Collecting and analyzing electronic survey responses including user-composed text
View Patent ↗Embodiments of the present disclosure relate to collecting and analyzing electronic survey responses that include user-composed text. In particular, systems and methods disclosed herein facilitate collection of electronic survey responses in response to electronic survey questions. The systems and methods disclosed herein classify the electronic survey questions and determine a semantics model including customized operators for analyzing the electronic survey responses to the corresponding electronic survey questions. In addition, the systems and methods disclosed herein provide a presentation of the results of the analysis of the electronic survey responses via a graphical user interface of a client device.
1. A method comprising:
receiving a search query requesting information from a collection of individual user-composed text instances, wherein each individual user-composed text instance is associated with at least one semantics model;
determining a search classification for the search query based on content of the search query;
identifying a subgroup of individual user-composed text instances from the collection of individual user-composed text instances based on determining that the subgroup of individual user-composed text instances relate to the search classification for the search query;
analyzing the subgroup of individual user-composed text instances based on the content of the search query and based on semantics models associated with the subgroup of individual user-composed text instances; and
providing, via a graphical user interface of a client device, a presentation of results for the search query comprising information identified within a plurality of electronic survey responses using the semantics models associated with the subgroup of individual user-composed text instances.
2. The method of claim 1 , further comprising generating the at least one semantics model to associate with each individual user-composed text instance of the collection of the individual user-composed text instances by identifying one or more operators that identify one or more types of information contained within each individual user-composed text instance of the collection of the individual user-composed text instances.
3. The method of claim 2 , wherein the one or more types of information comprise one or more of: opinions, recommendations, or questions.
4. The method of claim 1 , wherein the collection of individual user-composed text instances comprises a plurality of user-composed digital survey responses.
5. The method of claim 1 , wherein receiving a search query requesting information from a collection of individual user-composed text instances comprises receiving a natural language sentence.
6. The method of claim 5 , wherein determining a search classification for the search query based on content of the search query comprises analyzing the natural language sentence to determine if the search query is requesting information related to opinions, recommendations or questions.
7. The method of claim 1 , further comprising:
determining a first group of words related to positive opinions from the information identified within the plurality of electronic survey responses using the semantics models associated with the subgroup of individual user-composed text instances;
determining a second group of words related to negative opinions from the information identified within the plurality of electronic survey responses using the semantics models associated with the subgroup of individual user-composed text instances; and
wherein the presentation of the results for the search query further comprises a presentation of the first group of words and the second group of words.
8. A non-transitory computer readable storage medium storing instructions thereon that, when executed by at least one processor, cause a computing device to:
receive a search query requesting information from a collection of individual user-composed text instances, wherein each individual user-composed text instance is associated with at least one semantics model;
determine a search classification for the search query based on content of the search query;
identify a subgroup of individual user-composed text instances from the collection of individual user-composed text instances based on determining that the subgroup of individual user-composed text instances relate to the search classification for the search query;
analyze the subgroup of individual user-composed text instances based on the content of the search query and based on semantics models associated with the subgroup of individual user-composed text instances; and
provide, via a graphical user interface of a client device, a presentation of results for the search query comprising information identified within a plurality of electronic survey responses using the semantics models associated with the subgroup of individual user-composed text instances.
9. The non-transitory computer readable storage medium of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the computing device to generate the at least one semantics model to associate with each individual user-composed text instance of the collection of the individual user-composed text instances by identifying one or more operators that identify one or more types of information contained within each individual user-composed text instance of the collection of the individual user-composed text instances.
10. The non-transitory computer readable storage medium of claim 9 , wherein the one or more types of information comprise one or more of: opinions, recommendations, or questions.
11. The non-transitory computer readable storage medium of claim 8 , wherein the collection of individual user-composed text instances comprises a plurality of user-composed digital survey responses.
12. The non-transitory computer readable storage medium of claim 8 , wherein receiving a search query requesting information from a collection of individual user-composed text instances comprises receiving a natural language sentence.
13. The non-transitory computer readable storage medium of claim 12 , wherein determining a search classification for the search query based on content of the search query comprises analyzing the natural language sentence to determine if the search query is requesting information related to opinions, recommendations or questions.
14. A system comprising:
at least one processor; and
a non-transitory computer readable storage medium storing instructions thereon that, when executed by the at least one processor, cause the system to:
receive a search query requesting information from a collection of individual user-composed text instances, wherein each individual user-composed text instance is associated with at least one semantics model;
determine a search classification for the search query based on content of the search query;
identify a subgroup of individual user-composed text instances from the collection of individual user-composed text instances based on determining that the subgroup of individual user-composed text instances relate to the search classification for the search query;
analyze the subgroup of individual user-composed text instances based on the content of the search query and based on semantics models associated with the subgroup of individual user-composed text instances; and
provide, via a graphical user interface of a client device, a presentation of results for the search query comprising information identified within a plurality of electronic survey responses using the semantics models associated with the subgroup of individual user-composed text instances.
15. The system of claim 14 , further comprising instructions that, when executed by the at least one processor, cause the system to generate the at least one semantics model to associate with each individual user-composed text instance of the collection of the individual user-composed text instances by identifying one or more operators that identify one or more types of information contained within each individual user-composed text instance of the collection of the individual user-composed text instances.
16. The system of claim 15 , wherein the one or more types of information comprise one or more of: opinions, recommendations, or questions.
17. The system of claim 14 , wherein the collection of individual user-composed text instances comprises a plurality of user-composed digital survey responses.
18. The system of claim 14 , wherein receiving a search query requesting information from a collection of individual user-composed text instances comprises receiving a natural language sentence.
19. The system of claim 18 , wherein determining a search classification for the search query based on content of the search query comprises analyzing the natural language sentence to determine if the search query is requesting information related to opinions, recommendations or questions.
20. The system of claim 14 , further comprising instructions that, when executed by the at least one processor, cause the system to:
determine a first group of words related to positive opinions from the information identified within the plurality of electronic survey responses using the semantics models associated with the subgroup of individual user-composed text instances;
determine a second group of words related to negative opinions from the information identified within the plurality of electronic survey responses using the semantics models associated with the subgroup of individual user-composed text instances; and
wherein the presentation of the results for the search query comprises the first group of words and the second group of words.