Event-triggered microsurvey customization and delivery system
A real-time survey system can monitor real-time event and interaction data generated as a user interacts with an application. Using the event data in combination with static user attributes, the survey system can identify a subset of microsurveys a user is eligible to receive or participate in. Identifying eligibility can include applying one or more filters based on user attributes as well as detecting a triggering event that signals real-time relevance of the survey to the user's actions. If the user is eligible for multiple surveys, the survey system can select a single survey to send to the user. Surveys can be presented to users directly using the real-time survey system instead of via an alternate delivery method, such as email. After collecting survey data, survey system can automatically analyze survey responses, including by performing machine learning based thematic analysis on freeform text responses.
1. A method comprising:
generating a set of training data comprising historical survey responses each labeled with a response topic and a response intent;
training a neural network to identify topics and intents of survey responses from users using the generated set of training data;
monitoring, in real-time, interactions by a user with an application running on a user device;
determining one or more characteristics of the user;
querying a microsurvey database using the determined one or more characteristics of the user to identify a subset of microsurveys the user is eligible to receive, each of the identified subset of microsurveys corresponding to a trigger constraint;
querying the identified subset of microsurveys with a monitored interaction to identify a second subset of microsurveys corresponding to trigger constraints satisfied by the monitored interaction;
selecting a microsurvey from the second subset of microsurveys based on a sampling rate of each of the second subset of microsurveys;
modifying an interface of the application running on the user device to include the selected microsurvey, the display of the selected microsurvey comprising an interactive graphical element that, upon completion of the microsurvey by the user, is configured to modify the interface of the application to remove the selected microsurvey; and
applying the neural network to a response to the microsurvey from the user to identify a set of topics and a set of intents associated with the response.
2. The method of claim 1 , further comprising:
responsive to modifying the interface of the application to include the selected microsurvey for display, collecting a result of the microsurvey comprising one or more question responses.
3. The method of claim 2 , further comprising:
aggregating the result of the microsurvey with a plurality of other microsurvey results;
analyzing the set of microsurvey results using thematic analysis; and
grouping the microsurvey results based on theme based on the thematic analysis.
4. The method of claim 3 , further comprising:
transmitting the grouped set of microsurvey results to an online system associated with the application.
5. The method of claim 1 , wherein selecting a microsurvey from the second subset of microsurveys comprises:
applying a leaky bucket algorithm to select a microsurvey from the second subset of microsurveys.
6. The method of claim 1 , wherein the leaky bucket algorithm is a cross-leaky bucket algorithm.
7. The method of claim 1 , wherein selecting a microsurvey from the second subset of microsurveys comprises:
selecting a time within the user's session of the application to display the microsurvey.
8. A non-transitory computer-readable storage medium comprising instructions which, when executed by a processor, cause the processor to perform the steps of:
generating a set of training data comprising historical survey responses each labeled with a response topic and a response intent;
training a neural network to identify topics and intents of survey responses from users using the generated set of training data;
monitoring, in real-time, interactions by a user with an application running on a user device;
determining one or more characteristics of the user;
querying a microsurvey database using the determined one or more characteristics of the user to identify a subset of microsurveys the user is eligible to receive, each of the identified subset of microsurveys corresponding to a trigger constraint;
querying the identified subset of microsurveys with a monitored interaction to identify a second subset of microsurveys corresponding to trigger constraints satisfied by the monitored interaction;
selecting a microsurvey from the second subset of microsurveys based on a sampling rate of each of the second subset of microsurveys;
modifying an interface of the application running on the user device to include the selected microsurvey, the display of the selected microsurvey comprising an interactive graphical element that, upon completion of the microsurvey by the user, is configured to modify the interface of the application to remove the selected microsurvey; and
applying the neural network to a response to the microsurvey from the user to identify a set of topics and a set of intents associated with the response.
9. The non-transitory computer-readable storage medium of claim 8 , wherein the steps further comprise:
responsive to modifying the interface of the application to include the selected microsurvey for display, collecting a result of the microsurvey comprising one or more question responses.
10. The non-transitory computer-readable storage medium of claim 9 , wherein the steps further comprise:
aggregating the result of the microsurvey with a plurality of other microsurvey results;
analyzing the set of microsurvey results using thematic analysis; and
grouping the microsurvey results based on theme based on the thematic analysis.
11. The non-transitory computer-readable storage medium of claim 10 , wherein the steps further comprise:
transmitting the grouped set of microsurvey results to an online system associated with the application.
12. The non-transitory computer-readable storage medium of claim 8 , wherein selecting a microsurvey from the second subset of microsurveys comprises:
applying a leaky bucket algorithm to select a microsurvey from the second subset of microsurveys.
13. The non-transitory computer-readable storage medium of claim 8 , wherein the leaky bucket algorithm is a cross-leaky bucket algorithm.
14. The non-transitory computer-readable storage medium of claim 8 , wherein selecting a microsurvey from the second subset of microsurveys comprises:
selecting a time within the user's session of the application to display the microsurvey.
15. A method comprising:
collecting, by a network device, interaction data relating to interactions by a user with an application running on a user device and user data relating to characteristics of the user;
comparing, by the network device, the collected interaction data and the collected user data to trigger constraints associated with each of a set of microsurveys within a microsurvey database; and
collecting, by the network device, additional interaction data when the collected interaction data and collected user data satisfy the trigger constraints of a microsurvey, the additional interaction data comprising interactions by the user with the microsurvey when an interface of the application running on the user device is modified to display the microsurvey.
16. The method of claim 15 , further comprising:
aggregating the additional interaction data;
analyzing the collected additional interaction data using thematic analysis to identify a set of themes of the additional interaction data.
17. The method of claim 15 , wherein comparing the collected interaction data and the collected user data to trigger constraints associated with each of a set of comprises:
applying a leaky bucket algorithm to select a microsurvey from the set of microsurveys.
18. The method of claim 16 , wherein the leaky bucket algorithm is a cross-leaky bucket algorithm.