Frank Linton

Recommender Systems for Learning: Building User and Expert Models through Long-Term Observation of Application Use

Information technology has recently become the medium in which much professional office work is performed. This change offers an unprecedented opportunity to observe and record exactly how that work is performed. We describe our observation and logging processes and present an overview of the results of our long-term observations of a number of users of one desktop application. We then present our method of providing individualized instruction to each user by employing a new kind of user model and a new kind of expert model. The user model is based on observing the individuals behavior in a natural environment, while the expert model is based on pooling the knowledge of numerous individuals. Individualized instructional topics are selected by comparing an individuals knowledge to the pooled knowledge of her peers.

Promoting Effective Peer Interaction in an Intelligent Collaborative Learning System

Placing students in a group and assigning them a task does not guarantee that the students will engage in effective collaborative learning behavior. The collaborative learning model described in this paper identifies the specific characteristics exhibited by effective collaborative learning teams, and based on these characteristics, suggests strategies for promoting effective peer interaction. The model is designed to help an intelligent collaborative learning system recognize and target group interaction problem areas. Once targeted, the system can take actions to help students collaborate more effectively with their peers, maximizing individual student and group learning.

Building user and expert models by long-term observation of application usage

We describe a new kind of user model and a new kind of expert model and show how these models can be used to individualize the selection of instructional topics. The new user model is based on observing the individual’s behavior in a natural environment over a long period of time, while the new expert model is based on pooling the knowledge of numerous individuals. Individualized instructional topics are selected by comparing an individual’s knowledge to the pooled knowledge of her peers.

Using Dialogue Features to Predict Trouble During Collaborative Learning

A web-based, collaborative distance-learning system that will allow groups of students to interact with each other remotely and with an intelligent electronic agent that will aid them in their learning has the potential for improving on-line learning. The agent would follow the discussion and interact with the participants when it detects learning trouble of some sort, such as confusion about the problem they are working on or a participant who is dominating the discussion or not interacting with the other participants. In order to recognize problems in the dialogue, we investigated conversational elements that can be utilized as predictors for effective and ineffective interaction between human students. These elements can serve as the basis for student and group models. In this paper, we discuss group interaction during collaborative learning, our representation of participant dialogue, and the statistical models we are using to determine the role being played by a participant at any point in the dialogue and the effectiveness of the group. We also describe student and group models that can be built using conversational elements and discuss one set that we built to illustrate their potential value in collaborative learning.

Embedded Training for Complex Information Systems

One solution to providing affordable operator training in the workplace is to augment applications with intelligent embedded training systems. Intelligent embedded training is highly interactive: trainees practice problem-solving tasks on the prime application with guidance and feedback from the training system. We group the necessary assistance mechanisms into three layers: (1) an application interface layer, (2) an action interpretation layer, and (3) a training services layer. We discuss these layers, their interactions, and our prototype implementation of each one.

Towards intelligent agents for collaborative learning: recognizing the roles of dialogue participants

Our goal is to build and evaluate a web-based, collaborative distance-learning system that will allow groups of students to interact with each other remotely and with an intelligent agent that will aid them in their learning. The agent will follow the discussion and interact when it detects learning trouble of some sort, such as confusion about the problem they are working on or a participant who is dominating the discussion or not interacting with the other participants. In order to recognize problems in the dialogue, we are first examining the role that a participant is playing as the dialogue progresses. In this paper we discuss group interaction during collaborative learning, our representation of participant roles, and the statistical model we are using to determine the role being played by a participant at any point in the dialogue.

Encouraging Student Reflection and Articulation Using a Learning Companion: A Commentary.

Our 1998 paper “Encouraging Student Reflection and Articulation using a Learning Companion” (Goodman et al. 1998) was a stepping stone in the progression of learning companions for intelligent tutoring systems (ITS). A simulated learning companion, acting as a peer in an intelligent tutoring environment ensures the availability of a collaborator and encourages the student to learn collaboratively, while drawing upon the instructional advantages that ITSs provide. This paper is a commentary on our 1998 paper, reflecting on that research and some of the subsequent relevant research by others and us since then in Learning Companions, Intelligent Tutoring Systems, and Collaborative Learning.

Promoting the organization-wide learning of application software

This paper describes the characteristics of a system designed to promote one sort of organizational learning (Senge, 1990), in particular, to enhance the organization-wide learning of application software (note 1). The system presented here will (1) capture evolving expertise from a community of practice (Lave & Wenger 1991), (2) support less-skilled members of the community in acquiring that expertise, and (3) serve as an organizational memory for the expertise it captures. One version of the system has been partially implemented for a software engineering environment (Linton, 1990).In many workplaces … mastery is in short supply and what is required is a kind of collaborative bootstrapping of expertise. (Eales & Welch, 1995, p. 100)The main goal of the design is to continuously improve the performance of application users by providing individualized coaching based on the automated comparison of user logs to expert models. The system discussed here would be suitable for situations in which the following assumptions are true:(1) People who hold similar jobs and perform similar tasks have similar software usage patterns, e.g., managers use spreadsheet financial functions when preparing budgets, researchers use multiple views of the text when preparing journal articles, and salespeople use standard request forms when making travel arrangements.(2) Some people systematically make better use of their applications than others.(3) Everyone benefits when employees become optimal users of their application software (note 2).The fundamental requirement of the envisioned system is the capability to log the software usage patterns of a large number of individuals. Networked PC computing has recently made this logging requirement practical.

Accelerating workplace learning

We propose a new approach for instructional technology: workplace learning tools. These tools are embedded in the information technology environment of the workplace and are based on constructivist learning theories. Learning with these tools feels quite different from learning in a conventional setting. Our approach was inspired by three tools prototyped in a systems engineering organisation. The tools are designed to accelerate learning in the workplace. One tool gives application users feedback that fills the gaps and extends the boundaries of their knowledge. Another tool gives information consumers pointers to intranet URLs which their peers find valuable. A third tool finds experts based on their intranet publications. A fourth tool, based on the perspective these tools have inspired, will elicit tacit knowledge by encouraging reflection on the value of ones previous actions; once elicited, the knowledge will be made available to all for future use.

CHI 99 SIG: automated data collection for evaluating collaborative systems

The purpose of this CHI 99 Special Interest Group (SIG) session was to share lessons learned about using automated logging techniques to collect data for evaluating collaborative (multi-user) systems. Automated logging techniques are frequently used in evaluating the human-computer interaction of single-user systems. There has been much less experience in using logging techniques for evaluating collaborative systems, thus prompting the SIG proposal. We discussed issues surrounding using logging systems, methods, and metrics to collect data that are useful for evaluating collaborative systems.