University of Twente Student Theses
Artificial Intelligence Conversational Agents : Using Card Sorting To Revaluate The Validity Of The Chatbot Usability Scale
Ordelman, Amber (2022) Artificial Intelligence Conversational Agents : Using Card Sorting To Revaluate The Validity Of The Chatbot Usability Scale.
|
PDF
867kB |
| Abstract: | This research aims to further validate the Chatbot Usability Scale (BUS-11). The scale is revaluated in this research by testing its validity from a different angle, namely the face and construct validity. Moreover, in this study it is tested whether trust might affect the mental models of participants. To gain insight into the mental models of participants, a closed card sorting test was conducted. In order to check for the face and construct validity of the scale, heatmaps and item-level agreement matrixes were generated and then analysed. Additional heatmaps and an item-level agreement matrix were created considering the trust levels of the participants. Moreover, to quantitively test the possible effect of trust on card sorting an Kruskal-Wallis test was performed. The results of this research show that the mental models of participants appear to be in line with the expected item organization and the factorial structure of BUS-11. In addition, the previously found correlation between factor 2 and factor 3 of BUS-11 is also well reflected in the results of the card sorting. Moreover, trust appears to not have a significant effect on the mental models of the participants. |
| Item Type: | Essay (Bachelor) |
| Faculty: | BMS: Behavioural, Management and Social Sciences |
| Subject: | 77 psychology |
| Programme: | Psychology BSc (56604) |
| Link to this item: | https://purl.utwente.nl/essays/91464 |
| Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Show download statistics for this publication
Show download statistics for this publicationRepository Staff Only: item control page