This work proposes Dynamic Linear Epsilon-Greedy, a novel contextual multi-armed bandit algorithm that can adaptively assign personalized content to users while enabling unbiased statistical analysis. Traditional A/B testing and reinforcement learning approaches have trade-offs between empirical investigation and maximal impact on users. Our…

Systematic classroom observation is often used in evaluating and enhancing the quality of classroom instruction. However, classroom observation can potentially suffer from human bias. In addition, the traditional classroom observation is too expensive for resource-constrained environments (e.g., Sub-Saharan Africa, South and Central Asia). A…

Transactive discussion during collaborative learning is crucial for building on each other's reasoning and developing problem solving strategies. In a tabletop collaborative learning activity, student actions on the interface can drive their thinking and be used to ground discussions, thus affecting their problem-solving performance and learning.…

This paper demonstrates how to apply Machine Learning (ML) techniques to analyze student interaction data collected in an online mathematics game. We examined: (1) how different ML algorithms influenced the precision of middle-school students' (N = 359) performance prediction; and (2) what types of in-game features were associated with student…

The use of technology as a facilitator in learning environments has become increasingly prevalent with the global pandemic caused by COVID-19. As such, computer-supported collaborative learning (CSCL) gains a wider adoption in contrast to traditional learning methods. At the same time, the need for automated tools capable of assessing and…

We explore the effectiveness of a simple algorithm for adaptively deciding whether to further decompose a step in a line of reasoning during tutorial dialogue. We compare two versions of a tutorial dialogue system, Rimac: one that always decomposes a step to its simplest sub-steps and one that adaptively decides to decompose a step based on a…

Previous findings from the study within which this research is located had uncovered students' approaches to learning in the context of a second year chemical engineering course. Using an analysis of students' reflections on their experience, the study has shown the existence of three approaches to learning in this context: an 'information-based'…

This paper describes an investigation of problem sequencing as part of a symposium presenting theoretical concerns and research findings regarding several diverse types of strategies for designing and presenting instructional materials. The first step involved analyzing a set of problems, to determine the knowledge (rules) required for solving the…

Fourteen third graders were given numerical computation and division-with-remainder (DWR) problems both before and after they were taught the division algorithm in classrooms. Their solutions were examined. The results show that students' initial acquisition of the division algorithm did improve their performance in numerical division computations…

The concept of an algorithm derives from the physical sciences, but it has often been misunderstood and misapplied in the social sciences and in education. The theoretical and practical significance of algorithms stems from their applicability to problems of learning, instruction, and instructional design, and they may potentially provide the…

Online information retrieval is pervasive and its development in libraries is accelerating. Within the near future, most college and research libraries will provide direct access to their patrons to vast information resources via CD-ROMs, locally mounted databases, and gateways. The computer terminal and the "frame" of information it…

This paper describes an approach to instruction and learning processes in professional training schools using microcomputers and computer assisted instruction (CAI). It is argued that the use of computers in education changes existing approaches to teaching and learning by focusing on the structure of the information being taught, the organization…

The central objective of this study was to determine the effects of formal training in the use and types of questions and in the nature and use of algorithms on middle school students' achievement in economic geography. Subjects were 190 eighth grade students in a large metropolitan school district. Three experimental groups received either: (1)…

Higher order cognitive development and success in the study of high school mathematics and science require an understanding of rational number concepts and facility with proportional reasoning and computation. Proportional reasoning is an essential schema for developing formal operational thought. This study involving 16 ninth-grade students was…