Estimating affective response to a token instance of interest

• US 9,015,084 B2
• Filed: 10/20/2012
• Issued: 04/21/2015
• Est. Priority Date: 10/20/2011
• Status: Active Grant

• Current Assignee: Affectomatics ltd.
• Original Assignee: Affectomatics ltd.
• Inventors: Thieberger, Gil, Frank, Ari M
• Primary Examiner(s): Chaki, Kakali
• Assistant Examiner(s): SITIRICHE, LUIS A
• Application Number:
  US13/656,704
• Publication Number:
  US 20130103624A1
• Time in Patent Office: 913 Days
• Field of Search: None
• US Class Current: 706/12
• CPC Class Codes: G06F 18/214 Generating training patterns; Bootstrap methods, e.g. bagging or boosting
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06N 5/04 Inference or reasoning models
• CPC Class Codes: G06N 5/046 Forward inferencing; Production systems
• CPC Class Codes: G06Q 10/063 Operations research, analysis or management
• CPC Class Codes: G16H 50/20 for computer-aided diagnosis, e.g. based on medical expert systems

Abstract

A user may be exposed to multiple token instances representing stimuli that may influence the affective state of the user. Described herein are embodiments of systems, method, and computer programs for estimating affective response to a token instance of interest, selected from among the token instances. In one example embodiment, the token instance of interest is a token instance for which attention level of the user is higher than at least one other token instance.

Claims

1. A system configured to estimate affective response to a token instance of interest, comprising:

a memory configured to store;

token instances to which a user was exposed, a total affective response of the user to the token instances, and representations of first and second attention levels of the user in respective first and second token instances from among the token instances;

wherein the total affective response is based, at least in part, on values of a user measurement channel that are not utilized to generate the representations of the first and second attention levels;

wherein the first and second token instances have overlapping instantiation periods; and

wherein the first attention level is greater than the second attention level;

a processor configured to select, based on the representations of the first and second attention levels, the first token instance as the token instance of interest; and

the processor is further configured to estimate the affective response to the token instance of interest from the total affective response.

2. The system of claim 1, wherein the total affective response is expressed as an emotional response.

3. The system of claim 1, wherein the total affective response is based on values of a user measurement channel of the user.

4. The system of claim 1, wherein the total affective response is proportional to the difference between affective responses of the user before and after the user was exposed to the token instances.

5. The system of claim 1, wherein the memory is further configured to store a baseline value for affective response of the user, and the processor is further configured to calculate the total affective response with respect to the baseline value;

whereby the baseline value represents a usual affective response of the user, as computed from multiple values acquired over a period of at least a few hours.

6. The system of claim 1, wherein more than 50% of the total affective response is attributed to the affective response to the token instance of interest.

7. The system of claim 1, wherein the token instances originate from multiple distinct token sources.

8. A method for estimating affective response to a token instance of interest, comprising:

receiving token instances to which a user was exposed;

receiving a total affective response of the user to the token instances;

receiving representations of first and second attention levels of the user in respective first and second token instances from among the token instances;

wherein the first and second token instances have overlapping instantiation periods;

wherein the total affective response is based, at least in part, on values of a user measurement channel that are not utilized to generate the representations of the first and second attention levels; and

wherein the first attention level is greater than the second attention level;

selecting the first token instance as the token instance based on the representations of the first and second attention levels; and

estimating the affective response to the token instance of interest from the total affective response.

9. The method of claim 8, wherein the total affective response to the token instances is expressed as an emotional response.

10. The method of claim 8, wherein the total affective response is based on user measurement channels of the user.

11. The method of claim 8, wherein the total affective response to the token instances is proportional to the difference between affective responses of the user before and after the user was exposed to the token instances.

12. The method of claim 8, further comprising receiving a baseline value for the affective response of the user, and calculating the total affective response with respect to the baseline value;

whereby the baseline value represents a usual affective response of the user, as computed from multiple values acquired over a period of at least a few hours.

13. The method of claim 8, wherein more than 50% of the total affective response is attributed to the affective response to the token instance of interest.

14. The method of claim 8, wherein the token instances originate from multiple distinct token sources.

15. A non-transitory computer-readable medium for use in a computer to estimate affective response to a token instance of interest;

the computer comprises a processor, and the non-transitory computer-readable medium comprising;

program code for receiving token instances to which a user was exposed;

program code for receiving a total affective response of the user to the token instances;

program code for receiving representations of first and second attention levels of the user in respective first and second token instances from among the token instances;

wherein the first and second token instances have overlapping instantiation periods;

wherein the total affective response is based, at least in part, on values of a user measurement channel that are not utilized to generate the representations of the first and second attention levels; and

wherein the first attention level is greater than the second attention level;

program code for selecting the first token instance as the token instance of interest based on the representations of the first and second attention levels; and

program code for estimating the affective response to the token instance of interest from the total affective response.

16. The non-transitory computer-readable medium of claim 15, further comprising program code for receiving a baseline value for the affective response of the user, and calculating the total affective response with respect to the baseline value;

whereby the baseline value represents a usual affective response of the user, as computed from multiple values acquired over a period of at least a few hours.

17. The non-transitory computer-readable medium of claim 15, wherein the total affective response is expressed as an emotional response.

18. The non-transitory computer-readable medium of claim 15, wherein the total affective response is based on values of a user measurement channel of the user.

19. The non-transitory computer-readable medium of claim 15, wherein the total affective response is proportional to a difference between affective responses of the user before and after the user was exposed to the token instances.

20. The non-transitory computer-readable medium of claim 15, wherein more than 50% of the total affective response is attributed to the affective response to the token instance of interest.