Erin Walker

Creating cognitive tutors for collaborative learning: steps toward realization

Our long-term research goal is to provide cognitive tutoring of collaboration within a collaborative software environment. This is a challenging goal, as intelligent tutors have traditionally focused on cognitive skills, rather than on the skills necessary to collaborate successfully. In this paper, we describe progress we have made toward this goal. Our first step was to devise a process known as bootstrapping novice data (BND), in which student problem-solving actions are collected and used to begin the development of a tutor. Next, we implemented BND by integrating a collaborative software tool, Cool Modes, with software designed to develop cognitive tutors (i.e., the cognitive tutor authoring tools). Our initial implementation of BND provides a means to directly capture data as a foundation for a collaboration tutor but does not yet fully support tutoring. Our next step was to perform two exploratory studies in which dyads of students used our integrated BND software to collaborate in solving modeling tasks. The data collected from these studies led us to identify five dimensions of collaborative and problem-solving behavior that point to the need for abstraction of student actions to better recognize, analyze, and provide feedback on collaboration. We also interviewed a domain expert who provided evidence for the advantage of bootstrapping over manual creation of a collaboration tutor. We discuss plans to use these analyses to inform and extend our tools so that we can eventually reach our goal of tutoring collaboration.

Designing Automated Adaptive Support to Improve Student Helping Behaviors in a Peer Tutoring Activity

Adaptive collaborative learning support systems analyze student collaboration as it occurs and provide targeted assistance to the collaborators. Too little is known about how to design adaptive support to have a positive effect on interaction and learning. We investigated this problem in a reciprocal peer tutoring scenario, where two students take turns tutoring each other, so that both may benefit from giving help. We used a social design process to generate three principles for adaptive collaboration assistance. Following these principles, we designed adaptive assistance for improving peer tutor help-giving, and deployed it in a classroom, comparing it to traditional fixed support. We found that the assistance improved the conceptual content of help and the use of interface features. We qualitatively examined how each design principle contributed to the effect, finding that peer tutors responded best to assistance that made them feel accountable for help they gave.

CTRL: A research framework for providing adaptive collaborative learning support

There is evidence suggesting that providing adaptive assistance to collaborative interactions might be a good way of improving the effectiveness of collaborative activities. In this paper, we introduce the Collaborative Tutoring Research Lab (CTRL), a research-oriented framework for adaptive collaborative learning support that enables researchers to combine different types of adaptive support, particularly by using domain-specific models as input to domain-general components in order to create more complex tutoring functionality. Additionally, the framework allows researchers to implement comparison conditions by making it easier to vary single factors of the adaptive intervention. We evaluated CTRL by designing adaptive and fixed support for a peer tutoring setting, and instantiating the framework using those two collaborative scenarios and an individual tutoring scenario. As part of the implementation, we integrated pre-existing components from the Cognitive Tutor Algebra (CTA) with custom-built components. The three conditions were then compared in a controlled classroom study, and the results helped us to contribute to learning sciences research in peer tutoring. CTRL can be generalized to other collaborative scenarios, but the ease of implementation relates to the complexity of the existing components used. CTRL as a framework has yielded a full implementation of an adaptive support system and a controlled evaluation in the classroom.

Cognitive tutoring of collaboration: developmental and empirical steps towards realization

In this paper, we describe developmental and empirical steps we have taken toward providing Cognitive Tutoring to students within a collaborative software environment. We have taken two important steps toward realizing this goal. First, we have integrated a collaborative software tool, Cool Modes, with software designed to develop Cognitive Tutors (the Cognitive Tutor Authoring Tool). Our initial integration does not provide tutoring per se but rather acts as a means to capture data that provides the beginnings of a tutor for collaboration. Second, we have performed an initial study in which dyads of students used our software to collaborate in solving a classification / composition problem. This study uncovered five dimensions of analysis that our approach must use to help us better understand student collaborative behavior and lead to the eventual development of a Cognitive Tutor for collaboration. We discuss our plans to incorporate such analysis into our approach and to run further studies.

To Tutor the Tutor: Adaptive Domain Support for Peer Tutoring

The effectiveness of intelligent tutoring systems at increasing learning might be improved if the systems were combined with collaborative activities that encouraged conceptual elaboration. We extended the Cognitive Tutor Algebra, an intelligent tutoring system for high-school mathematics, with a peer tutoring activity that was designed to encourage interaction, reflection, and accountability. Two types of domain support were provided: adaptive support, which used the intelligent tutor domain models to provide feedback to the peer tutor, and fixed support, which simply consisted of answers to the problems. We compared the two peer tutoring conditions (adaptive or fixed support) to individual use of the cognitive tutor (without peer-tutoring activities). Even though students in the individual condition solved more problems during instruction, we did not find significant differences between the individual and collaborative conditions on learning. However, we found a correlation between tutee impasses and tutor learning.

Beyond explicit feedback: new directions in adaptive collaborative learning support

Adaptive collaborative learning support (ACLS) may be better than fixed forms of support at increasing learning from collaboration. While much existing adaptive assistance has focused on providing explicit feedback directly to the relevant student, we propose a two-dimensional design space which explores alternative methods of adaptive assistance that are implicit, indirect, or both. We investigated the viability of these ideas using data collected in a classroom evaluation of an ACLS system for peer tutoring which incorporated the design ideas in a manner that provided cognitive support to peer tutors. In this paper, we discuss how students interacted with the different forms of feedback, and propose a second iteration of the assistance that involves collaborative support in addition to domain support.

Modeling Helping Behavior in an Intelligent Tutor for Peer Tutoring

Giving effective help is an important collaborative skill that leads to improved learning for both the help-giver and help-receiver. Adding intelligent tutoring to student interaction may be one effective way of assisting students in giving and receiving better help. However, such systems have proven difficult to implement, in part due to the challenges of modeling productive dialogue in a collaborative activity. We present a theoretical model of good helping behavior in a peer tutoring context, and validate the model using student tutoring data, linking optimal and buggy behaviors to learning outcomes. We discuss the implications of the model with respect to providing intelligent tutoring for peer tutoring.

Cognitive tutors as research platforms: extending an established tutoring system for collaborative and metacognitive experimentation

Cognitive tutors have been shown to increase student learning in long-term classroom studies but would become even more effective if they provided collaborative support and metacognitive tutoring. Reconceptualizing an established tutoring system as a research platform to test different collaborative and metacognitive interventions would lead to gains in learning research. In this paper, we define a component-based architecture for such a platform, drawing from previous theoretical frameworks for tutoring systems. We then describe two practical implementation challenges not typically addressed by these frameworks. We detail our efforts to extend a cognitive tutor and evaluate our progress in terms of flexibility, control, and practicality.

Planning with Action Abstraction and Plan Decomposition Hierarchies

Useful and suitable action representations, with accompanying planning algorithms are crucial for the task performance of many agent systems, and thus a core issue of research on intelligent agents. An efficient and expressive representation of actions and plans can allow planning systems to retrieve relevant knowledge faster and to access and use suitable actions more effectively. Two general approaches have been pursued in the past; STRIPS-based planners, which construct plans from scratch, based on primitive action descriptions and planners using pre-defined Plan Decompositions Hierarchies, also known as Hierarchical Task Networks. In our research, we integrated both an inheritance hierarchy of actions, using STRIPS-like action descriptions, with a plan decomposition hierarchy, which consists of pre-defined plan schemata. This combination is suitable for a richer action and plan representation, and thus an improved planning algorithm. We implemented and tested this approach for a prototypical example application: the travel planning domain.

Using problem-solving context to assess help quality in computer-mediated peer tutoring

Collaborative activities, like peer tutoring, can be beneficial for student learning, but only when students are supported in interacting effectively. Constructing intelligent tutors for collaborating students may be an improvement over fixed forms of support that do not adapt to student behaviors. We have developed an intelligent tutor to improve the help that peer tutors give to peer tutees by encouraging them to explain tutee errors and to provide more conceptual help. The intelligent tutor must be able to classify the type of peer tutor utterance (is it next step help, error feedback, both, or neither?) and the quality (does it contain conceptual content?). We use two techniques to improve automated classification of student utterances: incorporating domain context, and incorporating students self-classifications of their chat actions. The domain context and self-classifications together significantly improve classification of student dialogue over a baseline classifier for help type. Using domain features alone significantly improves classification over baseline for conceptual content.