RECOMMENDATION AGENT USING A PERSONALITY MODEL DETERMINED FROM MOBILE DEVICE DATA

1 . A method of creating a customized recommendation agent for a user, the method comprising:

obtaining a plurality of labelled context slices derived from context data associated with a user, each labelled context slice including a time, a location, and a user context label specifying at least a place inferred from the location;

obtaining place features of places included in the obtained plurality of labelled context slices, the obtained place features relevant to personality traits of the user;

identifying, using the plurality of labelled context slices, one or more home areas corresponding to one or more places at which the user has spent a majority of time spanned by the labelled context slices;

identifying, from the places included in the plurality of labelled context slices, one or more non-home areas corresponding to one or more places that do not correspond to the one or more home areas;

determining a home area statistic and a non-home area statistic from the obtained place features, the home area statistic describing place features of the one or more home areas, the non-home area statistic describing place features of the one or more non-home areas;

determining, by a processor, a personality metric based on the home area statistic and the non-home area statistic, the personality metric quantifying a personality trait dimension of the user; and

creating the customized recommendation agent configured to provide a recommendation to the user responsive to the personality metric indicating the user is likely to find value in the recommendation.

2 . The method of claim 1 ,

wherein obtaining the place features comprises determining a category that groups similar places in one of the identified non-home areas, and

wherein determining the non-home area statistic comprises determining a frequency of visits to the category of the one of the non-home areas.

3 . The method of claim 1 ,

wherein obtaining the place features comprises determining distances from the identified one or more non-home areas to a geographically nearest home area, and

wherein determining the non-home area statistics comprises determining a non-home area statistic summarizing the determined distances from the identified one or more non-home areas to the geographically nearest home area.

4 . The method of claim 1 , wherein determining the home area statistic comprises: determining a proportion of visits to an identified home area relative to total visits to the places specified by the plurality of labelled context slices.

5 . The method of claim 1 , wherein the personality trait dimension includes at least one of: desire for novelty, desire for extravagance, willingness to travel, love of the outdoors, preference for physical activity, and desire for solitude.

6 . The method of claim 1 , wherein the customized recommendation agent provides the recommendation to the user by performing steps comprising:

identifying a reason why the recommendation was selected; and

providing the reason for presentation to the user in conjunction with the recommendation.

7 . The method of claim 1 , wherein the customized recommendation agent provides the recommendation to the user by performing steps comprising:

receiving an input context associated with the user;

selecting the recommendation from a corpus of recommendations based on the determined personality metric and the input context; and

providing the recommendation for presentation to the user.

8 . The method of claim 7 , wherein selecting the recommendation comprises:

determining a weight for each of a plurality of recommendations from the corpus, each weight based on a degree of correspondence between the personality metric and a corresponding recommendation; and

selecting the recommendation from the plurality of recommendations responsive to the weight corresponding to the recommendation.

9 . The method of claim 8 , wherein the recommendation corresponds to a venue, wherein determining the weight comprises:

adjusting the weight corresponding to the recommendation based on a rating for the venue provided by another user.

10 . The method of claim 1 , further comprising:

receiving feedback indicating how the user responded to the recommendation; and

updating the personality metric based on the feedback.

11 . The method of claim 10 , wherein the feedback indicates at least one of: the user following the recommendation, the user adding the recommendations to a plan, the user partially following the recommendation, and the user rejecting the recommendation.

12 . The method of claim 1 , further comprising:

providing the user with a series of questions, each question a binary choice that determines affinity for one of the personality trait dimensions; and

adjusting at least one personality metric of the plurality based on the user's responses to the series of questions.

13 . A non-transitory computer-readable storage medium comprising executable computer program code, the computer program code comprising instructions for:

obtaining a plurality of labelled context slices derived from context data associated with a user, each labelled context slice including a time, a location, and a user context label specifying at least a place inferred from the location;

obtaining place features of places included in the obtained plurality of labelled context slices, the obtained place features relevant to personality traits of the user;

identifying, using the plurality of labelled context slices, one or more home areas corresponding to one or more places at which the user has spent a majority of time spanned by the labelled context slices;

identifying, from the places included in the plurality of labelled context slices, one or more non-home areas corresponding to one or more places that do not correspond to the one or more home areas;

determining a home area statistic and a non-home area statistic from the obtained place features, the home area statistic describing place features of the one or more home areas, the non-home area statistic describing place features of the one or more non-home areas;

determining a personality metric based on the home area statistic and the non-home area statistic, the personality metric quantifying a personality trait dimension of the user; and

creating the customized recommendation agent configured to provide a recommendation to the user responsive to the personality metric indicating the user is likely to find value in the recommendation.

14 . The medium of claim 13 ,

wherein obtaining the place features comprises determining a category that groups similar places in one of the identified non-home areas, and

wherein determining the non-home area statistic comprises determining a frequency of visits to the category of the one of the non-home areas.

15 . The medium of claim 13 ,

wherein obtaining the place features comprises determining distances from the identified one or more non-home areas to a geographically nearest home area, and

wherein determining the non-home area statistics comprises determining a non-home area statistic summarizing the determined distances from the identified one or more non-home areas to the geographically nearest home area.

16 . The medium of claim 13 , wherein determining the home area statistic comprises: determining a proportion of visits to an identified home area relative to total visits to the places specified by the plurality of labelled context slices.

17 . The medium of claim 13 , wherein the customized recommendation agent is configured to provide the recommendation to the user by performing steps comprising:

receiving an input context associated with the user;

selecting the recommendation from a corpus of recommendations based on the determined personality metric and the input context; and

providing the recommendation for presentation to the user.

18 . The medium of claim 17 , wherein selecting the recommendation comprises:

determining a weight for each of a plurality of recommendations from the corpus, each weight based on a degree of correspondence between the personality metric and a corresponding recommendation; and

selecting the recommendation from the plurality of recommendations responsive to the weight corresponding to the recommendation.

19 . The medium of claim 13 , wherein the computer program code further comprises instructions for:

receiving feedback indicating how the user responded to the recommendation; and

updating the personality metric based on the feedback.

20 . A system for creating a customized recommendation agent for a user, the system comprising:

a processor; and

a non-transitory computer-readable storage medium comprising computer program code executable by the processor, the computer program code comprising instructions for:

obtaining a plurality of labelled context slices derived from context data associated with a user, each labelled context slice including a time, a location, and a user context label specifying at least a place inferred from the location;

obtaining place features of places included in the obtained plurality of labelled context slices, the obtained place features relevant to personality traits of the user;

identifying, using the plurality of labelled context slices, one or more home areas corresponding to one or more places at which the user has spent a majority of time spanned by the labelled context slices;

identifying, from the places included in the plurality of labelled context slices, one or more non-home areas corresponding to one or more places that do not correspond to the one or more home areas;

determining a home area statistic and a non-home area statistic from the obtained place features, the home area statistic describing place features of the one or more home areas, the non-home area statistic describing place features of the one or more non-home areas;

determining a personality metric based on the home area statistic and the non-home area statistic, the personality metric quantifying a personality trait dimension of the user; and

creating the customized recommendation agent configured to provide a recommendation to the user responsive to the personality metric indicating the user is likely to find value in the recommendation.