WP 7 Evaluation

Background (NBU)
The Central and Eastern Center for Cognitive Science has long history of usability reports. An evaluation and experimentation plan for assessing the usability of RASCALLI applications has been prepared and is going to be used when assessing the RASCALLI applications.

Standards (NBU)
In order to complain to usability standards, the ECA should meet the following requirements:
Learnability, ease of use. The interaction with the ECA should be easy to learn, should be easy and should happen in a natural way. The user should be able to start working with the agent rapidly.
Efficiency. The agent should enable the tasks to be completed in a timely and effective manner.
Errors. There should be a minimum number of errors occurring while interacting with the ECA.
Satisfaction. The interaction should be pleasant and the users should like the agent. The goal is the users to be subjectively satisfied while interacting with the agent and to want to spend time with the agent.

Assessment (NBU)
Those requirements are assessed by using all kinds of communication between the user and RASCALLI: nonverbal behavior like gestures, facial displays and gaze behavior and its conversational abilities. On the other hand, the system is going to be assessed by the impact it makes on the user: ease of working with the system, quality of interaction, usefullness of the agent, percieved personal characteristics of the agent, liking of the agent and finally - satisfaction of the user of the interaction between him/her and the agent.

Back to workpackages

RASCALLI is supported by the European Commission Cognitive Systems Programme (IST-27596-2004).


RASCALLI develops a new type of personalized cognitive agents, the Rascalli, that live and learn on the Internet.

Rascalli combine Internet-based perception, action, reasoning, learning, and communication.

Rascalli come into existence by creation through the user. The users not only create their Rascalli but also train them to fulfil specific tasks, such as be experts in a quiz game or assist the user in a music portal.