University of Twente Student Theses


Inclusion vs exclusion oriented clarifying questions for conversational product search

Ignat, R. (2023) Inclusion vs exclusion oriented clarifying questions for conversational product search.

[img] PDF
Abstract:Standard product search techniques such as faceted search are commonly employed in today’s systems. Even though widely used, they come with several limitations, such as not being able to understand users’ natural language. Therefore, other search methods like conversational search became a topic of interest to the scientific community. As conversational product search systems such as product advisors become more prevalent, the question of what the benefits and drawbacks of different approaches are arises. There is existing work discussing different types of clarifying questions or various frameworks such as critiquing. Typically, these questions aim to find an acceptable range of values. However, research on the benefits and drawbacks of asking clarifying questions that seek to exclude rather than include certain values is scarce. This research employed a qualitative user study in which we explored the advantages and disadvantages of inclusion-oriented and exclusion-oriented clarifying questions. Our findings suggest that exclusion-based questions are found to be harder to answer and are perceived more negatively, but can be useful for asking categorical questions in situations where it is likely for users to have “dealbreakers”.
Item Type:Essay (Bachelor)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:54 computer science
Programme:Computer Science BSc (56964)
Link to this item:
Export this item as:BibTeX
HTML Citation
Reference Manager


Repository Staff Only: item control page