Commercial Chatbot: Performance Evaluation, Usability Metrics and Quality Standards of Embodied Conversational Agents

2015 ◽  
Vol 2 (02) ◽  
pp. 1-16 ◽  
Author(s):  
Karolina Kuligowska
Author(s):  
Uday Kumar Adusumilli ◽  
Rajneesh Pandeya ◽  
Arvind Sebastian ◽  
Nanda Ashwin

A key goal of this paper is to investigate commercial applications for chatbots and propose several evaluation metrics for evaluating an embodied conversational agent's performance, usability, and overall quality. Our assessment is based on metrics that include a) size of market share & reach, b) range of users and c) likelihood of being the most advanced commercial chatbot created by their creators. Our study examines several aspects of the function of embodied conversational agents, including their visual appearance, implementation of web sites, speech synthesis unit, built-in knowledge base (with general and specialized information), presentation of knowledge and additional functionality, emergency responses in unexpected situations, and user ratings. An evaluation of any commercial chatbot deployment requires a multidimensional assessment and the current state of Conversational Intelligence in the commercial virtual assistant market.


2007 ◽  
Vol 8 (3) ◽  
pp. 391-410 ◽  
Author(s):  
Justine Cassell ◽  
Andrea Tartaro

What is the hallmark of success in human–agent interaction? In animation and robotics, many have concentrated on the looks of the agent — whether the appearance is realistic or lifelike. We present an alternative benchmark that lies in the dyad and not the agent alone: Does the agent’s behavior evoke intersubjectivity from the user? That is, in both conscious and unconscious communication, do users react to behaviorally realistic agents in the same way they react to other humans? Do users appear to attribute similar thoughts and actions? We discuss why we distinguish between appearance and behavior, why we use the benchmark of intersubjectivity, our methodology for applying this benchmark to embodied conversational agents (ECAs), and why we believe this benchmark should be applied to human–robot interaction.


2008 ◽  
Author(s):  
Markku Turunen ◽  
Jaakko Hakulinen ◽  
Cameron Smith ◽  
Daniel Charlton ◽  
Li Zhang ◽  
...  

2006 ◽  
Vol 6 ◽  
pp. 37-45
Author(s):  
Barbara Becker

The construction of embodied conversational agents – robots as well as avatars – seem to be a new challenge in the field of both cognitive AI and human-computer-interface development. On the one hand, one aims at gaining new insights in the development of cognition and communication by constructing intelligent, physical instantiated artefacts. On the other hand people are driven by the idea, that humanlike mechanical dialog-partners will have a positive effect on human-machine-communication. In this contribution I put for discussion whether the visions of scientist in this field are plausible and which problems might arise by the realization of such projects.


Sign in / Sign up

Export Citation Format

Share Document