{"id":717,"date":"2021-05-13T20:18:12","date_gmt":"2021-05-13T20:18:12","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/?post_type=pattern&p=717"},"modified":"2023-10-25T07:41:45","modified_gmt":"2023-10-25T14:41:45","slug":"g15-b-request-explicit-feedback-on-selected-system-outputs","status":"publish","type":"pattern","link":"https:\/\/www.microsoft.com\/en-us\/haxtoolkit\/pattern\/g15-b-request-explicit-feedback-on-selected-system-outputs\/","title":{"rendered":"Pattern 15B: Request explicit feedback on selected system outputs"},"content":{"rendered":"\n\n
User feedback is needed to assess the system and help it improve over time.<\/p>\n\n\n\n
Implement a user-feedback mechanism that occasionally asks the user to provide explicit feedback for selected items or instances of system outputs. The system initiates the feedback interaction.<\/p>\n\n\n\n
Leverage user feedback for:<\/p>\n\n\n\n
Decide what type of feedback to collect from the user. Options include:<\/p>\n\n\n\n
Ensure the information collected is both meaningful to the user and can be leveraged for system improvement.<\/p>\n\n\n\n
Design a mechanism for proactively requesting system-initiated feedback for specific system outputs, items, or instances.<\/p>\n\n\n\n
Determine how often to request user feedback and whether to request feedback from all users or from groups of users on a rotating basis.<\/p>\n\n\n\n
Consider how to convey to the user that the feedback was received, how it will be used, and whether the user experience changes immediately after giving feedback (see Guideline 16, Convey the consequences of user actions<\/em><\/a>).<\/p>\n\n\n\n Leverage the user feedback data as a metric of system performance (e.g., to evaluate output correctness, utility).<\/p>\n\n\n\n Leverage the user feedback data for system training by working with an AI\/ML expert to decide what the model can learn from the feedback and how to integrate this data into the model\u2019s training.<\/p>\n\n\n\n For open-ended feedback that may not be machine-interpretable, put a process in place for interpreting and using the feedback to improve the system.<\/p>\n\n\n\n Consider how to convey to the user that the feedback was received, how it will be used, and whether the user experience changes immediately after giving feedback (see Guideline 16<\/a>).<\/p>\n\n\n\nUser benefits<\/h4>\n\n\n\n