Toward Automatic Hint Generation for Logic Proof Tutoring Using Historical Student Data

@inproceedings{Barnes2008TowardAH,
  title={Toward Automatic Hint Generation for Logic Proof Tutoring Using Historical Student Data},
  author={Tiffany Barnes and John C. Stamper},
  booktitle={Intelligent Tutoring Systems},
  year={2008}
}
We have proposed a novel application of Markov decision processes (MDPs), a reinforcement learning technique, to automatically generate hints for an intelligent tutor that learns. We demonstrate the feasibility of this approach by extracting MDPs from four semesters of student solutions in a logic proof tutor, and calculating the probability that we will be able to generate hints at any point in a given problem. Our results indicate that extracted MDPs and our proposed hint-generating functions… 
A pilot study on logic proof tutoring using hints generated from historical student data
TLDR
The results of the pilot study using Deep Thought with the Hint Factory demonstrate that hints generated from historical data can support students in writing logic proofs.
Unsupervised MDP Value Selection for Automating ITS Capabilities.
TLDR
A novel method for assigning prior values to student work that depends only on frequency of occurrence for the component steps is proposed, and the results show that the utility metric outperforms a classic MDP solution in selecting hints in logic.
An Improved Data-Driven Hint Selection Algorithm for Probability Tutors
TLDR
A novel hint-selection algorithm for coherent derivational domains, such as probability, which addresses this problem by searching a frontier of viable, partially matching student states by providing higher value hints to students in unknown states.
Experimental Evaluation of Automatic Hint Generation for a Logic Tutor
TLDR
This work augmented the Deep Thought logic tutor with a Hint Factory that generates data-driven, context-specific hints for an existing computer aided instructional tool, and shows that hints help students persist in a deductive logic proofs tutor.
Enhancing the Automatic Generation of Hints with Expert Seeding
TLDR
This paper describes the use of expert sample solutions to "seed" the hint generation process, and shows that just a few expert solutions give significant coverage (over 50%) for hints.
Autonomously Generating Hints by Inferring Problem Solving Policies
TLDR
This paper autonomously generate hints for the Code.org `Hour of Code,' (which is to the best of the authors' knowledge the largest online course to date) using historical student data, and discovers that this statistic is highly predictive of a student's future success.
Automatic Generation of Deductive Logic Proof Problems
TLDR
This work aims to automatically generate proofs for deductive logic proofs in such a way that fulfills the parameters set by the instructors, while using the progress recorded to generate further questions specific to the individual student.
Effects of Automatically Generated Hints on Time in a Logic Tutor
TLDR
This work explores the effects of using automatically generated hints in Deep Thought, a propositional logic tutor, and finds a consistent trend in which students without hints spent more time on problems when compared to students that were provided hints.
Generating Data-driven Hints for Open-ended Programming
TLDR
A new data-driven algorithm is presented, based on the Hint Factory, to generate hints for open-ended programming assignments, that can provide hints that successfully lead students to solutions from any state, help students achieve assignment objectives, and align with the student’s future solution.
Data-Driven Hint Generation in Vast Solution Spaces: a Self-Improving Python Programming Tutor
TLDR
The results show that ITAP is capable of producing hints for almost any given state after being given only a single reference solution, and that it can improve its performance by collecting data over time.
...
...

References

SHOWING 1-10 OF 18 REFERENCES
Toward the extraction of production rules for solving logic proofs
TLDR
This work proposes a novel application of Markov decision processes (MDPs), a reinforcement learning technique, to automatically extract production rules for an intelligent tutor that learns, and demonstrates the feasibility of this approach by extracting MDPs from student solutions in a logic proof tutor, and using these to analyze and visualize student work.
Towards an Intelligent Tutoring System for Propositional Proof Construction
TLDR
Two project goals are addressed here: identifying at-risk students at an early stage in the semester, and generating a visual representation of student proof efforts as a step toward understanding those efforts.
Opening the Door to Non-programmers: Authoring Intelligent Tutor Behavior by Demonstration
TLDR
A method and set of software tools that ease the process of cognitive task analysis and tutor development by allowing the author to demonstrate, instead of programming, the behavior of an intelligent tutor without requiring AI programming are described.
ADVISOR: A Machine Learning Architecture for Intelligent Tutor Construction
TLDR
ADVISOR, a two-agent machine learning architecture for intelligent tutoring systems (ITS), is constructed to centralize the reasoning of an ITS into a single component to allow customization of teaching goals and to simplify improving the ITS.
Bootstrapping Novice Data: Semi-Automated Tutor Authoring Using Student Log Files
TLDR
A potentially powerful way to aid in the authoring of intelligent tutoring systems is to directly leverage student interaction log data to directly construct an initial tutoring system model.
A Comparative Analysis of Cognitive Tutoring and Constraint-Based Modeling
TLDR
This paper compares Cognitive Tutoring to Constraint-Based Modeling (CBM) and argues the differences are often more apparent than real: for specific domains one approach may be favoured over the other, making them viable complementary methods for supporting learning.
Authoring Intelligent Tutoring Systems: An analysis of the state of the art
TLDR
An in-depth summary and analysis of the research and development state of the art for intelligent tutoring system (ITS) authoring systems and the major unknowns and bottlenecks to having widespread use of ITS authoring tools.
Effective Feedback Content for Tutoring Complex Skills
TLDR
Results of a study using the Geometry Tutor for building geometry proofs found that feedback about the goal structure of geometry problems led to better performance than Feedback about the reasons for error or than simply being told that an error had occurred.
Reinforcement Learning: An Introduction
TLDR
This book provides a clear and simple account of the key ideas and algorithms of reinforcement learning, which ranges from the history of the field's intellectual foundations to the most recent developments and applications.
Introduction to Reinforcement Learning
TLDR
In Reinforcement Learning, Richard Sutton and Andrew Barto provide a clear and simple account of the key ideas and algorithms of reinforcement learning.
...
...