Jennifer K. Olsen

Using an Intelligent Tutoring System to Support Collaborative as well as Individual Learning

Collaborative learning has been shown to be beneficial for older students, but there has not been much research to show if these results transfer to elementary school students. In addition, collaborative and individual modes of instruction may be better for acquiring different types of knowledge. Collaborative Intelligent Tutoring Systems (ITS) provide a platform that may be able to provide both the cognitive and collaborative support that students need. This paper presents a study comparing collaborative and individual methods while receiving instruction on either procedural or conceptual knowledge. The collaborative groups had the same learning gains as the individual groups in both the procedural and conceptual learning conditions but were able to do so with fewer problems. This work indicates that by embedding collaboration scripts in ITSs, collaborative learning can be an effective instructional method even with young children.

Authoring Tools for Collaborative Intelligent Tutoring System Environments.

Authoring tools have been shown to decrease the amount of time and resources needed for the development of Intelligent Tutoring Systems (ITSs). Although collaborative learning has been shown to be beneficial to learning, most of the current authoring tools do not support the development of collaborative ITSs. In this paper, we discuss an extension to the Cognitive Tutor Authoring Tools to allow for development of collaborative ITSs through multiple synchronized tutor engines. Using this tool, an author can combine collaboration with the type of problem solving support typically offered by an ITS. Different phases of collaboration scripts can be tied to particular problem states in a flexible, problem-specific way. We illustrate the tool’s capabilities by presenting examples of collaborative tutors used in recent studies that showed learning gains. The work is a step forward in blending computer-supported collaborative learning and ITS technologies in an effort to combine their strengths.

Intelligent Tutoring Systems for Collaborative Learning: Enhancements to Authoring Tools

Collaborative and individual instruction may support different types of knowledge. Optimal instruction for a subject domain may therefore need to combine these two modes of instruction. There has not been much research, however, on combining individual and collaborative learning with Intelligent Tutoring Systems (ITSs). A first step is to expand ITSs for collaborative learning. This paper investigates the expansion of the Cognitive Tutor Authoring Tools to include collaborative components for example-tracing tutors. The tools were enhanced to support flexible use of collaboration scripts so different learning goals can be supported. We introduce the collaboration features supported and describe an initial pilot study using the new features in a fractions ITS.

Mailing Archived Emails as Postcards: Probing the Value of Virtual Collections

People accumulate huge assortments of virtual possessions, but it is not yet clear how systems and system designers can help people make meaning from these large archives. Early research in HCI has suggested that people generally appear to value their virtual things less than their material things, but theory on material possessions does not entirely explain this difference. To investigate if changes to the form and behavior of virtual things may surface valued elements of a virtual archive, we designed a technology probe that selected snippets from old emails and mailed them as physical postcards to participating households. The probe uncovered features of emails that trigger meaningful reflection, and how contextual information can help people engage in reminiscence. Our study revealed insights about how materializing virtual possessions influences factors shaping how people draw on, understand, and value those possessions. We conclude with implication and strategies for aimed at supporting people in having more meaningful interactions and experiences with their virtual possessions.

Adapting Collaboration Dialogue in Response to Intelligent Tutoring System Feedback

To be able to provide better support for collaborative learning in Intelligent Tutoring Systems, it is important to understand how collaboration patterns change. Prior work has looked at the interdependencies between utterances and the change of dialogue over time, but it has not addressed how dialogue changes during a lesson, an analysis that allows us to investigate the adaptivity of student strategies as students gain domain knowledge. We address this question by analyzing the shift in types of collaborative talk occurring within a single session and in particular how they relate to errors for 26 4th and 5th grade dyads working on a fractions tutor. We found that, over time, the frequency of interactive talk and errors both decrease in dyads working together on conceptual problems. Although interactive talk is often held as a gold standard in collaboration, as students become more proficient, it may not be as important.

Toward Combining Individual and Collaborative Learning Within an Intelligent Tutoring System

Collaborative and individual learning appear to have complementary strengths; however, the best way to combine these learning methods is still unclear. While previous work has demonstrated the effectiveness of Intelligent Tutoring Systems (ITSs) for individual learning, collaborative learning with ITSs is much less frequent – especially for young students. In this paper, we discuss our prior and future work with elementary school students that aims to investigate how to best combine individual and collaborative learning using their complementary strengths within an ITS. Our previous findings demonstrate that ITSs are able to support collaboration, as well as individual learning, for this population. In addition, we propose future research to understand how to best combine individual and collaborative learning within an ITS.

Exploring Causality Within Collaborative Problem Solving Using Eye-Tracking.

When students are working collaboratively and communicating verbally in a technology enhanced environment, the system is not aware of what collaboration is happening outside of the technology, making it difficult to adapt the system to better support the collaboration of the students. In this paper, we analyze the causal relationships between collaborative and individual gaze measures and the influence that the students dialogue, prior knowledge, or success has on these relationships to find indicators that can be used within an adaptive system. We found that when students are discussing concrete aspects of the problem, the causal relationship between their eye gaze measures changes compared to other types of dialogue patterns. The results also show a clear difference in causal relations when the pairs with high prior knowledge or success are compared with the pairs with low prior knowledge or success. Collaborative gaze causes the individual gaze for pairs with high prior knowledge and the opposite for the pairs with low prior knowledge.

Exploring Dual Eye Tracking as a Tool to Assess Collaboration

In working towards unraveling the mechanisms of productive collab- orative learning, dual eye tracking, a method where two peoples eyes are tracked as they collaborate on a task, is a potentially helpful tool to identify moments when students are collaborating effectively. However, we are only beginning to understand how eye gaze relates to effective collaborative learning and how it fits in with other data streams. In this paper, we present three broad areas of analysis where we believe dual eye tracking will promote our under- standing of collaborative learning. These areas are: (a) How eye gaze is associ- ated with other communication measures, (b) how eye gaze is associated with task features, and (c) how eye gaze relates to learning outcomes. We present exploratory analyses in each of the three areas using a dataset of 28 4 th and 5 th grade dyads working on an Intelligent Tutoring System for fractions. Our anal- yses illustrate how dual eye tracking could be used in conjunction with other data streams to assess collaborative learning.