An official website of the United States government
Learning to derive subgoals reduces the gap between experts and students and prepares students for future problem solving. This paper explores a training strategy using backward worked examples (BWE) and backward problem solving (BPS) within an intelligent logic tutor to support backward strategy learning, with analysis of student experience, performance, and proof construction. Results show that students trained with both BWE and BPS outperform those receiving none or only BWE, demonstrating more efficient subgoal derivation.
more »
« less
In the proceeding of 24th International Conference OF Artificial Intelligence in Education (AIED)
Humans adopt various problem-solving strategies depending on their mastery level, problem type, and complexity. Many of these problem-solving strategies have been integrated within intelligent problem-solvers to solve structured and complex problems efficiently. One such strategy is the means-ends analysis which involves comparing the goal and the givens of a problem and iteratively setting up subgoal(s) at each step until the subgoal(s) are straightforward to derive from the givens. However, little is known about the impact of explicitly teaching novices such a strategy for structured problem-solving with tutors. In this study, we teach novices a subgoal-directed problem-solving strategy inspired by means-ends analysis using a problem-based training intervention within an intelligent logic-proof tutor. As we analyzed students’ performance and problem-solving approaches after training, we observed that the students who learned the strategy used it more when solving new problems, constructed optimal logic proofs, and outperformed those who did not learn the strategy.
more »
« less
- Award ID(s):
- 2013502
- PAR ID:
- 10525848
- Publisher / Repository:
- Springer
- Date Published:
- Format(s):
- Medium: X
- Location:
- In the proceeding of 24th International Conference OF Artificial Intelligence in Education (AIED)
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The assistance dilemma is a well-recognized challenge to determine when and how to provide help during problem solving in intelligent tutoring systems. This dilemma is particularly challenging to address in domains such as logic proofs, where problems can be solved in a variety of ways. In this study, we investigate two data-driven techniques to address the when and how of the assistance dilemma, combining a model that predicts \textit{when} students need help learning efficient strategies, and hints that suggest \textit{what} subgoal to achieve. We conduct a study assessing the impact of the new pedagogical policy against a control policy without these adaptive components. We found empirical evidence which suggests that showing subgoals in training problems upon predictions of the model helped the students who needed it most and improved test performance when compared to their control peers. Our key findings include significantly fewer steps in posttest problem solutions for students with low prior proficiency and significantly reduced help avoidance for all students in training.more » « less
-
Problem decomposition into sub-problems or subgoals and recomposition of the solutions to the subgoals into one complete solution is a common strategy to reduce difficulties in structured problem solving. In this study, we use a datadriven graph-mining-based method to decompose historical student solutions of logic-proof problems into Chunks. We design a new problem type where we present these chunks in a Parsons Problem fashion and asked students to reconstruct the complete solution from the chunks. We incorporated these problems within an intelligent logic tutor and called them Chunky Parsons Problems (CPP). These problems demonstrate the process of problem decomposition to students and require them to pay attention to the decomposed solution while they reconstruct the complete solution. The aim of introducing CPP was to improve students’ problem-solving skills and performance by improving their decomposition-recomposition skills without significantly increasing training difficulty. Our analysis showed that CPPs could be as easy as Worked Examples (WE). And, students who received CPP with simple explanations attached to the chunks had marginally higher scores than those who received CPPs without explanation or did not receive them. Also, the normalized learning gain of these students shifted more towards the positive side than other students. Finally, as we looked into their proof-construction traces in posttest problems, we observed them to form identifiable chunks aligned with those found in historical solutions with higher efficiency.more » « less
-
null (Ed.)Subgoal labels are function-based instructional explanations that describe the problem-solving steps to the learner, highlighting the solution process. There is strong evidence that the use of subgoal labels within worked examples improves student learning in other STEM fields. Initial research shows that using subgoal labels within computer science improves student learning, but this has only been tested using a single programming concept (indefinite loops) with text-based programming languages. The proposers are currently expanding subgoal labels to the main programming concepts taught in an introductory programming course using an imperative programming language. In this BOF we seek to uncover tacit knowledge that programming instructors have in order to develop instructional materials that bridge the gap between students, who are CS novices, and instructors, who are CS experts, to improve learning for students who are under-prepared for or struggle in CS1. We will be seeking feedback on the selection of programming topics to be covered, the defined subgoals for those topics and the worked examples created for instructional purposes.more » « less
-
Free-body diagrams (FBDs) are diagrammatic representations of external forces and moments exerted on an object of interest for solving kinetics problems. Several studies have reported different ways of teaching FBDs in terms of pictorial representation of forces (e.g., placement of vectors or labeling). However, there is little research on practice strategies for helping students learn how to draw FBDs. Through the use of task analysis and a model of subgoal learning, we will develop task-analysis-guided deliberate practice to enhance learning. Task analysis is often used in instructional design to extract knowledge requirements for acquiring a skill. Skill acquisition is usually divided into three phases including declarative, knowledge compilation, and procedural. Task analysis in our study will identify relevant declarative and procedural knowledge related to drawing FBDs. The findings will be used to develop deliberate practice. Deliberate practice can help novices develop good representations of the knowledge needed to produce superior problem solving performance. This has been viewed as a gold standard for practice. Although deliberate practice is mainly studied among elite performers, the recent literature has revealed promising results for novices. Considering cognitive capacity limitations, we will apply cognitive load theory to develop deliberate practice to help students build declarative and procedural knowledge without exceeding their working memory limitations. A knowledge extraction expert will take an iterative approach to conduct task analyses with a subject matter expert (or experts)to distill knowledge to a level that is appropriate for students in the dynamics course. We will then integrate the task analysis results with instructional design strategies derived from cognitive load theory and the subgoal learning model to develop deliberate practice and assessment materials. Examples and assessment results will be provided to evaluate the effectiveness of the instructional design strategies as well as the challenges.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Conference Proceeding:
- The DOI is not currently available.
