A pedagogic conversational agent (PCA) can be defined as a computer system that interacts with the student in natural language assuming the role of the instructor, a student or a companion. It can have a personality and can generate different sentences according to the agent or the student mood. Empathy with the students' feelings seems to increase their motivation to study. However, the influence of the agent personality and role as well as the students' opinion is still unclear. Therefore, in this article, it is explored with the help of a field experiment, for the first time, how these factors can affect the interaction of children with PCAs, and their opinions according to an anonymous and voluntary opinion questionnaire and some personal interviews.

Willow is a free-text Adaptive Computer Assisted Assessment system, which supports natural language processing and user modeling. In this paper we discuss the benefits coming from extending Willow with recommendations. The approach combines human computer interaction methods to elicit the recommendations with data mining techniques to adjust their definition. Following a scenario-based approach, 12 recommendations were designed and delivered in a large scale evaluation with 377 learners. A statistically significant positive impact was found on indicators dealing with the engagement in the course, the learning effectiveness and efficiency, as well as the knowledge acquisition. We present the overall system functionality, the interaction among the different subsystems involved and some evaluation findings.

Willow is a Web-based application which automatically and adaptively assesses students' free-text answers written in Spanish and English. It is intended to help students review concepts outside of class, and provides an alternative assessment method. However, students tend to be greatly concerned by computer generated scores and, although they have been told that the system is not intended for summativepurposes and their teachers will not have access to that scores, they remain worried that the machine could make a mistake and this mistake could have a negative impact on their final course grade. Given that automatic scoring cannot assure 100% approximation to a human teacher's assessment, we have introduced self-assessment features in Willow. Thanks to the combination of automatic free-text scoring and self-assessment, students have more control over their evaluation and, whenever they do not agree with the automatic score assigned by the system, they can change it. This new feature has been tested by 22 students reviewing a course with Willow in the 2007-2008 academic year. We observed that the students did not abuse the self-assessment feature, only modifying the score assigned in 5% of answered questions.