Expanding semantic classes via user feedback
The present technology extends to methods, systems, and computer program products for expanding semantic classes via user feedback. Aspects of the technology learn how a set of labels can be expanded from user-generated tags. Text labels applied by human reviewers to digital content can be inspected and compared to one another. When a threshold of human-generated text tags contain similar terminology, the set of labels can be expanded to define a representation of the similar terminology. Similar terminology can include terms that originate from the same base term, are synonyms, are more specific terms related to a general term category, etc. Similar terminology can be consolidated into a defining term that is used to generate a new (more granular) label or a new top level label. Accordingly, new semantic classes can be discovered from user-generated feedback. New semantic classes can provide a more granular representation of content item classification.
1. A computer-implemented method comprising:
accessing an initial semantic class set;
creating a set of labels based on received tags on content items with classifications from the initial semantic class set;
determining a subset of the set of labels is associated with a shared terminology; generating a first new semantic sub-class based on the shared terminology;
providing the first new semantic sub-class as a new tag available for users to tag social media interactions;
receiving an indication for tagging a social media interaction with the new tag; and
performing a predetermined action based on the new tag.
2. The computer-implemented method of claim 1 , further comprising:
generating a second new semantic sub-class that is not associated with the shared terminology.
3. The computer-implemented method of claim 2 , wherein the second new semantic sub-class is for catch-all label comments that do not belong it any other subclass.
4. The computer-implemented method of claim 1 , further comprising:
resolving a database including the received tags into the first new semantic sub-class with a new label based on the shared terminology.
5. The computer-implemented method of claim 4 , wherein the resolving the database expands the initial semantic class set by adding the new label that serves as the first new semantic sub-class of the initial semantic class set.
6. The computer-implemented method of claim 1 , further comprising:
detecting that a threshold number of content items in a corpus of content items include related terminology, the corpus of content items being associated with initial semantic classes that classify the corpus of content items.
7. The computer-implemented method of claim 6 , further comprising:
based on the detection, generating, via a semantics class computer module, a consolidated term for a tag of a new semantic class based on the related terminology, the new semantic class being in addition to the initial semantic classes classifying the corpus of content items; and
expanding the initial semantic classes into an expanded set of semantic classes by adding the tag corresponding to the new semantic class.
8. A system comprising:
storage configured to store instructions; and
one or more processors configured to execute the instructions and cause the one or more processors to:
access an initial semantic class set;
create a set of labels based on received tags on content items with classifications from the initial semantic class set;
determine a subset of the set of labels is associated with a shared terminology;
generate a first new semantic sub-class based on the shared terminology;
provide the first new semantic sub-class as a new tag available for users to tag social media interactions;
receive an indication for tagging a social media interaction with the new tag; and
perform a predetermined action based on the new tag.
9. The system of claim 8 , further comprising:
generating a second new semantic sub-class that is not associated with the shared terminology.
10. The system of claim 9 , wherein the second new semantic sub-class is for catch-all label comments that do not belong it any other subclass.
11. The system of claim 8 , further comprising:
resolving a database including the received tags into the first new semantic sub-class with a new label based on the shared terminology.
12. The system of claim 11 , wherein the resolving the database expands the initial semantic class set by adding the new label that serves as the first new semantic sub-class of the initial semantic class set.
13. The system of claim 12 , further comprising:
detecting that a threshold number of content items in a corpus of content items include related terminology, the corpus of content items being associated with initial semantic classes that classify the corpus of content items.
14. The system of claim 13 , further comprising:
based on the detection, generating, via a semantics class computer module, a consolidated term for a tag of a new semantic class based on the related terminology, the new semantic class being in addition to the initial semantic classes classifying the corpus of content items; and
expanding the initial semantic classes into an expanded set of semantic classes by adding the tag corresponding to the new semantic class.
15. A non-transitory computer-readable medium comprising instructions, the instructions, when executed by a computing system, cause the computing system to:
access an initial semantic class set;
create a set of labels based on received tags on content items with classifications from the initial semantic class set;
determine a subset of the set of labels is associated with a shared terminology;
generate a first new semantic sub-class based on the shared terminology;
provide the first new semantic sub-class as a new tag available for users to tag social media interactions;
receive an indication for tagging a social media interaction with the new tag; and
perform a predetermined action based on the new tag.
16. The non-transitory computer-readable medium of claim 15 , wherein the non-transitory computer-readable medium further comprises instructions that, when executed by the computing system, cause the computing system to:
generate a second new semantic sub-class that is not associated with the shared terminology.
17. The non-transitory computer-readable medium of claim 16 , wherein the second new semantic sub-class is for catch-all label comments that do not belong it any other subclass.
18. The non-transitory computer-readable medium of claim 15 , wherein the non-transitory computer-readable medium further comprises instructions that, when executed by the computing system, cause the computing system to:
resolving a database including the received tags into the first new semantic sub-class with a new label based on the shared terminology.
19. The non-transitory computer-readable medium of claim 18 , wherein the non-transitory computer-readable medium further comprises instructions that, when executed by the computing system, cause the computing system to:
detecting that a threshold number of content items in a corpus of content items include related terminology, the corpus of content items being associated with initial semantic classes that classify the corpus of content items.
20. The non-transitory computer-readable medium of claim 19 , wherein the non-transitory computer-readable medium further comprises instructions that, when executed by the computing system, cause the computing system to:
based on the detection, generating, via a semantics class computer module, a consolidated term for a tag of a new semantic class based on the related terminology, the new semantic class being in addition to the initial semantic classes classifying the corpus of content items; and
expanding the initial semantic classes into an expanded set of semantic classes by adding the tag corresponding to the new semantic class.