CSAIL Publications and Digital Archive header
bullet Research Abstracts Home bullet CSAIL Digital Archive bullet Research Activities bullet CSAIL Home bullet

link to publications.csail.mit.edu link to www.csail.mit.edu horizontal line


Research Abstracts - 2007
horizontal line

horizontal line

vertical line
vertical line

Classroom Learning Partner: 

Supporting Interpretation and Aggregation of Digital Ink Answers to In-Class Exercises

Kimberle Koile & Howard Shrobe


The goal of the Classroom Learning Partner (CLP) project is to increase instructor-student interaction and student learning in large classes by developing software to support the use of in-class exercises. 

Figure 1.  Student works an introductory computer
                computer science exercise using CLP.

Figure 2.  Example submitted student answer in
                an introductory computer science class.




Previous research  has shown that students learn better when they are actively engaged in the learning situation, e.g., [4,  6].  It also has shown that students learn better when engagement takes the form of hands-on activities that yield immediate feedback through interaction with peers and/or instructors, e.g. [6, 9].  Taking advantage of these techniques in a large class is a challenge:  How can instructors determine which concepts have been understood in classes of size 50, 100, or even 200?  How can instructors make determinations quickly and effectively enough to give feedback to that many students, and in real-time?   The key idea is to interpret and aggregate student digital ink answers to in-class exercises, presenting an instructor with summary information in much the same way that wireless polling systems do, e.g., [5].


Classroom Learning Partner employs Tablet PC technology and extends an existing wireless presentation system to support the submission and aggregation of student solutions to in-class exercises.  Using the existing presentation system Classroom Presenter [1], an instructor lectures, annotating slides with digital ink.  The slides and ink are displayed simultaneously on a large screen and on students’ Tablet PCs.  When an instructor displays a slide containing an exercise, the students work the exercise, using digital ink on their Tablet PCs, then anonymously submit their solutions to the instructor via a wireless network.  Using Classroom Presenter in this way works well in classes of size eight or smaller, but instructors are easily overwhelmed by more than eight solutions [2]

Using Classroom Learning Partner, an instructor displays a slide containing an exercise and students wirelessly submit digital ink answers to the exercise.  The instructor then aggregates the student solutions into a small number of equivalence classes and views the results in the form of a histogram and representative solutions. This teaching methodology is similar to that employed by wireless polling systems, but since students using CLP write their solutions rather than choosing from pre-existing sets of possible solutions, the instructor is not limited to using only multiple-choice, matching, or true-false exercises.  Such close-ended questions do not foster the critical thinking skills that open-ended questions do [3].

The current CLP system consists of a network of Tablet PCs, and software for posing questions to students, interpreting their handwritten digital ink answers, and aggregating those answers into equivalence classes, each of which represents a particular level of understanding or misconception of the material.  The current system supports a useful set of recognizers for specific types of answers, and employs AI techniques in the knowledge representation and reasoning necessary to support interpretation and aggregation of the answers.  Shown below is a diagram of the CLP architecture.

Figure 3:  Components of CLP; see [8] for details and discussion

Classroom Studies 

In addition to developing aggregation software, and the ink interpretation software that enables aggregation, this project has completed three studies that evaluated the hypothesis that the use of Tablet-PC-based classroom systems such as Classroom Presenter and Classroom Learning Partner increases student learning by (1) increasing student focus and attentiveness in class, (2) providing immediate feedback to both students and instructor about student misunderstandings, (3) enabling the instructor to adjust course material in real time based upon student answers to in-class exercises, and (4) increasing student satisfaction.  Two of the three studies were controlled classroom experiments; all three studies employed the same pedagogy, that of real-time feedback to anonymous wirelessly submitted digital ink answers to in-class exercises.  Each study demonstrated that this approach reaches students who would have otherwise been left behind:  fewer students performed poorly in the classes using Tablet PCs.  Each study also demonstrated that the approach leads to more interactions between instructor and student, greater attentiveness in class, and greater student satisfaction.  [7,  8]



Figure 4:  Graphs of  student performance for two controlled studies  [8]


Current Work

We are continuing our two lines of research:  further development of CLP, and conducting another learning study this term.  Development efforts focus on instructor tools for presentation preparation and data analysis, and support for interpretation and aggregation of sketched student answers.

Research Support

We thank MIT iCampus (http://icampus.mit.edu) for funding this project.  We also thank Hewlett Packard and MIT Academic Computing (now the Office of Educational Innovation and Technology, http://web.mit.edu/dur/OEIT) for generously donating Tablet PCs.


This project would not be possible without  the students in the CLP Group:  Kevin Chevalier, Capen Low, Sanjutka Pal, Adam Rogal, Jordan Sorensen, Kah Seng Tay, and Kenneth Wu; alums: Karin Iancu, Michel Rbeiz, Amanda Smith. Additionally, Owen Lin has provided valuable assistance to the projec


[1] Anderson,  R., Anderson, R., Simon, B., Wolfman, S., VanDeGrift, T., and Yasuhara, K.  Experiences with a tablet-pc-based lecture presentation system in computer science courses.  In Proceedings of  SIGCSE '04.

[2] Anderson, R.  Personal communication.   2005. 

[3] Bloom B.S.  Taxonomy of Educational Objectives, Handbook I:  The Cognitive Domain. New York: David McKay Co. Inc., New York, 1956.

[4] Bransford, J.D., Brown, A.L. and Cocking, R.R., How People Learn: Brain, Mind, Experience, and School, National Academy Press, Washington , D.C. , 2003.

[5]  Draper, S.W.  From active learning to interactive teaching: Individual activity and interpersonal interaction.  In Proceedings of Teaching and Learning Symposium:  Teaching Innovations, 2004, The Hong Kong University of Science and Technology. 

[6] Hake, R.R. Interactive-engagement versus traditional methods: A six-thousand student survey of mechanics test data for introductory physics courses, American Journal of Physics , 66(1):64-74, 1998.

[7] Koile, K. and Singer, D.   Improving learning in CS1 via tablet-pc-based in-class assessment.  In Proceedings of International Computing Education Research Workshop (ICER) 2006, September 9-10, 2006, University of Kent, Canterbury, UK.

[8]  Koile, K.,  Chevalier, K., Rbeiz, M., Rogal, A., Singer, D., Sorensen, J., Smith, A., Tay, K.S., Wu, K.  Supporting feedback and assessment of digital ink answers to in-class exercises.  To appear in Proceedings of the Nineteenth Conference on Innovative Applications of AI, July 22-29, 2007.

[9] Steadman, M.  Using classroom assessment to change both teaching and learning.  New Directions for Teaching and Learning, 75, 1998, pp. 23-35.


vertical line
vertical line
horizontal line

MIT logo Computer Science and Artificial Intelligence Laboratory (CSAIL)
The Stata Center, Building 32 - 32 Vassar Street - Cambridge, MA 02139 - USA
tel:+1-617-253-0073 - publications@csail.mit.edu