Abstract

In building intelligent tutoring systems, it is critical to be able to understand and diagnose student responses in interactive problem solving. However, building this understanding into a computer-based intelligent tutor is a time-intensive process usually conducted by subject experts. Much of this time is spent in building production rules that model all the ways a student might solve a problem. In our prior work, we proposed a novel application of Markov decision processes (MDPs) 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 for students at any point in a given problem. Our past results indicated that extracted MDPs and our proposed hint-generating functions will be able to provide hints over 80% of the time. Our results also indicated that we can provide valuable tradeoffs between hint specificity and the amount of data used to create an MDP. (Contains 12 tables and 1 figure.)

Citation

Barnes, T. & Stamper, J. (2010). Automatic Hint Generation for Logic Proof Tutoring Using Historical Data. Journal of Educational Technology & Society, 13(1), 3-12. Retrieved August 8, 2024 from https://www.learntechlib.org/p/75238/.

This record was imported from ERIC on April 19, 2013. [Original Record]

ERIC is sponsored by the Institute of Education Sciences (IES) of the U.S. Department of Education.

Copyright for this record is held by the content creator. For more details see ERIC's copyright policy.

Keywords

• Computer Assisted Instruction
• Data Processing
• decision making
• Experiments
• Feedback (Response)
• higher education
• intelligent tutoring systems
• Logical Thinking
• models
• Pattern Recognition
• Probability
• problem solving
• Student Reaction
• tutoring
• tutors