Method and system for mapping notable entities to their social profiles
View Patent ↗Methods, systems, and computer-readable media for mapping entities to social profile data. Social data regarding an entity (e.g., a notable entity, celebrity, movie, famous brand, etc.) is filtered from one or more open knowledge databases to produce filtered social data regarding the entity (or entities). The filtered social data is clustered and classified with respect to the entity according to a hash function to produce candidate results related to the entity. Ambiguous results are then filtered out from the candidate results, thereby automatically mapping facts contained in one or more of the open knowledge databases to a social profile associated with the entity.
1. A method for mapping entities to social profile data, comprising:
filtering social data regarding at least one entity from at least one open knowledge database to produce filtered social data regarding said at least one entity;
clustering and classifying said filtered social data with respect to said at least one entity according to a hash function to produce candidate results related to said at least one entity; and
filtering out ambiguous results from said candidate results, thereby automatically mapping facts contained in said at least one open knowledge database to social profiles associated with said at least one entity.
2. The method of claim 1 wherein filtering social data regarding at least one entity from at least one open knowledge database to produce filtered social data, further comprises:
filtering said social data regarding said at least one entity based on data associated with a subset of verified social network accounts originating from a social network provider.
3. The method of claim 1 wherein clustering and classifying said filtered social data with respect to said at least one entity according to a hash function to produce candidate results related to said at least one entity, further comprises:
calculating said at least one hash function based on a common attribute.
4. The method of claim 1 wherein clustering and classifying said filtered social data with respect to said at least one entity according to a hash function to produce candidate results related to said at least one entity, further comprises:
clustering said at least one entity based on said hash function.
5. The method of claim 1 wherein clustering and classifying said filtered social data with respect to said at least one entity according to a hash function to produce candidate results related to said at least one entity, further comprises:
calculating said at least one hash function based on a common attribute; and
clustering said at least one entity based on said hash function.
6. The method of claim 1 wherein filtering out ambiguous results further comprises:
determining if a single verified entity is contained among said ambiguous results; and
selecting said single verified entity in response to determining that said single verified entity is contained among said ambiguous results.
7. The method of claim 1 wherein classifying said filtered social data further comprises:
classifying said filtered social data utilizing a classifier that is trained to determine a difference between real social network data and fake social network data.
8. A system for mapping entities to social profile data, said system comprising:
at least one processor; and
a memory, wherein said at least one processor or said memory is configured for:
filtering social data regarding at least one entity from at least one open knowledge database to produce filtered social data regarding said at least one entity;
clustering and classifying said filtered social data with respect to said at least one entity according to a hash function to produce candidate results related to said at least one entity; and
filtering out ambiguous results from said candidate results, thereby automatically mapping facts contained in said at least one open knowledge database to social profiles associated with said at least one entity.
9. The system of claim 8 wherein filtering social data regarding at least one entity from at least one open knowledge database to produce filtered social data, further comprises:
filtering said social data regarding said at least one entity based on data associated with a subset of verified social network accounts originating from a social network provider.
10. The system of claim 8 wherein clustering and classifying said filtered social data with respect to said at least one entity according to a hash function to produce candidate results related to said at least one entity, further comprises:
calculating said at least one hash function based on a common attribute.
11. The system of claim 8 wherein clustering and classifying said filtered social data with respect to said at least one entity according to a hash function to produce candidate results related to said at least one entity, further comprises:
clustering said at least one entity based on said hash function.
12. The system of claim 8 wherein clustering and classifying said filtered social data with respect to said at least one entity according to a hash function to produce candidate results related to said at least one entity, further comprises:
calculating said at least one hash function based on a common attribute; and
clustering said at least one entity based on said hash function.
13. The system of claim 8 wherein filtering out ambiguous results further comprises:
determining if a single verified entity is contained among said ambiguous results; and
selecting said single verified entity in response to determining that said single verified entity is contained among said ambiguous results.
14. The system of claim 8 wherein classifying said filtered social data further comprises:
classifying said filtered social data utilizing a classifier that is trained to determine a difference between real social network data and fake social network data.
15. A non-transitory computer-readable storage medium for mapping entities to social profile data, comprising:
instructions for filtering social data regarding at least one entity from at least one open knowledge database to produce filtered social data regarding said at least one entity;
instructions for clustering and classifying said filtered social data with respect to said at least one entity according to a hash function to produce candidate results related to said at least one entity; and
instructions for filtering out ambiguous results from said candidate results, thereby automatically mapping facts contained in said at least one open knowledge database to social profiles associated with said at least one entity.
16. The non-transitory computer-readable storage medium of claim 15 wherein said instructions for filtering social data regarding at least one entity from at least one open knowledge database to produce filtered social data, further comprises:
instructions for filtering said social data regarding said at least one entity based on data associated with a subset of verified social network accounts originating from a social network provider.
17. The non-transitory computer-readable storage medium of claim 15 wherein said instructions for clustering and classifying said filtered social data with respect to said at least one entity according to a hash function to produce candidate results related to said at least one entity, further comprises:
instructions for calculating said at least one hash function based on a common attribute; and
instructions for clustering said at least one entity based on said hash function.
18. The non-transitory computer-readable storage medium of claim 15 wherein said instructions for filtering out ambiguous results further comprises:
instructions for determining if a single verified entity is contained among said ambiguous results.
19. The non-transitory computer-readable storage medium of claim 18 wherein said instructions for filtering out ambiguous results further comprises:
instructions for selecting said single verified entity in response to determining that said single verified entity is contained among said ambiguous results.
20. The non-transitory computer-readable storage medium of claim 15 wherein said instructions for classifying said filtered social data further comprises:
instructions for classifying said filtered social data utilizing a classifier that is trained to determine a difference between real social network data and fake social network data.