Methods and systems for personalizing user experience based on attitude prediction
The disclosure herein relates to a system and method for personalizing an online experience of a user based on the user's attitude. Attitude models are constructed from user activity data that are able to infer or determine attitudes for a user. Based on the attitudes derived from applying the attitude models, attitude profiles are created for the users. As a users engage in various types of online interactions, the attitude profiles associated with the users can be utilized to personalize the online experience of the user.
1. A method for personalizing a user online experience, the method comprising:
constructing, via at least one computing device, at least one attitude model based, at least in part, on an activity stream indicative of activities and/or interactions performed by users during engaging in online activities, wherein the activity stream at least comprises: click logs, logs related to advertisements presented to the user, metrics from website analytic software, logs indicative of user exposure to or interaction with multimedia or user-generated content, social graphs, logs indicative of activity on social networking websites, e-mail communications, instant messaging communications, social networking metrics, or a combination thereof, and wherein the at least one attitude model is indicative of a user attitude toward at least one online interaction;
via the at least one computing device, generating an attitude profile for at least one user based at least partially on the at least one attitude model, wherein the attitude profile indicates a user's attitude toward the at least one online interaction; and
via the at least one computing device, personalizing an online experience of the at least one user based at least partially on the user's attitude in the attitude profile.
2. The method as recited in claim 1 , wherein the constructing at least one attitude model comprises: identifying a focal attitude for investigation; and identifying relevant portions of the activity stream associated with the focal attitude for generating the at least one attitude model.
3. The method as recited in claim 1 , further comprising: specifying one or more metrics for the activity stream to be used in constructing the at least one attitude model.
4. The method as recited in claim 2 , further comprising: administering a survey instrument to users for assessing feasibility of the relationship between the focal attitude and the identified activity stream.
5. The method as recited in claim 2 , further comprising: performing a model fitting technique to select an attitude model from a plurality of candidate attitude models.
6. The method as recited in claim 1 , further comprising: updating the attitude profile of the at least one user based at least partially on a newly received activity stream.
7. The method as recited in claim 1 , further comprising: periodically supplementing the at least one attitude model to adjust a manner in which the at least one attitude model determines attitudes for the at least one user.
8. The method as recited in claim 1 , wherein personalizing the online experience of the at least one user includes at least one of: personalizing presentation of advertisements to the user based at least partially on the attitude profile for the at least one user; emphasizing or de-emphasizing features of an interface presented to the at least one user based at least partially on the attitude profile for the at least one user; personalizing feedback provided to the at least one user based at least partially on the attitude profile for the at least one user; or personalizing incentives presented to the at least one user based at least partially on the attitude profile for the at least one user.
9. A system for personalizing an online experience comprising:
at least one server to:
construct at least one attitude model based, at least in part, on an activity stream to be indicative of activities and/or interactions to be performed by users to be engaged in online activities, wherein the activity stream is to at least comprise: click logs, logs related to advertisements presented to the user, metrics from website analytic software, logs indicative of user exposure to or interaction with multimedia or user-generated content, social graphs, logs indicative of activity on social networking websites, e-mail communications, instant messaging communications, social networking metrics, or a combination thereof, and wherein the at least one attitude model is to be indicative of a user attitude toward at least one online interaction;
generate an attitude profile for at least one user based at least partially on the at least one attitude model, wherein the attitude profile to indicate a user's attitude toward the at least one online interaction; and
personalize an online experience of the at least one user to be based on the user's attitude in the attitude profile.
10. The system as recited in claim 9 , wherein the at least one server to: identify a focal attitude for investigation; and identify relevant portions of the activity stream to be associated with the focal attitude to generate the at least one attitude model.
11. The system as recited in claim 9 , wherein the at least one server to: specify one or more metrics for the activity stream to be used in constructing the at least one attitude model.
12. The system as recited in claim 10 , wherein the at least one server to: administer a survey instrument to users for assessing feasibility of the relationship between the focal attitude and the identified activity stream.
13. The system as recited in claim 9 , wherein the at least one server to: perform a model fitting technique to select an attitude model from a plurality of candidate attitude models.
14. The system as recited in claim 9 , wherein the at least one server to: update the attitude profile of the at least one user based at least partially on a newly to be received activity stream.
15. The system as recited in claim 9 , wherein the at least one server to: periodically supplement the at least one attitude model to adjust a manner in which the at least one attitude model is to determine attitudes for the at least one user.
16. The system as recited in claim 9 , wherein the at least one server to: personalize presentation of advertisements to the user based at least partially on the attitude profile for the at least one user; emphasize or de-emphasize features on an interface to be presented to the at least one user based at least partially on the attitude profile for the at least one user; personalize feedback to be provided to the at least one user based at least partially on the attitude profile for the at least one user; or personalize incentives to be presented to the at least one user based at least partially on the attitude profile for the at least one user.
17. A non-transitory computer storage medium comprising computer executable instructions to:
construct at least one attitude model based, at least in part, on an activity stream to be indicative of activities and/or interactions to be performed by users to be engaged in online activities, wherein the activity stream is to at least comprise: click logs, logs related to advertisements presented to the user, metrics from website analytic software, logs indicative of user exposure to or interaction with multimedia or user-generated content, social graphs, logs indicative of activity on social networking websites, e-mail communications, instant messaging communications, social networking metrics, or a combination thereof, and wherein the at least one attitude model is to be indicative of a user attitude toward at least one online interaction;
generate an attitude profile for at least one user based at least partially on the at least one attitude model, wherein the attitude profile to indicate a user's attitude toward the at least one online interaction; and
personalize an online experience of the at least one user to be based on the user's attitude in the attitude profile.
18. The computer storage medium as recited in claim 17 , wherein the executable instructions are further to specify one or more metrics for the activity stream to be used in constructing the attitude model.
19. The computer storage medium as recited in claim 17 , wherein the executable instructions are further to perform a model fitting technique to select an attitude model from a plurality of candidate attitude models.
20. The computer storage medium as recited in claim 17 , wherein the executable instructions are further to personalize presentation of advertisements to the user based at least partially on the attitude profile for the at least one user; emphasize or de-emphasize features on an interface to be presented to the at least one user based at least partially on the attitude profile for the at least one user; personalize feedback to be provided to the at least one user based at least partially on the attitude profile for the at least one user; or personalize incentives to be presented to the at least one user based at least partially on the attitude profile for the at least one user.
21. A method for personalizing a user experience, the method comprising:
constructing, via at least one computing device, at least one attitude model based, at least in part, on an activity stream indicative of activities and/or interactions performed by users during engaging in online activities, wherein the at least one attitude model is indicative of a user attitude toward at least one online interaction, and wherein constructing at least one attitude model further comprises:
identifying an attitude for analysis and identifying at least one candidate activity stream related to the identified attitude;
generating a survey instrument to be administered to users and associated with the at least one candidate activity stream;
collecting responses to the generated survey instrument;
employing an associational analysis to determine one or more statistical relationships between the at least one candidate activity stream and the collected responses to the generated survey instrument, and wherein the constructed at least one attitude model is based, at least in part, on the one or more statistical relationships;
via the at least one computing device, generating an attitude profile for at least one user based at least partially on the at least one attitude model, wherein the attitude profile indicates a user's attitude toward the at least one online interaction; and
via the at least one computing device, personalizing an online experience of the at least one user based at least partially on the user's attitude in the attitude profile.