Amy Soller

Computational Modeling and Analysis of Knowledge Sharing in Collaborative Distance Learning

This research aims to support collaborative distance learners by demonstrating how a probabilistic machine learning method can be used to model and analyze online knowledge sharing interactions. The approach applies Hidden Markov Models and Multidimensional Scaling to analyze and assess sequences of coded online student interaction. These analysis techniques were used to train a system to dynamically recognize (1) when students are having trouble learning the new concepts they share with each other, and (2) why they are having trouble. The results of this research may assist an instructor or intelligent coach in understanding and mediating situations in which groups of students collaborate to share their knowledge.

Developing a framework for integrating prior problem solving and knowledge sharing histories of a group to predict future group performance

Using a combination of machine learning probabilistic tools, we have shown that some chemistry students fail to develop productive problem solving strategies through practice alone and will require interventions to continue making strategic progress. One particularly useful form of intervention was face-to-face collaborative learning which increased the overall solution rate of the problem solving while also improving the strategies used. However, the collaborative intervention was not effective for all groups making complicated. To better model the effects of group composition we have developed a synchronous and symmetrical collaborative extension to the online IMMEX problem solving environment. This online collaborative environment appeared an accurate representation of the face-to-face collaboration episode in that both groupings showed similar gains in the problem solution frequency as well as in the differential use of particular strategies. We also noticed that some groups, like some individuals, rapidly developed and persisted with unproductive approaches highlighting the importance of identifying, and perhaps re-assembling such groups for subsequent problem solving. To support such decisions, we describe a causal model approach for integrating the performance and knowledge sharing histories of a group to help predict which groups should remain together

Preface to the special issue on user modeling to support groups, communities and collaboration

Technology should support and enhanceour ability towork, learn, andmakedecisions. These activities naturally involve collaboration and communication, yet the personal computers we use to carry them out are traditionally individualized. This special issue addresses the design and extension of adaptive individual user technology to support complex collaborative processes involving information sharing, communication, and collaborative group work. Recent integration efforts have successfully combined collaborative and communication services with multi-user tools to create environments that enable individuals to communicate and share information. Examples of such environments include computer-supported collaborative workspaces, distributed learning management systems, online communities of interest, and peer-to-peer systems. While these environments enable collaboration, they provide no guarantee that timely productive collaboration occurs and proceeds effectively. Such assurance requires more substantial effort in understanding how the collaboration process is shaped by the individuals’ characteristics, behaviors, and relationships, and how to support their dynamic interaction. Models of groups, collaboration, and communities collect and structure the

Workshop on Applications of Semantic Web Technologies for E-learning

SW-EL’04 will focus on issues related to using concepts, ontologies and semantic web technologies to build e-learning applications. It follows the successful workshop on Concepts and Ontologies in Web-based Educational Systems, held in conjunctions with ICCE’2002 in Auckland, New Zealand. Due to the great interest, the 2004 edition of the workshop will be organized in three sessions held at three different conferences. The aim is to discuss the current problems in e-learning from different perspectives, including those of web-based intelligent tutoring systems and adaptive hypermedia courseware, and the implications of applying semantic web standards and technologies for solving them.

Workshop on Designing Computational Models of Collaborative Learning Interaction

During collaborative learning activities, factors such as students’ prior knowledge, motivation,roles, language, behavior and interaction dynamics interact with each other in unpredictable ways, making it very difficult to predict and measure learning effects. This may be one reason why the focus of collaborative learning research shifted in the nineties from studying group characteristics and products to studying group process. With an interest in having an impact on the group process in modern distance learning environments, the focus has recently shifted again – this time from studying group processes to identifying computational strategies that positively influence group learning. This shift toward mediating and supporting collaborative learners is fundamentally grounded in our understanding of the interaction described by our models of collaborative learning interaction. In this workshop, we will explore the advantages, implications, and support possibilities afforded by the various types of computational models of collaborative learning processes.