Designing Conversational Evaluation Tools

Conversational agents (CAs) provide opportunities for improving the interaction in evaluation surveys. To investigate if and how a user-centered conversational tool impacts users' response quality their experience, we build EVA - novel course educational scenarios. In field experiment with 128 students, compared against static web survey. Our results confirm prior findings from literature about positive effect of tools domain education. Second, then differences between voice-based text-based human-computer same experimental set-up. Against our expectation, students answered higher information but lower quantity to modality. indicate that using CA (voice text-based) user experience survey interface.