CONTENT PRE-PERSONALIZATION USING BIOMETRIC DATA

• US 20200135039A1
• Filed: 10/30/2018
• Published: 04/30/2020
• Est. Priority Date: 10/30/2018
• Status: Active Grant

• Current Assignee: International Business Machines Corporation
• Original Assignee: International Business Machines Corporation
• Inventors: Karna, Geetha, Kakaraparthy, Sreekanth L., Dey, Kuntal
• Granted Patent: US 11,928,985 B2
• Time in Patent Office: Days
• CPC Class Codes: G06N 20/00 Machine learning
• CPC Class Codes: G06V 40/174 Facial expression recognition
• CPC Class Codes: G09B 7/00 Electrically-operated teaching apparatus or devices working with questions and answers mechanically operated G09B3/00; computing arrangements G06F

Abstract

Methods, computer program products, and systems are presented. The method computer program products, and systems can include, for instance: predicting an exhibited sentiment of a certain user on being presented one or more candidate education segment, wherein the predicting is in dependence on historical sentiment parameter values of one or more user on being exposed to presented educational content, the historical sentiment parameter values being stored in a data repository, wherein the presented education segments comprise digital media content adapted for playing by a digital media player; selecting at least one of the one or more candidate education segment in dependence on a result of the predicting so that a selected at least one of the one or more candidate education resulting from the selecting is personalized for the certain user; and presenting to the certain user the selected at least one of the one or more candidate education segment.

Claims

1. A method comprising:

predicting an exhibited sentiment of a certain user on being presented one or more candidate education segment, wherein the predicting is in dependence on historical sentiment parameter values of one or more user on being exposed to presented educational content, the historical sentiment parameter values being stored in a data repository, wherein the presented education segments comprise digital media content adapted for playing by a digital media player;

selecting at least one of the one or more candidate education segment in dependence on a result of the predicting so that a selected at least one of the one or more candidate education resulting from the selecting is personalized for the certain user; and

presenting to the certain user the selected at least one of the one or more candidate education segment.

2. The method of claim 1, wherein the historical sentiment parameter values are derived using biometric sensor output data of the certain user collected with the certain user being exposed to presented educational content.

3. The method of claim 1, wherein the historical sentiment parameter values are derived using biometric sensor output data of the certain user collected with the certain user being exposed to presented educational content, wherein the biometric sensor output data includes measured brain activity data.

4. The method of claim 1, wherein the historical sentiment parameter values are derived using biometric sensor output data of the certain user collected with the certain user being exposed to presented educational content, wherein the biometric sensor output data includes video data representing facial expressions of the certain user.

5. The method of claim 1, wherein the historical sentiment parameter values are derived using biometric sensor output data of the certain user collected with the certain user being exposed to presented educational content, wherein the biometric sensor output data includes video data representing eye gaze patterns of the certain user.

6. The method of claim 1, wherein the selecting at least one of the one or more candidate education segment is in dependence on a currently exhibited sentiment of the certain user.

7. The method of claim 1, wherein the method includes operating in a certain mode in which the selecting at least one of the one or more candidate education segment is on the basis of which of the one or more candidate education segment is predicted to induce the most positive sentiment on the part of the certain user, and activating the certain mode in dependence on a currently exhibited sentiment of the certain user.

8. The method of claim 1, wherein the selecting the at least one of the one or more candidate education segment includes querying a certain predictive model that has been trained by supervised machine learning, wherein training of the predictive model includes applying training data to the predictive model, the training data including for each of N instances of presented education segments presented to the certain user one or more of the following selected from the group consisting of (a) a topic classification dataset characterizing one or more topic of a presented education segment and (b) a content classification dataset characterizing content of a presented education segment.

9. The method of claim 1, wherein the selecting the at least one of the one or more candidate education segment includes querying a certain predictive model that has been trained by supervised machine learning, wherein training of the predictive model includes applying training data to the predictive model, the training data including for each of N instances of presented education segments presented to the certain user a topic classification dataset characterizing one or more topic of a presented education segment and a content classification dataset characterizing content of a presented education segment, and wherein the querying includes querying the certain predictive model with query data that includes one or more of the following selected from the group consisting of (a) a topic classification dataset characterizing one or more topic of a candidate education segment and (b) a content classification dataset characterizing content of a candidate education segment.

10. The method of claim 1, wherein the selecting the at least one of the one or more candidate education segment is performed to induce a sentiment of the certain user determined to be a sentiment exhibited by the certain user when the certain user optimally retains presented educational content, wherein the method includes ascertaining a sentiment exhibited by the certain user when the certain user optimally retains presented educational content using a trained predictive model trained by machine learning, the trained predictive model being trained to return predicted educational content retention data in response to applied query data that includes a set of sentiment parameter values.

11. The method of claim 1, wherein the one or more user includes the certain user.

12. The method of claim 1, further comprising identifying with use of one or more clustering algorithm, a second user exhibiting sentiment behavior similar to a sentiment behavior exhibited by the certain user, and wherein the selecting the at least one of the one or more candidate education segment includes using a particular trained predictive model, the particular trained predictive model being associated to the second user, wherein training data for training the particular trained predictive model includes historical sentiment parameter values exhibited by the second user when presented with educational content.

13. A computer program product comprising:

a computer readable storage medium readable by one or more processing circuit and storing instructions for execution by one or more processor for performing the method comprising;

predicting an exhibited sentiment of a certain user on being presented one or more candidate education segment, wherein the predicting is in dependence on historical sentiment parameter values of one or more user on being exposed to presented educational content, the historical sentiment parameter values being stored in a data repository, wherein the presented education segments comprise digital media content adapted for playing by a digital media player;

selecting at least one of the one or more candidate education segment in dependence on a result of the predicting so that a selected at least one of the one or more candidate education resulting from the selecting is personalized for the certain user; and

presenting to the certain user the selected at least one of the one or more candidate education segment.

14. The computer program product of claim 13, wherein the historical sentiment parameter values are derived using biometric sensor output data of the certain user collected with the certain user being exposed to presented educational content.

15. The computer program product of claim 13, wherein the historical sentiment parameter values are derived using biometric sensor output data of the certain user collected with the certain user being exposed to presented educational content, wherein the biometric sensor output data includes measured brain activity data.

16. The computer program product of claim 13, wherein the historical sentiment parameter values are derived using biometric sensor output data of the certain user collected with the certain user being exposed to presented educational content, wherein the biometric sensor output data includes video data representing facial expressions of the certain user.

17. The computer program product of claim 13, wherein the historical sentiment parameter values are derived using biometric sensor output data of the certain user collected with the certain user being exposed to presented educational content, wherein the biometric sensor output data includes video data representing eye gaze patterns of the certain user.

18. The computer program product of claim 13, wherein the method includes operating in a certain mode in which the selecting at least one of the one or more candidate education segment is on the basis of which of the one or more candidate education segment is predicted to induce the most positive sentiment on the part of the certain user, and activating the certain mode in dependence on a currently exhibited sentiment of the certain user.

19. The computer program product of claim 13, wherein the selecting the at least one of the one or more candidate education segment includes querying a certain predictive model that has been trained by supervised machine learning, wherein training of the predictive model includes applying training data to the predictive model, the training data including for each of N instances of presented education segments presented to the certain user one or more of the following selected from the group consisting of (a) a topic classification dataset characterizing one or more topic of a presented education segment and (b) a content classification dataset characterizing content of a presented education segment.

20. A system comprising:

a memory;

at least one processor in communication with memory; and

program instructions executable by one or more processor via the memory to perform a method comprising;

predicting an exhibited sentiment of a certain user on being presented one or more candidate education segment, wherein

the predicting is in dependence on historical sentiment parameter values of one or more user on being exposed to presented educational content, the historical sentiment parameter values being stored in a data repository, wherein the presented education segments comprise digital media content adapted for playing by a digital media player;

selecting at least one of the one or more candidate education segment in dependence on a result of the predicting so that a selected at least one of the one or more candidate education resulting from the selecting is personalized for the certain user; and

presenting to the certain user the selected at least one of the one or more candidate education segment.