Sebastian Gross

A Review of AI-Supported Tutoring Approaches for Learning Programming

In this paper, we review tutoring approaches of computer-supported systems for learning programming. From the survey we have learned three lessons. First, various AI-supported tutoring approaches have been developed and most existing systems use a feedback-based tutoring approach for supporting students. Second, the AI techniques deployed to support feedback-based tutoring approaches are able to identify the student’s intention, i.e. the solution strategy implemented in the student solution. Third, most reviewed tutoring approaches only support individual learning. In order to fill this research gap, we propose an approach to pair learning which supports two students who solve a programming problem face-to-face.

Example-based feedback provision using structured solution spaces

Intelligent tutoring systems (ITSs) typically rely on a formalised model of the underlying domain knowledge in order to provide feedback to learners adaptively to their needs. This approach implies two general drawbacks: the formalisation of a domain-specific model usually requires a huge effort, and in some domains it is not possible at all. In this paper, we propose feedback provision strategies in absence of a formalised domain model, motivated by example-based learning approaches. We demonstrate the feasibility and effectiveness of these strategies in several studies with experts and students. We discuss how, in a set of solutions, appropriate examples can be automatically identified and assigned to given student solutions via machine learning techniques in conjunction with an underlying dissimilarity metric. The plausibility of such an automatic selection is evaluated in an expert survey, while possible choices for domain-agnostic dissimilarity measures are tested in the context of real solution sets of Java programs. The quantitative evidence suggests that the proposed feedback strategies and automatic example assignment are viable in principle, further user studies in large-scale learning environments being the subject of future research.

Cluster based feedback provision strategies in intelligent tutoring systems

In this paper, we propose the use of machine learning techniques operating on sets of student solutions in order to automatically infer structure on these spaces. Feedback opportunities can then be derived from the clustered data. A validation of the approach based on data from a programming course confirmed the feasibility of the approach.

How to Select an Example? A Comparison of Selection Strategies in Example-Based Learning

In this paper, we investigate an Intelligent Tutoring System (ITS) for Java programming that implements an example-based learning approach. The approach does not require an explicit formalization of the domain knowledge but automatically identifies appropriate examples from a data set consisting of learners’ solution attempts and sample solution steps created by experts. In a field experiment conducted in an introductory course for Java programming, we examined four example selection strategies for selecting appropriate examples for feedback provision and analyzed how learners’ solution attempts changed depending on the selection strategy. The results indicate that solutions created by experts are more beneficial to support learning than solution attempts of other learners, and that examples modeling steps of problem solving are more appropriate for very beginners than complete sample solutions.

How Do Learners Behave in Help-Seeking When Given a Choice?

We describe the results of a study that investigated learners’ help-seeking behavior using two feedback options implemented in an ITS for Java programming. The 25 students had the choice between asking for feedback on errors in their programs and feedback on possible next steps in the solution process. We hypothesized that learners’ choices would depend on correctness of their programs and their progress in problem-solving. Surprisingly, this hypothesis was not confirmed.

Towards an Integrative Learning Environment for Java Programming

Learning programming can be a challenging task for students that not only requires them to acquire knowledge but also to make use of their knowledge in solving real-world problems. In this paper, we introduce an intelligent, adaptive and adaptable learning environment for Java programming called FIT Java Tutor. The learning environment integrates several pedagogical approaches in order to help learners learn programming considering individual needs. For testing purposes, we prepared a set of learning resources consisting of video tutorials, programming tasks, quizzes and multiple-choice tests, and deployed the learning system in an introductory programming class at Humboldt-Universitat zu Berlin. Based on experiences gained from this setup, we derived three research questions for investigation in future studies.

Learning Feedback in Intelligent Tutoring Systems

Intelligent Tutoring Systems (ITSs) are adaptive learning systems that aim to support learners by providing one-on-one individualized instruction. Typically, instructing learners in ITSs is build on formalized domain knowledge and, thus, the applicability is restricted to well-defined domains where knowledge about the domain being taught can be explicitly modeled. For ill-defined domains, human tutors still by far outperform the performance of ITSs, or the latter are not applicable at all. As part of the DFG priority programme “Autonomous Learning”, the FIT project has been conducted over a period of 3 years pursuing the goal to develop novel ITS methods, that are also applicable for ill-defined problems, based on implicit domain knowledge extracted from educational data sets. Here, machine learning techniques have been used to autonomously infer structures from given learning data (e.g., student solutions) and, based on these structures, to develop strategies for instructing learners.

Towards Providing Feedback to Students in Absence of Formalized Domain Models

In this paper, we propose the provision of feedback in Intelligent Tutoring Systems in absence of a formalized domain model. In a Wizard of Oz experiment, a human tutor gave feedback to students based on sample solutions applying two strategies which aimed to encourage learners’ self-reflection. We discuss possibilities to automate the methods of feedback provision using domain-independent proximity measures.

How to quantitatively compare data dissimilarities for unsupervised machine learning

For complex data sets, the pairwise similarity or dissimilarity of data often serves as the interface of the application scenario to the machine learning tool. Hence, the final result of training is severely influenced by the choice of the dissimilarity measure. While dissimilarity measures for supervised settings can eventually be compared by the classification error, the situation is less clear in unsupervised domains where a clear objective is lacking. The question occurs, how to compare dissimilarity measures and their influence on the final result in such cases. In this contribution, we propose to use a recent quantitative measure introduced in the context of unsupervised dimensionality reduction, to compare whether and on which scale dissimilarities coincide for an unsupervised learning task. Essentially, the measure evaluates in how far neighborhood relations are preserved if evaluated based on rankings, this way achieving a robustness of the measure against scaling of data. Apart from a global comparison, local versions allow to highlight regions of the data where two dissimilarity measures induce the same results.

Orientation and Navigation Support in Resource Spaces Using Hierarchical Visualizations

Abstract In this article we investigate how orientation and navigation in (extensive) spaces consisting of digital resources can be supported by using hierarchical visualizations. Such spaces can consist of heterogeneous sets of digital resources as for instance articles from Wikipedia, textbooks, and videos. Due to easier access to digital resources in the Internet age, a manual exploration of these spaces might lead to information overload. As a result, techniques need to be developed in order to automatically analyze and structure sets of resources. We introduce a prototypical implementation of a visualization pipeline that extracts information dimensions from resources in order to group them into semantically similar clusters, and visualizes these clusters using two different visualizations: a treemap visualizing clusters and nested subclusters, and a rooted tree visualizing groups of semantically similar resources as subtrees. In a lab study we evaluated the two visualizations and compared them to two control groups. The results may hint to users’ better understanding of the resources’ underlying knowledge as compared to using typical approaches (e.g. web search results as list) when using hierarchical visualizations.