Event-Triggered Microsurvey System for Real-Time User Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional survey methods are inefficient in reaching a representative user base and timing, and manual thematic analysis is difficult to automate, with existing automated techniques failing to achieve the granularity of manual analysis.
Innovation Solution
A real-time survey system that monitors user interactions and event data to dynamically select and administer microsurveys based on user attributes and event triggers, using machine learning for automatic thematic analysis of freeform text responses.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If traditional survey methods (email blasts or immediate surveys of all eligible users) are used, then surveys can be sent to a large number of users, but the efficiency in reaching an optimal, desired, or representative set of users deteriorates
Solution Approach 1:
The system pre-defines multiple survey templates with different topics, questions, and target audience criteria before deployment. These templates are prepared in advance with associated event triggers and user segmentation rules, enabling rapid deployment of targeted surveys without manual configuration at survey time.
Solution Approach 2:
The survey system dynamically selects and delivers appropriate survey templates to users based on real-time event data and user attributes. The system adapts survey delivery by monitoring user actions, device information, and contextual signals to determine which users receive which surveys at which moments, optimizing representativeness and relevance.
2Quantity of substance
If traditional survey methods are used, then surveys can be distributed broadly, but the timing proximate to the event or action the survey is asking about deteriorates
Solution Approach 1:
Survey templates are pre-configured with event trigger conditions and timing parameters before deployment. The system prepares multiple survey versions with different trigger events (e.g., app launch, feature usage, error occurrence) so that when a triggering event occurs, the appropriate survey is immediately delivered without delay.
Solution Approach 2:
The system continuously monitors user actions, device events, and contextual data in real-time to detect triggering events. When a relevant event occurs (such as a user performing a specific action or encountering an issue), the system automatically delivers the corresponding survey at that moment, ensuring timing proximity to the relevant event while maintaining broad distribution capability.
3Reliability
If the number of surveys sent out is increased to improve service, then user feedback quality improves, but user annoyance increases
Solution Approach 1:
The system segments users into different groups based on device attributes, user behavior patterns, and event contexts. Each segment receives customized survey templates relevant to their specific situation rather than generic surveys. This segmentation allows the system to send more surveys overall while maintaining lower annoyance per user by ensuring each survey is highly relevant.
Solution Approach 2:
The system delivers different survey templates with different questions, lengths, and topics to different users based on their specific context, device type, and triggered events. For example, mobile users might receive shorter surveys while desktop users receive more detailed ones, or users who just experienced a bug receive technical troubleshooting surveys while general users receive feature feedback surveys.
4Measurement precision
If manual thematic analysis is used, then granular thematic insights can be achieved, but automation difficulty increases
Solution Approach 1:
The system introduces an intermediary processing layer that automatically extracts and structures key information from free-form survey responses. This intermediary layer uses natural language processing to identify themes, sentiments, and actionable insights, then formats them into structured data that can be automatically analyzed and reported, bridging the gap between manual analysis quality and automated efficiency.
Data Source
AI summary
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.