Thousands of students enroll in Massive Open Online Courses~(MOOCs) to seek opportunities for learning and self-improvement. However, the learning process often involves struggles with confusion, which may have an adverse effect on the course participation experience, leading to dropout along the way. In this paper, we quantify that effect. We describe a classification model using discussion forum behavior and clickstream data to automatically identify posts that express confusion. We then apply survival analysis to quantify the impact of confusion on student dropout. The results demonstrate that the more confusion students express or are exposed to, the lower the probability of their retention. Receiving support and resolution of confusion helps mitigate this effect. We explore the differential effects of confusion expressed in different contexts and related to different aspects of courses. We conclude with implications for design of interventions towards improving the retention of students in MOOCs.

The unique social presence of robots can be leveraged in learning situations to reduce student evaluation anxiety, while still providing instructional guidance on multiple levels of communication. Furthermore, social role of the instructor can also impact the prevalence of evaluation apprehension. In this study, we examine how human and robot social role affects help-seeking behaviors and learning outcomes in a one-on-one tutoring setting. Our results show that help-seeking is a moderator of the significant relationship between condition and learning, with the "human teacher" condition resulting in significantly less learning (and marginally less help-seeking) than the "human assistant" and both robot conditions.

The arrival of a new interest-sharing network, So.cl, provides for a new opportunity to explore human behavior as it relates to constructing public contributions and receiving community response. This study looks at archival data in order to better understand how types of shared content receive interaction from others. The results suggest that a So.cl user should include more photos and less links on their post to increase the quantity of likes and comments the community gives to the post, among other discoveries.

With over 13.3 million children living below poverty line in the United States, there is a pressing need for engaging HCI research with children at the socio-economic margins. Drawing from design studio culture and art therapy literature, we explore wearable computing as a creative and tangible medium (similar to markers, paints, clays, etc.) for motivating 'at-risk' children in hands-on making and expressive instantiation of ideas. Working with a local outreach organization for 'at-risk' middle school girls, we conducted five weekly workshops during which participants ideated, designed and implemented personal wearable computing projects. These sessions inspired participants (age 10-12) who tend to be uninterested and uncooperative in educational activities to complete interactive projects and engage with workshop volunteers as mentors and peers. We present the challenges, merits and outcomes of our approach, proposing wearable computing as a healing outlet and a mentoring strategy for at-risk children.

We present the results of a study in which we contrast alternative forms of collaborative learning support in the midst of a collaborative design task in which students negotiate between increasing power and increasing environmental friendliness. Our research question is whether interactive instructional support in collaborative learning environments is more effective when it is offered as solicited or unsolicited help. The finding from our classroom study is that dialogue-based support is more effective in this collaborative context when invitations for help in the form of pointer hints are offered automatically, but dialogue agents are only provided when the invitation is explicitly accepted.

This poster describes a controlled study that examines how individual motivation orientations affect computer-supported collaborative learning (CSCL) activities with an adaptive thermodynamics dialogue tutor. Our results show that motivation orientation has an effect on perceptions of one's learning partner, and possibly one's self-confidence.

Cognitive Tutors have been shown to lead to impressive improvement in student learning in a range of domains, including middle school mathematics. Most Cognitive Tutors focus on providing learning support for tasks involving problem solving. They typically emphasize facilitating the acquisition of procedural knowledge, on the assumption that the acquisition of conceptual knowledge will be supported outside the tutor through classroom activities or an accompanying textbook. Many researchers agree that expertise in a domain involves not just procedural knowledge, but also conceptual knowledge, as well as tight interconnections between the two. In order to provide two types of knowledge instruction within the same Intelligent Tutoring System, we are now building a novel type of Cognitive Tutor to bridge the existing gap between teaching conceptual and procedural instruction with the same educational software.