Generating and distributing digital surveys based on predicting survey responses to digital survey questions
The present disclosure relates to systems, methods, and non-transitory computer readable media for generating a predicted response to a digital survey question and identifying digital survey questions to remove from a digital survey. For example, the disclosed systems can reduce the number of digital survey questions distributed as part of a digital survey by identifying and removing similar digital survey questions. In addition, the disclosed systems can generate a predicted response to an unprovided digital survey question based on determining relationships between respondents. Further, based on respondent relationships, the disclosed systems can identify digital survey questions that a respondent is likely to answer and can provide the digital survey questions to a respondent device of the respondent.
1. A computer-implemented method comprising:
receiving, from a respondent device, a response comprising freeform text, the response corresponding to a digital survey question from a plurality of digital survey questions associated with a digital survey;
analyzing the freeform text to determine response attributes associated with the response;
determining, based on the response attributes, a relationship between the response and an unanswered digital survey question from the plurality of digital survey questions; and
based on the relationship between the response and the unanswered digital survey question, modifying administration of the digital survey to exclude the unanswered digital survey question from presentation on the respondent device.
2. The computer-implemented method of claim 1 , wherein receiving the response comprises identifying the freeform text in an electronic message or a post.
3. The computer-implemented method of claim 1 , wherein modifying the administration of the digital survey comprises customizing the plurality of digital survey questions for the respondent device by excluding the unanswered digital survey question from the digital survey.
4. The computer-implemented method of claim 1 , further comprising:
determining, based on the response comprising the freeform text, a relationship between a respondent associated with the respondent device and at least one other respondent of a plurality of respondents; and
generating, for the respondent, a predicted response to the unanswered digital survey question based on the relationship between the respondent and the at least one other respondent.
5. The computer-implemented method of claim 1 , further comprising:
determining, based on the response attributes, an additional relationship between the response and an additional unanswered digital survey question from the plurality of digital survey questions; and
providing the additional unanswered digital survey question to the respondent device based on the additional relationship between the response and the additional unanswered digital survey question.
6. The computer-implemented method of claim 5 , wherein determining the additional relationship between the response and the additional unanswered digital survey question comprises:
determining a relevance score for the additional unanswered digital survey question in relation to a respondent associated with the respondent device based on the response attributes; and
determining that the relevance score satisfies a relevance threshold.
7. The computer-implemented method of claim 1 , wherein determining the relationship between the response and the unanswered digital survey question comprises:
generating a set of similarity scores representing similarities between the response and each response in a set of responses;
determining, from the set of similarity scores, a similarity score between the response and an additional response satisfies a similarity threshold; and
determining the unanswered digital survey question elicited the additional response.
8. The computer-implemented method of claim 1 , wherein determining the relationship between the response and the unanswered digital survey question comprises:
generating a response vector representing the response attributes of the response and a set of response vectors representing response attributes of a set of responses;
determining distances between the response vector and each of the set of response vectors within a vector space;
determining, within the vector space, an additional response vector from the set of response vectors is closest to the response vector; and
determining the unanswered digital survey question elicited an additional response represented by the additional response vector.
9. The computer-implemented method of claim 1 , wherein:
receiving the response comprises receiving the freeform text in response to a digital survey question from among the plurality of digital survey questions;
determining the relationship between the response and the unanswered digital survey question comprises determining a similarity score between the digital survey question and the unanswered digital survey question satisfies a similarity threshold; and
modifying administration of the digital survey comprises excluding the unanswered digital survey question based on the similarity score satisfying the similarity threshold.
10. A non-transitory computer-readable medium comprising instructions that, when executed by at least one processor, cause a computing device to:
receive, from a respondent device, a response comprising freeform text, the response corresponding to a digital survey question from a plurality of digital survey questions associated with a digital survey;
analyze the freeform text to determine response attributes associated with the response;
determine, based on the response attributes, a relationship between the response and an unanswered digital survey question from the plurality of digital survey questions; and
based on the relationship between the response and the unanswered digital survey question, modifying administration of the digital survey to exclude the unanswered digital survey question from presentation on the respondent device.
11. The non-transitory computer-readable medium of claim 10 , further comprising instructions that, when executed by the at least one processor, cause the computing device to receive the response by identifying the freeform text in an electronic message or a post.
12. The non-transitory computer-readable medium of claim 10 , further comprising instructions that, when executed by the at least one processor, cause the computing device to modify the administration of the digital survey to customize the plurality of digital survey questions for the respondent device by excluding the unanswered digital survey question from the digital survey.
13. The non-transitory computer-readable medium of claim 10 , further comprising instructions that, when executed by the at least one processor, cause the computing device to:
determine, based on the response comprising the freeform text, a relationship between a respondent associated with the respondent device and at least one other respondent of a plurality of respondents; and
generate, for the respondent, a predicted response to the unanswered digital survey question based on the relationship between the respondent and the at least one other respondent.
14. The non-transitory computer-readable medium of claim 10 , further comprising instructions that, when executed by the at least one processor, cause the computing device to:
determine, based on the response attributes, an additional relationship between the response and an additional unanswered digital survey question from the plurality of digital survey questions; and
provide the additional unanswered digital survey question to the respondent device based on the additional relationship between the response and the additional unanswered digital survey question.
15. The non-transitory computer-readable medium of claim 14 , further comprising instructions that, when executed by the at least one processor, cause the computing device to determine the additional relationship between the response and the additional unanswered digital survey question by:
determining a relevance score for the additional unanswered digital survey question in relation to a respondent associated with the respondent device based on the response attributes; and
determining that the relevance score satisfies a relevance threshold.
16. A system comprising:
at least one processor; and
a non-transitory computer-readable medium comprising instructions that, when executed by the at least one processor, cause the system to:
receive, from a respondent device, a response comprising freeform text, the response corresponding to a digital survey question from a plurality of digital survey questions associated with a digital survey;
analyze the freeform text to determine response attributes associated with the response;
determine, based on the response attributes, a relationship between the response and an unanswered digital survey question from the plurality of digital survey questions; and
based on the relationship between the response and the unanswered digital survey question, modifying administration of the digital survey to exclude the unanswered digital survey question from presentation on the respondent device.
17. The system of claim 16 , further comprising instructions that, when executed by the at least one processor, cause the system to receive the response by identifying the freeform text in an electronic message or a post.
18. The system of claim 16 , further comprising instructions that, when executed by the at least one processor, cause the system to modify the administration of the digital survey to customize the plurality of digital survey questions for the respondent device by excluding the unanswered digital survey question from the digital survey.
19. The system of claim 16 , further comprising instructions that, when executed by the at least one processor, cause the system to:
determine, based on the response attributes, an additional relationship between the response and an additional unanswered digital survey question from the plurality of digital survey questions; and
provide the additional unanswered digital survey question to the respondent device based on the additional relationship between the response and the additional unanswered digital survey question.
20. The system of claim 19 , further comprising instructions that, when executed by the at least one processor, cause the system to determine the additional relationship between the response and the additional unanswered digital survey question by:
determining a relevance score for the additional unanswered digital survey question in relation to a respondent associated with the respondent device based on the response attributes; and
determining that the relevance score satisfies a relevance threshold.