You are looking at a platform that generates automated responses to questions about fraud risks in humanitarian contexts.
The purpose of this study is to understand how you perceive the usefulness, clarity and quality of the responses produced by the tool we are developing.
Please note that this is not a test of your knowledge and there are no right or wrong answers. We are interested in your honest reaction as a (potential) user.
The questionnaire includes 30 questions, and for each one you will see two responses.
Your task is to read both responses and decide which one you think is more useful, or if they are equally good or bad.
A useful answer is one that helps you understand the issue or take appropriate action. It should answer the question directly, provide accurate and relevant information, include enough detail to satisfy the request, be clear and easy to understand, and avoid unsupported or misleading claims.
When making your choice, please consider:
You will then select from a list the criterion or criteria that best explain your choice.
You will also be able to add a few words explaining your choice. Written comments are optional, but are the most valuable feedback you can give us to improve the tool. Even a short note will help us a lot!
Do not reward unnecessary length. Do not penalize concise answers if they are useful and fully answer the question. Penalize unsupported claims, evasiveness, unnecessary verbosity, and failure to follow instructions.
Your progress saves automatically, so you can stop and resume at a later time using the same username. When you're done, you may optionally leave overall feedback at the bottom.
Your feedback is anonymized and used only to improve the responses going forward.
* indicates a mandatory field
data/ and check
config.json, then restart the server.