Method and system for creating filters for social data topic creation
Disclosed is a system, method, and computer program product for performing semantic analysis and creating topics with regards to social data. A user interface is provided that allows the user to view and interact with to view and control the process/mechanism or creating topics. The user interface allows the user to create one or more text-based filters and metadata filters based on which social data for each topic is filtered.
1. A method comprising:
generating a graphical user interface for defining a semantic analysis topic;
receiving, via the graphical user interface, one or more first user inputs indicating a search term;
generating, based on the search term and a sample corpus of data, a plurality of content themes, wherein generating the plurality of content themes comprises accessing a semantic space to perform semantic analysis on the sample corpus of data;
presenting the plurality of content themes in the graphical user interface;
receiving, via the graphical user interface, one or more second user inputs indicating that a first content theme in the plurality of content themes is not pertinent to the semantic analysis topic;
generating, based at least on the one or more second user inputs, a semantic filter to include in the semantic analysis topic,
wherein the semantic filter matches messages corresponding to a second content theme, in the plurality of content themes, that is pertinent to the semantic analysis topic, and
wherein the semantic filter does not match messages corresponding to the first content theme that is not pertinent to the semantic analysis topic;
receiving a plurality of messages; and
categorizing the plurality of messages at least by applying the semantic analysis topic to the plurality of messages, wherein applying the semantic analysis topic to the plurality of messages comprises applying the semantic filter to the plurality of messages,
wherein applying the semantic filter to the plurality of messages comprises, for a message in the plurality of messages:
vectorizing the message to obtain a vectorized message;
analyzing the vectorized message against a topic vector corresponding to the semantic filter; and
annotating the message, based at least in part on analyzing the vectorized message against the topic vector,
wherein the method is performed by one or more devices comprising one or more hardware processors.
2. The method of claim 1 , further comprising:
receiving, via the graphical user interface, one or more third user inputs indicating that the second content theme is pertinent to the semantic analysis topic.
3. The method of claim 1 , wherein applying the semantic analysis topic to the plurality of messages further comprises applying a keyword search to each message in the plurality of messages.
4. The method of claim 1 , wherein applying the semantic analysis topic to the plurality of messages further comprises applying a metadata filter to each message in the plurality of messages.
5. The method of claim 4 , wherein the metadata filter is based on one or more geographical locations indicated by metadata in the plurality of messages.
6. The method of claim 4 , wherein the metadata filter is based on one or more content types indicated by metadata in the plurality of messages.
7. The method of claim 4 , wherein the metadata filter is based on one or more uniform resource locators (URL's) indicated by metadata in the plurality of messages.
8. The method of claim 4 , wherein the metadata filter is based on one or more message authors indicated by metadata in the plurality of messages.
9. A non-transitory computer readable medium comprising instructions which, when executed by one or more hardware processors, cause performance of operations comprising:
generating a graphical user interface for defining a semantic analysis topic;
receiving, via the graphical user interface, one or more first user inputs indicating a search term;
generating, based on the search term and a sample corpus of data, a plurality of content themes, wherein generating the plurality of content themes comprises accessing a semantic space to perform semantic analysis on the sample corpus of data;
presenting the plurality of content themes in the graphical user interface;
receiving, via the graphical user interface, one or more second user inputs indicating that a first content theme in the plurality of content themes is not pertinent to the semantic analysis topic;
generating, based at least on the one or more second user inputs, a semantic filter to include in the semantic analysis topic,
wherein the semantic filter matches messages corresponding to a second content theme, in the plurality of content themes, that is pertinent to the semantic analysis topic, and
wherein the semantic filter does not match messages corresponding to the first content theme that is not pertinent to the semantic analysis topic;
receiving a plurality of messages; and
categorizing the plurality of messages at least by applying the semantic analysis topic to the plurality of messages, wherein applying the semantic analysis topic to the plurality of messages comprises applying the semantic filter to the plurality of messages,
wherein applying the semantic filter to the plurality of messages comprises, for a message in the plurality of messages:
vectorizing the message to obtain a vectorized message;
analyzing the vectorized message against a topic vector corresponding to the semantic filter; and
annotating the message, based at least in part on analyzing the vectorized message against the topic vector.
10. The non-transitory computer readable medium of claim 9 , the operations further comprising:
receiving, via the graphical user interface, one or more third user inputs indicating that the second content theme is pertinent to the semantic analysis topic.
11. The non-transitory computer readable medium of claim 9 , wherein applying the semantic analysis topic to the plurality of messages further comprises applying a keyword search to each message in the plurality of messages.
12. The non-transitory computer readable medium of claim 9 , wherein applying the semantic analysis topic to the plurality of messages further comprises applying a metadata filter to each message in the plurality of messages.
13. The non-transitory computer readable medium of claim 12 , wherein the metadata filter is based on one or more geographical locations indicated by metadata in the plurality of messages.
14. The non-transitory computer readable medium of claim 12 , wherein the metadata filter is based on one or more content types indicated by metadata in the plurality of messages.
15. The non-transitory computer readable medium of claim 12 , wherein the metadata filter is based on one or more uniform resource locators (URL's) indicated by metadata in the plurality of messages.
16. The non-transitory computer readable medium of claim 12 , wherein the metadata filter is based on one or more message authors indicated by metadata in the plurality of messages.
17. A system comprising:
one or more hardware processors; and
one or more one or more non-transitory computer-readable media storing instructions, which when executed by the one or more hardware processors, cause execution of operations comprising:
generating a graphical user interface for defining a semantic analysis topic;
receiving, via the graphical user interface, one or more first user inputs indicating a search term;
generating, based on the search term and a sample corpus of data, a plurality of content themes, wherein generating the plurality of content themes comprises accessing a semantic space to perform semantic analysis on the sample corpus of data;
presenting the plurality of content themes in the graphical user interface;
receiving, via the graphical user interface, one or more second user inputs indicating that a first content theme in the plurality of content themes is not pertinent to the semantic analysis topic;
generating, based at least on the one or more second user inputs, a semantic filter to include in the semantic analysis topic,
wherein the semantic filter matches messages corresponding to a second content theme, in the plurality of content themes, that is pertinent to the semantic analysis topic, and
wherein the semantic filter does not match messages corresponding to the first content theme that is not pertinent to the semantic analysis topic;
receiving a plurality of messages; and
categorizing the plurality of messages at least by applying the semantic analysis topic to the plurality of messages, wherein applying the semantic analysis topic to the plurality of messages comprises applying the semantic filter to the plurality of messages,
wherein applying the semantic filter to the plurality of messages comprises, for a message in the plurality of messages:
vectorizing the message to obtain a vectorized message;
analyzing the vectorized message against a topic vector corresponding to the semantic filter; and
annotating the message, based at least in part on analyzing the vectorized message against the topic vector.
18. The system of claim 17 , the operations further comprising:
receiving, via the graphical user interface, one or more third user inputs indicating that the second content theme is pertinent to the semantic analysis topic.
19. The system of claim 17 , wherein applying the semantic analysis topic to the plurality of messages further comprises applying a keyword search to each message in the plurality of messages.
20. The system of claim 17 , wherein applying the semantic analysis topic to the plurality of messages further comprises applying a metadata filter to each message in the plurality of messages.
21. The system of claim 20 , wherein the metadata filter is based on one or more geographical locations indicated by metadata in the plurality of messages.
22. The system of claim 20 , wherein the metadata filter is based on one or more content types indicated by metadata in the plurality of messages.
23. The system of claim 20 , wherein the metadata filter is based on one or more uniform resource locators (URL's) indicated by metadata in the plurality of messages.
24. The system of claim 20 , wherein the metadata filter is based on one or more message authors indicated by metadata in the plurality of messages.