AnalyticalInk: An Interactive Learning Environment for Math Word Problem Solving

We present AnalyticalInk, a novel math learning environment prototype that uses a semantic graph as the knowledge representation of algebraic and geometric word problems. The system solves math problems by reasoning upon the semantic graph and automatically generates conceptual and procedural scaffoldings in sequence. We further introduces a step-wise tutoring framework, which can check students' input steps and provide the adaptive scaffolding feedback. Based on the knowledge representation, AnalyticalInk highlights keywords that allow users to further drag them onto the workspace to gather insight into the problem's initial conditions. The system simulates a pen-and-paper environment to let users input both in algebraic and geometric workspaces. We conducted an usability evaluation to measure the effectiveness of AnalyticalInk. We found that keyword highlighting and dragging is useful and effective toward math problem solving. Answer checking in the tutoring component is useful. In general, our prototype shows the promise in helping users to understand geometrical concepts and master algebraic procedures under the problem solving.

[1]  Lipu Zhou,et al.  Learn to Solve Algebra Word Problems Using Quadratic Programming , 2015, EMNLP.

[2]  Yun Huang,et al.  Your Model Is Predictive - but Is It Useful? Theoretical and Empirical Considerations of a New Paradigm for Adaptive Tutoring Evaluation , 2015, EDM.

[3]  Philipp Koehn,et al.  Abstract Meaning Representation for Sembanking , 2013, LAW@ACL.

[4]  Oren Etzioni,et al.  Solving Geometry Problems: Combining Text and Diagram Interpretation , 2015, EMNLP.

[5]  Hongan Wang,et al.  Intelligent understanding of handwritten geometry theorem proving , 2010, IUI '10.

[6]  Tracy Anne Hammond,et al.  PaleoSketch: accurate primitive sketch recognition and beautification , 2008, IUI '08.

[7]  John Dunlosky,et al.  Improving Students’ Learning With Effective Learning Techniques: Promising Directions From Cognitive and Educational Psychology , 2012 .

[8]  Neil T. Heffernan,et al.  Expanding the Model-Tracing Architecture: A 3rd Generation Intelligent Tutor for Algebra Symbolization , 2008, Int. J. Artif. Intell. Educ..

[9]  Vincent Aleven,et al.  A New Paradigm for Intelligent Tutoring Systems: Example-Tracing Tutors , 2009, Int. J. Artif. Intell. Educ..

[10]  John R. Anderson,et al.  Cognitive Tutors: Lessons Learned , 1995 .

[11]  Neil T. Heffernan,et al.  The Composition Effect in Symbolizing: The Role of Symbol Production vs. Text Comprehension , 2013 .

[12]  Sumit Gulwani,et al.  Synthesizing geometry constructions , 2011, PLDI '11.

[13]  Jean-François Lebeau,et al.  Designing a Knowledge Representation Approach for the Generation of Pedagogical Interventions by MTTs , 2014, International Journal of Artificial Intelligence in Education.

[14]  Bat-Sheva Ilany,et al.  Language and Mathematics: Bridging between Natural Language and Mathematical Language in Solving Problems in Mathematics , 2010 .

[15]  Susan Craw,et al.  Case-Based Reasoning , 2010, Encyclopedia of Machine Learning.

[16]  Mitchell J. Nathan,et al.  The Real Story Behind Story Problems: Effects of Representations on Quantitative Reasoning , 2004 .

[17]  Luke S. Zettlemoyer,et al.  Learning to Automatically Solve Algebra Word Problems , 2014, ACL.

[18]  Kurt VanLehn,et al.  The Andes Physics Tutoring System: Lessons Learned , 2005, Int. J. Artif. Intell. Educ..

[19]  Ryan Shaun Joazeiro de Baker,et al.  New Potentials for Data-Driven Intelligent Tutoring System Development and Optimization , 2013, AI Mag..

[20]  Julie L. Booth,et al.  Instructional Complexity and the Science to Constrain It , 2013, Science.

[21]  Robert C. Zeleznik,et al.  Hands-on math: a page-based multi-touch and pen desktop for technical work and problem solving , 2010, UIST.

[22]  B. Rittle-Johnson,et al.  Developing Conceptual Understanding and Procedural Skill in Mathematics: An Iterative Process. , 2001 .

[23]  Kenneth R. Koedinger,et al.  A paradigm for handwriting-based intelligent tutors , 2012, Int. J. Hum. Comput. Stud..

[24]  Bryan Ford,et al.  Parsing expression grammars: a recognition-based syntactic foundation , 2004, POPL '04.

[25]  A. Schoenfeld Learning to Think Mathematically: Problem Solving, Metacognition, and Sense Making in Mathematics (Reprint) , 2009 .

[26]  Kenneth D. Forbus,et al.  Towards a computational model of sketching , 2001, IUI '01.

[27]  Vincent Aleven,et al.  Intelligent Tutoring Goes To School in the Big City , 1997 .

[28]  Sharon L. Oviatt Interfaces for thinkers: computer input capabilities that support inferential reasoning , 2013, ICMI '13.

[29]  Lisa Anthony,et al.  A lightweight multistroke recognizer for user interface prototypes , 2010, Graphics Interface.

[30]  John R. Anderson,et al.  Knowledge tracing: Modeling the acquisition of procedural knowledge , 2005, User Modeling and User-Adapted Interaction.

[31]  Joseph J. LaViola,et al.  MathPad2: a system for the creation and exploration of mathematical sketches , 2004, SIGGRAPH 2004.

[32]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[33]  Joseph J. LaViola,et al.  MathPaper: Mathematical Sketching with Fluid Support for Interactive Computation , 2008, Smart Graphics.

[34]  Joseph J. LaViola,et al.  MathPad2: a system for the creation and exploration of mathematical sketches , 2004, ACM Trans. Graph..