In engineering design courses, many problems have a specification that the student's implementation must meet, but give the student a broad range of freedom for the internal design of that implementation. There may be several distinct, correct strategies for solving them, some of which may be unknown to the teaching staff or intelligent tutor designer. Visualizing and classifying the multiple solutions that students generate in response to assigned engineering design problems will improve hints and answers to students' questions, whether they are provided by peers, staff, or automation. I log incremental snapshots of students' solutions as they progress toward correct and incorrect solutions. Initial investigations demonstrate that the choice of features to represent solutions is critical, and may be domain- or problem-dependent.
[1]
Lauri Malmi,et al.
Automatic recognition of students' sorting algorithm implementations in a data structures and algorithms course
,
2012,
Koli Calling.
[2]
Lydia B. Chilton,et al.
Personalized Online Education - A Crowdsourcing Challenge
,
2012,
HCOMP@AAAI.
[3]
Lauri Malmi,et al.
How do students solve parsons programming problems?: an analysis of interaction traces
,
2012,
ICER '12.
[4]
Elena L. Glassman,et al.
Toward facilitating assistance to students attempting engineering design problems
,
2013,
ICER.
[5]
Paulo Blikstein,et al.
Modeling how students learn to program
,
2012,
SIGCSE '12.