedent includes computing a characteristic of the message selected from the group consisting of:

source of the message, a form of the message, an authority of the message, and combinations thereof.

4. The method of claim 1, wherein the computation of the recipient antecedent includes computing a characteristic selected from the group consisting of:

prior knowledge on a subject of the message, influences from an associated social circle, and combinations thereof.

5. The method of claim 1, wherein the computation of the one or more motivators includes computing a factor selected from the group consisting of:

one or more past behavior records related to the message, thinking style regarding cost and benefit of one or more actions extracted from available recipient information, and combinations thereof.

6. The method of claim 1, further comprising factoring a personality trait of the recipient.

7. A computer program product for predicting action propensity, the computer program product comprising a computer readable storage device having program code embodied therewith, the program code executable by a processing unit to:

compute a trust antecedent from a message;

compute a recipient antecedent from recipient social media information;

combine the computed trust antecedent and computed recipient antecedent, and predict credibility perception towards the message with the combined antecedents;

compute at least one motivator from one or more message recipients;

return an action propensity prediction measurement as a trust measurement for the message from the motivator computation, the prediction measurement including a combination of the predicted perception of credibility and the motivator computation; and

a message recipient identified from the returned prediction measurement for receipt of the message.

8. The computer program product of claim 7, wherein the action propensity is a sum of available actions advocated by the message weighted by an importance of the actions.

9. The computer program product of claim 7, further comprising code to compute the trust antecedent, including assigning a numerical value to each trust antecedent.

10. The computer program product of claim 7, wherein the computation of the recipient antecedent includes data from available recipient information, including a characteristic selected from the group consisting of:

prior knowledge on a subject of the message, influences from an associated social circle, and combinations thereof.

11. The computer program product of claim 7, wherein the computation of the one or more motivators includes computing a factor selected from the group consisting of:

one or more past behavior records related to the message, thinking style regarding cost and benefit of one or more actions extracted from available recipient information, and combinations thereof.

12. The computer program product of claim 7, further comprising program code to factor a personality trait of the recipient.

13. A computer system comprising:

a processing unit operatively coupled to memory;

a tool in communication with the processing unit to predict action propensity, including;

a trust manager to compute a trust antecedent from a message;

a recipient manager to compute a recipient antecedent from recipient social media information;

a director in communication with the trust manager and the recipient manager, the director to combine the computed trust antecedent and computed recipient antecedent, and to predict a perception of credibility towards the message with the combined antecedents;

the recipient manager to compute one or more motivators from one or more message recipients;

an action propensity prediction measurement returned to the director from the recipient manager as a trust measurement for the message, the prediction measurement including a combination of the predicted perception of credibility and the motivator computation; and

a message sent to a recipient identified from the returned prediction measurement.

14. The system of claim 13, wherein the action propensity is a sum of available actions advocated by the message weighted by an importance of the actions.

15. The system of claim 13, further comprising the trust manager to compute the trust antecedent, including assigning a numerical value to each trust antecedent.

16. The system of claim 13, wherein the computation of the recipient antecedent includes data from available recipient information, including a characteristic selected from the group consisting of:

prior knowledge on a subject of the message, influences from an associated social circle, and combinations thereof.

17. The system of claim 13, wherein the computation of the one or more motivators includes computation of a factor selected from the group consisting of:

one or more past behavior records related to the message, thinking style regarding cost and benefit of one or more actions extracted from available recipient information, and combinations thereof.

18. The system of claim 13, further comprising the director to include a personality trait of the recipient with the action propensity prediction measurement, the inclusion to improve prediction accuracy.