Addressing student misinterpretations of story problems in MAST

Abstract

Story problems are of ultimate importance of mathematics. This stems from the fact that they help improve various students' skills including reading the story problem, extracting the embedded mathematical information and the unknown quantity to compute, and applying the correct mathematical operators to solve the problem. Unfortunately, this type of problems may suffer from misinterpretation errors and errors due to overlooking some embedded information regardless of the proficiency of the students in mathematics. This paper introduces the Math Story Problem Tutor (MAST), a Web-based intelligent tutoring system of probability story problems. The focus of this paper is to explain how MAST deals with those problems using the Question Generation Module (QGM) and the Cognitive Module (CM). The QGM is able to generate story problems based on Natural Language Generation (NLG) techniques. This results in known semantic descriptions and linguistic structures of each story problem part. The CM, on the other hand generates the correct answer through interpreting the story problem parts and converting them into a corresponding mathematical model. This helps MAST in tracing the student answer and addressing any misinterpretations or overlooked information using different types of feedback. A satisfaction questionnaire has shown extreme satisfaction of the students and teachers with the capabilities of MAST.