Method and system for personalizing software based on real time tracking of voice-of-customer feedback
Techniques are disclosed for dynamically personalizing application content presented to a user based on “voice-of-customer” feedback, in real-time. As described, the user may provide voice-of-customer feedback characterizing an initial selection of application content presented to the user may be evaluated to identify a set of topics referenced by the voice-of-customer feedback. Keywords associated with the identified topics may be used to enhance the selection of application content presented to the user. For example, keywords associated with the identified topics may be added to an initial search query composed by the user. Doing so can improve the relevance or helpfulness of information content or software interfaces identified using the query.
1. A computer-implemented method for dynamically personalizing application content of a software application presented to a user based on usefulness feedback, comprising:
receiving, from a user, a first search query related to application content of the software application;
searching one or more content repositories associated with the software application for a first selection of application content based on the first search query;
presenting the first selection of application content to the user; and
while the user is interacting with the software application:
presenting, to the user, a prompt for usefulness feedback from the user;
receiving the usefulness feedback from the user, wherein the usefulness feedback indicates a user opinion of the usefulness of the first selection of application content;
evaluating the received usefulness feedback to identify at least a first topic referenced in the received usefulness feedback;
determining one or more keywords associated with the first topic;
searching the one or more content repositories associated with the software application for a second selection of application content based on one or more keywords identified in the first search query and the determined one or more keywords associated with the first topic, wherein the second selection of application content comprises information including one or more topics missing in the first selection of application content; and
presenting the second selection of application content to the user.
2. A computer-readable storage medium storing instructions, which when executed on a processor, perform an operation for dynamically personalizing application content of a software application presented to a user based on usefulness feedback, the operation comprising:
receiving, from a user, a first search query related to application content of the software application;
searching one or more content repositories associated with the software application for a first selection of application content based on the first search query;
presenting the first selection of application content to the user; and
while the user is interacting with the software application:
presenting, to the user, a prompt for usefulness feedback from the user;
receiving the usefulness feedback from the user, wherein the usefulness feedback indicates a user opinion of the usefulness of the first selection of application content;
evaluating the received usefulness feedback to identify at least a first topic referenced in the received usefulness feedback;
determining one or more keywords associated with the first topic;
searching the one or more content repositories associated with the software application for a second selection of application content based on one or more keywords identified in the first search query and the determined one or more keywords associated with the first topic, wherein the second selection of application content comprises information including one or more topics missing in the first selection of application content; and
presenting the second selection of application content to the user.
3. A system, comprising:
a processor; and
a memory containing a program which, when executed on the processor, performs an operation for dynamically personalizing application content of a software application presented to a user based on usefulness feedback, the operation comprising:
receiving, from a user, a first search query related to application content of the software application,
searching one or more content repositories associated with the software application for a first selection of application content based on the first search query;
presenting the first selection of application content to the user, and
while the user is interacting with the software application:
presenting, to the user, a prompt for usefulness feedback from the user;
receiving the usefulness feedback from the user, wherein the usefulness feedback indicates a user opinion of the usefulness of the first selection of application content;
evaluating the received usefulness feedback to identify at least a first topic referenced in the received usefulness feedback;
determining one or more keywords associated with the first topic;
searching the one or more content repositories associated with the software application for a second selection of application content based on one or more keywords identified in the first search query and the determined one or more keywords associated with the first topic, wherein the second selection of application content comprises information including one or more topics missing in the first selection of application content; and
presenting the second selection of application content to the user.
4. The computer-implemented method of claim 1 , wherein the received usefulness feedback is evaluated using a probabilistic topic model generated from the one or more content repositories associated with the software application.
5. The computer-implemented method of claim 1 , wherein the first search query identifies a first set of keywords.
6. The computer-implemented method of claim 1 , wherein either the first or second selection of application content, or both, reference one or more application features accessible to the user.
7. The computer-implemented method of claim 1 , wherein the software application comprises an online interactive service exposed to users over computer networks.
8. The method of claim 1 , wherein determining one or more keywords associated with the first topic comprises determining one or more keywords associated with a topic having a probability of being referenced in the one or more content repositories above a threshold probability.
9. The computer-readable storage medium of claim 2 , wherein the received usefulness feedback is evaluated using a probabilistic topic model generated from the one or more content repositories associated with the software application.
10. The computer-readable storage medium of claim 2 , wherein the first search query identifies a first set of keywords.
11. The computer-readable storage medium of claim 2 , wherein either the first or second selection of application content, or both, reference one or more application features accessible to the user.
12. The computer-readable storage medium of claim 2 , wherein determining one or more keywords associated with the first topic comprises determining keywords associated with a topic having a probability of being referenced in the one or more content repositories above a threshold probability.
13. The system of claim 3 , wherein the received usefulness feedback is evaluated using a probabilistic topic model generated from the one or more content repositories associated with the software application.
14. The system of claim 3 , wherein the first search query identifies a first set of keywords.
15. The system of claim 3 , wherein either the first or second selection of application content, or both, reference one or more application features accessible to the user.
16. The system of claim 3 , wherein determining one or more keywords associated with the first topic comprises determining keywords associated with a topic having a probability of being referenced in the one or more content repositories above a threshold probability.
17. The computer-implemented method of claim 4 , wherein the one or more content repositories include user generated content published by an online community supporting the software application.
18. The computer-implemented method of claim 4 , wherein the probabilistic topic model is a Latent Dirichlet Allocation (LDA) model.
19. The computer-implemented method of claim 5 , wherein searching the one or more content repositories for the second selection of application content based on the determined one or more keywords associated with the first topic comprises:
generating a second search query by adding the one or more keywords associated with the first topic to the first search query; and
performing the second search query.
20. The computer-readable storage medium of claim 9 , wherein the one or more content repositories include user generated content published by an online community supporting the software application.
21. The computer-readable storage medium of claim 9 , wherein the probabilistic topic model is a Latent Dirichlet Allocation (LDA) model.
22. The computer-readable storage medium of claim 10 , wherein searching the one or more content repositories associated with the software application for the second selection of application content based on the determined one or more keywords associated with the first topic comprises:
generating a second search query by adding the one or more keywords associated with the first topic to the first search query; and
performing the second search query.
23. The system of claim 13 , wherein the one or more content repositories include user generated content published by an online community supporting the software application.
24. The system of claim 13 , wherein the probabilistic topic model is a Latent Dirichlet Allocation (LDA) model.
25. The system of claim 14 , wherein searching the one or more content repositories associated with the software application for the second selection of application content based on the determined one or more keywords associated with the first topic comprises:
generating a second search query by adding the one or more keywords associated with the first topic to the first search query; and
performing the second search query.