BACK IN THE 1960S, I USED my MD degree to sneak into experimental biology laboratories and spent 4 decades learning how to perform and think about experiments under the guidance of scientists with Ph.D. degrees, sometimes helping Ph.D. students to learn the same skills. Those experiments prompted me to ask 2 questions. First, must the average biomedical Ph.D. student take more than 6 years to g...

In this report, the student presents her study on a multivariate visualization task. Specifically, the student would like to learn the use of Locally Linear Embedding (LLE) for visualization. While the experiment is using Wisconsin Breast Cancer dataset, the method is more generally applicable to other high-dimensional data as well. Three experiments were run to visualize the dataset. The three...

Numerous studies have shown the effectiveness of Intelligent Tutoring Systems in improving learning. However, there are still students who do not engage with problem solving and therefore miss opportunities for learning. In my project, I am investigating whether it is possible to predict when the student would abandon a problem, thus allowing the system to try to motivate the student to perseve...

In a controlled experiment using Comrade, a computer-supported peer review system, student reviewers offered feedback to student authors on their written analyses of a problem scenario. In each condition, reviewers received a different type of rating prompt: domain-related writing composition prompts or problem/issue specific prompts. We found that the reviewers were sensitive to the type of ra...

The class qusi-experiment was conducted to determine whether using scaffolding teaching strategy enhanced student understanding of statistics concepts for students enrolled in an introductory course. In this two-year longitudinal study, students received scaffolding intervention in experimental group and traditional teaching method in control group. In particular, learning effectiveness differe...

This paper presents a method to introduce the notion of a student selected difficulty level for the task of pronunciation learning of a second language. Three difficulty levels, novice, acceptable and native, are constructed using a tri-/biand unigram language model each using a specific set of broad phonetic groups determined using underspecification. The evaluation of the experiment is based ...

The effectiveness of a Navigation Agent has been evaluated, which determines a path through course material tailored to the individual student. Lesson selection by the agent showed an advantage for students who were unable to monitor their own learning process. Initiative by the agent --where the agent also chooses the moment for selecting another lesson-reduced the time needed to finish the ta...

In a controlled experiment using Comrade, a computer-supported peer review system, we explored whether a simple manipulation of the reviewing process could improve the reviewers’ understanding of an author’s essay topic and thus improve the quality of the reviews as well as the reviewer’s own subsequent draft. Student reviewers were randomly assigned either to an original-feedback condition, wh...

We present an experiment aimed at improving interpretation robustness of a tutorial dialogue system that relies on detailed semantic interpretation and dynamic natural language feedback generation. We show that we can improve overall interpretation quality by combining the output of a semantic interpreter with that of a statistical classifier trained on the subset of student utterances where se...

Computer-supported group formation enables educators to assign students to project teams. The focus in this paper is placed on gathering data about student attributes that are relevant in the context of specific course projects. We developed a method that automatically produces learner models from existing documents, by linking students to topics and estimating the levels of skill, knowledge, a...