Loading...
Paper Type
Complete
Description
With advances in computing and a preference for convenience in completing digital tasks, conversational agents (CAs) have gained widespread popularity throughout the world. However, most of the CAs seem to lack several necessary capabilities to satisfy the users’ needs. Our study focused on text-based CAs (also known as chatbots) and examines the factors associated with their performance. The literature on IS success and adoption suggest that various factors related to the technology, users, and tasks can jointly play a role in satisfying user needs. Thus, we adopt a holistic approach to evaluating chatbot performance by identifying chatbot attributes, user attributes, and task attributes and their impact on chatbot performance from the users’ view. We conducted interviews with chatbot users and using a qualitative approach, provide a theoretical framework for chatbot performance evaluation. All the interviews were conducted with the users of rule-based chatbots as these are widely used by all sizes of organizations.
Paper Number
1405
Recommended Citation
Khan, Abdul Kader and Palvia, Prashant, "Toward Identifying the Factors Associated with Conversational Agents’ Performance" (2023). AMCIS 2023 Proceedings. 6.
https://aisel.aisnet.org/amcis2023/sig_aiaa/sig_aiaa/6
Toward Identifying the Factors Associated with Conversational Agents’ Performance
With advances in computing and a preference for convenience in completing digital tasks, conversational agents (CAs) have gained widespread popularity throughout the world. However, most of the CAs seem to lack several necessary capabilities to satisfy the users’ needs. Our study focused on text-based CAs (also known as chatbots) and examines the factors associated with their performance. The literature on IS success and adoption suggest that various factors related to the technology, users, and tasks can jointly play a role in satisfying user needs. Thus, we adopt a holistic approach to evaluating chatbot performance by identifying chatbot attributes, user attributes, and task attributes and their impact on chatbot performance from the users’ view. We conducted interviews with chatbot users and using a qualitative approach, provide a theoretical framework for chatbot performance evaluation. All the interviews were conducted with the users of rule-based chatbots as these are widely used by all sizes of organizations.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.
Comments
SIG AIAA