Percent agree is an estimate of the percentage of participants that would agree with a particular response.
We compute these scores, using a machine learning model called collaborative filtering, from the voting activities the participants complete after submitting their own responses.
There are currently two types of exercises that participants complete:
- Agree/Disagree
- Binary Choice
The agree/disagree exercise presents the participant with a single response that was submitted by someone in the audience and prompts them to select if they agree or disagree with that response. This exercise gives us an absolute baseline of what a participant does or doesn’t agree with.
The binary choice exercise presents the participant with two responses that were submitted by individuals in the group and prompts them to select the response they prefer more. This exercise provides a relative signal of agreement or disagreement between the responses which assists in a relative ranking of responses.
- NOTE: Participants have the first 80% of the Ask Opinion time to respond. If they don't respond in that time, their responses will be automatically submitted. Then the participants will move into voting exercises.