SolveDeep: A System for Supporting Subgoal Learning in Online Math Problem Solving

Learner-driven subgoal labeling helps learners form a hierarchical structure of solutions with subgoals, which are conceptual units of procedural problem solving. While learning with such hierarchical structure of a solution in mind is effective in learning problem solving strategies, the development of an interactive feedback system to support subgoal labeling tasks at scale requires significant expert efforts, making learner-driven subgoal labeling difficult to be applied in online learning environments. We propose SolveDeep, a system that provides feedback on learner solutions with peer-generated subgoals. SolveDeep utilizes a learnersourcing workflow to generate the hierarchical representation of possible solutions, and uses a graph-alignment algorithm to generate a solution graph by merging the populated solution structures, which are then used to generate feedback on future learners' solutions. We conducted a user study with 7 participants to evaluate the efficacy of our system. Participants did subgoal learning with two math problems and rated the usefulness of system feedback. The average rating was 4.86 out of 7 (1: Not useful, 7: Useful), and the system could successfully construct a hierarchical structure of solutions with learnersourced subgoal labels.

[1]  Neil T. Heffernan,et al.  AXIS: Generating Explanations at Scale with Learnersourcing and Machine Learning , 2016, L@S.

[2]  Christus,et al.  A General Method Applicable to the Search for Similarities in the Amino Acid Sequence of Two Proteins , 2022 .

[3]  Richard Catrambone,et al.  Aiding subgoal learning: Effects on transfer. , 1995 .

[4]  R. Catrambone.  The subgoal learning model: Creating better examples so that students can solve novel problems. , 1998 .

[5]  Juho Kim,et al.  Improving learning with collective learner activity , 2015 .

[6]  Krzysztof Z. Gajos,et al.  Learnersourcing Subgoal Labels for How-to Videos , 2015, CSCW.

[7]  R. Catrambone.  Generalizing Solution Procedures Learned From Examples , 1996 .

[8]  T. Sørensen,et al.  A method of establishing group of equal amplitude in plant sociobiology based on similarity of species content and its application to analyses of the vegetation on Danish commons , 1948 .

[9]  Andrew Olney,et al.  Authoring Intelligent Tutoring Systems Using Human Computation: Designing for Intrinsic Motivation , 2015, HCI.

[10]  Juho Kim,et al.  ConceptScape: Collaborative Concept Mapping for Video Learning , 2018, CHI.

[11]  Mark Guzdial,et al.  Subgoal-labeled instructional material improves performance and transfer in learning to develop mobile applications , 2012, ICER '12.

[12]  Richard Catrambone,et al.  Improving problem solving performance in computer-based learning environments through subgoal labels , 2014, L@S.

[13]  Mark Guzdial,et al.  Subgoals, Context, and Worked Examples in Learning Computing Problem Solving , 2015, ICER.

[14]  K. Holyoak,et al.  Learning subgoals and methods for solving probability problems , 1990, Memory & cognition.