Supporting the Guide on the SIDE

We present SIDE1 (the Summarization Integrated Development Environment), which is an infrastructure that facilitates the construction of reporting interfaces that support group learning facilitators in the task of getting a quick sense of the quality and effectiveness of a collaborative learning interaction. The SIDE framework offers flexibility in the specification of which conversational behavior to take note of as well as how noted behavior should be reported to instructors, making it a valuable research tool. It is said that a facilitator of effective collaborative learning should be a “guide on the side” rather than a “sage on the stage”. In classrooms, instructors roam around the room, listen to conversations, and jump in at key moments to offer guidance. In online settings, group learning facilitators are responsible for a larger number of groups. Listening in on conversations involves reading a high volume of text based chat, often paired with data streams in other modalities such as a digital whiteboard. The challenge is to enable group learning facilitators to quickly get a sense of the collaborative interaction so his resources can be strategically invested. In this poster, we present SIDE (the Summarization Integrated Development Environment), an infrastructure that supports group learning facilitators in quickly getting a sense of the quality and effectiveness of a collaborative learning interaction so that the instructor is better equipped to carry out this challenging task. It has been found that effective learning in collaborative groups is linked to the process by which learners work on the task together, how they construct arguments, and how they build on the contributions of their learning partners, otherwise known as transactivity. Earlier research suggests that it is more effective to judge the quality of an interaction for learning when transactivity based conversational contributions are flagged [2]. The goal of our proposed reporting interface is to track these qualities of collaborative discourse as is becoming more practical because of projects such as TagHelper tools [1] that are capable of automatic collaborative learning process analysis. However, investigating the patterns of conversational behavior that are most indicative of the quality of an interaction or indicative of trouble in an interaction, is still an active area of research. Open questions related to which types of information 1 This research was supported by Office of Naval Research, Cognitive and Neural Sciences Division, grant N00014-05-1-0043.