Upload
edwin-mckenzie
View
213
Download
0
Tags:
Embed Size (px)
Citation preview
1
Andes Tutoring: Freedom, Support,
and Accelerated Learning as Students
Solve Complex Physics Problems
Kurt VanLehn & Brett van de SandeSchool of Computing, Informatics and Decision Engineering
Arizona State University
USN
2
Andes development team Developers
– Brett van de Sande
Instructors/designers– Bob Shelby– Don Treacy
Experimenters– Scotty Craig– Bob Hausmann– Sandy Katz– Tim Nokes– Michael Ringenberg
Instructors4-year colleges
Jim Culbertson – Arizona State University, AZJohn Fontinella – US Naval Academy, MDDavid Guerra – St. Anselm College, NHTroy Hacker – US Air Force Academy, COAndrew Heckler – Ohio State University, OHGerd Kortemeyer – Michigan State UniversityTed McClanahan – US Naval Academy, MDMary Wintersgill – US Naval Academy, MD
2-year collegesTom Wilbur – Ann Arundel Com. College, MD
High SchoolsSophia Gersham – Watchung Hills Reg. HS, NJPaul Perkins – Belleview Christian School, WADavid Richardson – Packer Academy, NY
3
Outline
Goals of the Andes project Andes – the core Andes – the surroundings Andes – technology Evaluation Why does Andes succeed?
Next
4
Why physics?
Required for the other sciences Major source of attrition Well-studied in cognitive science Other courses are similar
5
A typical physics courseRepeat: Read chapter Attend lectures Solve problems Do lab Review for exam Take chapter exam
Take finals: Standardized & conceptual
Tutoring needed
6
Why focus on problem solving?
Students spend most of their time on problem solving
Frustrating; May causes attrition Bad habits can develop
– “Symbol pushing” instead of deep understanding
Done right, it can elicit deep, conceptual understanding
Professional human tutors focus on it
7
What do professional tutors do?
Pick a good problem– Neither trivially easy nor impossibly difficult– Problem targets a weakness of the student
Help the student solve it– Let student try each step– Give immediate feedback if step is wrong– Give hints sparingly
Reflective debriefing– What were main principles?– What did you learn?
Andes could, but doesn’t
Andes does
Under development
8
How to evaluate Andes?Repeat: Read chapter Attend lectures Solve problems Do lab Review for exam Take chapter exam
1. Paper & human graders
2. Paper & grading service
3. Andes
4. Professionalhuman tutor
Take finals: Standardized & Conceptual
Com
paris
on c
ondi
tions
Just these 2 as of todayJust these 2 as of today
9
Main goals: Andes should be a “workbook” where:
Instructors select & assign Andes problems– Need lots of problems, covering all textbooks
Students solve problems on Andes, not paper – getting immediate feedback and hints
Students learn more, compared to paper
10
More goals
Instructors agree with all of Andes’ advice Instructors no longer need to grade
homework Students prefer Andes to paper Andes is as effective as human tutors
11
Outline
Goals of the Andes project Andes – the core Andes – the surroundings Andes – technology Evaluation Why does Andes succeed?
Next
12
A typical physics problem
University introductory physics courses High school physics courses
A 2000 kg car at the top of a 20º inclined driveway 20 m long slips its parking brake and rolls down. If we ignore friction and drag, what is the magnitude of the velocity of the car when it hits the garage door?
13
Andes user interface
Read a physics problem
Type in equations
Draw vectors
Type in answer
14
Andes feedback and hints“What should I do next?”
Green means correctRed means incorrect
“What’s wrong with that?”
Dialogue & hints
15
Frequently asked questions (slide 1 of 3) Why is Andes sometimes called an intelligent
tutoring system?– Tutors usually replace classes; Andes doesn’t.– Andes should be called a “step-based homework
helper”
Is Andes the same as web-based grading services such as WebAssign, Mastering Physics & LON-CAPA?– They give feedback & hints on answers only– Andes gives feedback & hints on steps leading to
answers
16
Most existing tutoring systems and web-based grading services accept only the answer
W = 25
Answer
What is the value ofangle w?
45°
w°
x°
30°
40°
z°y°
u°
17
With step-based systems (e.g., Andes), students enter steps leading up to the answer
Step
Step
Step
Answer
Step
40+30+x=180
x=110
x=z
w+45+z=180
w+45+110=180
w=180-155
w=25
Step
Step
Step
What is the value ofangle w?
45°
w°
x°
30°
40°
z°y°
u°
18
Step-based homework helpers usually give immediate feedback on each step
w = 40
OPPS!
OK
45°
w°
x°
30°
40°
z°y°
u°
What is the value ofangle w?
19
Hints start general…
w = 40
Lines that look parallel often are not.
OK
45°
w°
x°
30°
40°
z°y°
u°
What is the value ofangle w?
20
Hints become more specific.
w = 40
Try summing the angles of the triangle that include angle w. (see pg. 212)
OK
45°
w°
x°
30°
40°
z°y°
u°
What is the value ofangle w?
21
Usually, the last hint tells the student exactly what to enter.
w = 40
You should apply the triangle sum rule by entering 45+z+w=180.
OK
45°
w°
x°
30°
40°
z°y°
u°
What is the value ofangle w?
22
Frequently asked questions(slide 2 of 3)
Does Andes require students to do all the steps?– No. But skipping conceptual steps lowers the score.
Does it require doing steps in a particular order?– No, except that variables must be defined before being
used in equations– The only way to define a vector component is to draw
the vector
Are there correct solutions that Andes doesn’t accept.– No (we hope).
23
Frequently asked questions(slide 3 of 3)
Why does Andes focus on problem solving? Problem solving doesn’t improve conceptual understanding [sic]. Instruction really should focus on __________ instead of problem-solving. – Andes requires more conceptual steps than paper.– Reflective debriefing is being added– Perhaps instructors should let Andes to handle
problem-solving so they can focus on __________.
24
Outline
Goals of the Andes project Andes – the core Andes – the surroundings Andes – technology Evaluation Why does Andes succeed?
Next
25
Two methods for accessing Andes problems
Stand-alone– Downloads as a standard Windows application
Open-Learning Initiative (Web-based LMS)
26
Standalone opening screen is a menu of physics topics (apprx. chapters)
27
After clicking on “Translational dynamics,” get menu of problems
28
Two methods for accessing Andes problems
Stand-alone– Downloads as a standard Windows application
Open-Learning Initiative (Web-based LMS)– Free & open usage
» OLI keeps no record of student’s usage
– Authenticated member of a registered class» OLI keeps a grade book for the instructor
Next
29
OLI top level screen
Andes
30
OLI top level of Andes is a menu of topics (apprx. Chapters)
31
After clicking on “Translational Dynamics” module, get menu of problems
32
OLI grade book Looks/acts like a spreadsheet
– One row per student– One column per problem– Cell has student’s score on the problem
Can export to Excel or database Clicking a cell displays student’s solution in
instructor’s Andes.– Can check student’s work– Good for office hours
33
Outline
Goals of the Andes project Andes – the core Andes – the surroundings Andes – technology Evaluation Why does Andes succeed?
Next
The major components of an ITS
P(mastery) for each knowledge compo.
Problem to be solved
All correct steps in all orders
Response pattern for each student step
Expert
Assessor
Helper
Use
r in
terf
ace
The expert’s computation Expert can be authors,
students or an expert system
Solve the problem in all acceptable ways
Record steps taken Record knowledge
components used at each step
P(mastery) for each knowledge compo.
Problem to be solved
All correct steps in all orders
Response patterns for each student step
Expert
Assessor
Helper
Andes uses an expert system
Knowledge base organized by “problem solving methods” – One per major physics principle– Often called as “principle schemas”– Approximately 100 principles covered in 1-year course
Can solve more that 500 physics problems For each, finds all acceptable solutions
– Merges them into a solution graph
Pre-generates solution graphs & saves on disk– Allows regression testing (compare new to old)– Allows instructors to inspect
36
Problem solving method for Newton’s second lawTo apply Newton’s second law to <body> at <time> along <axis>: Draw a free-body diagram for <body> at <time> including <axis>
– For each force on <body> at <time>, draw it.– Draw the acceleration of <body> at <time>
Write the F=m*a in terms of components along <axis> For each vector (i.e., acceleration and each force), write a projection equation
for the vector along <axis> For each minor principle of the form <force magnitude> = <expression> where
the force is one of the ones on <body> at <time>, write the minor principle’s equation.
37
38
Problem & its solution graph
Draw coord. axes @ 20 deg
Define given quantitiesd=20 m; m= 200kg
Apply conservation of energyvf^2 = 2*g*sin(20 deg)
Apply translational kinematicsvi^2 = 2*a*d
Apply Newton’s second lawa= -g*cos(200 deg)
Solve equations for final velocityvf= 11.59 m/s
Enter answer: 11.59 m/s
Draw body for car
1. Draw free-body diagram2. Apply F=m*a along x-axis3. Project vectors onto x-axis4. Apply weight law W=m*g
•Draw weight force•Draw normal force•Draw acceleration
4 popular designsfor the Expert
Hand-author all possible solutions per problem– AutoTutor, CTAT
Rule-based AI problem solver + problem all possible solutions– Andes, Cognitive tutors
Hand-author one solution & use constraints to generalize to all possible solutions– Constraint-based tutors e.g., SQL Tutor
Given log files from students, induce shortest/best paths– iLisp, Barnes tutor
Problem to be solved
All correct steps in all orders
Expert
The helper’s computation
When the student enters a step, match it to a correct step
Give feedback & hints as necessary
Record response pattern
P(mastery) for each knowledge compo
Problem to be solved
All correct steps in all orders
Response patterns for each student step
Expert
Assessor
Helper
How to tell if student’s equation is correct? Color by numbers algorithm Given student’s equation “Fw_x+m*g*sin(20 deg)” Substitute values from solution point
– Fw_x 6704 N– g 9.8 m/s^2– m 2000 kg
Check arithmetic.– If checks, equation is correct
See paper for dealing with variables that don’t have values in the solution point
41
When the student needs a hint, how to choose next step?
Which solution branch is student probably following?
First PSM along path that is not finished? First step inside the PSM that is not yet
done?
But how to tell which equation-writing steps have been done already?
42
Matching equations via the indy check algorithm
Student enters “Fw_x+m*g*sin(20 deg)”– Row S below
Which equations in solution were combined?– Rows A, B, C, D– Because S’s gradient is a linear combination of their gradients
43
Function f f/m f/g f/Fw f/Fw_x gradient
A Fw_x –Fw*cos(250º) 0 0 –cos250º 1 (0, 0, 0.342, 1)
B Fw – mc*g –g –mc 1 0 (–9.8 ,–2000, 1,0)
C mc – 2000 1 0 0 0 (1, 0, 0, 0)
D g – 9.8 0 1 0 0 (0, 1, 0, 0)
S Fw_x+mc*g*sin(20º) g*sin20º mc*sin20º 0 1 (3.352, 684, 0, 1)
3 main design issuesfor the Helper
Matching student’s step to correct steps– Natural language: Use LSA, keywords, Atlas…– Math expressions: Substitute numbers for variables– Physical actions: Fuzzy, Bayesian
Handling pedagogically important student errors Managing the student-tutor dialogue
– Immediate feedback + hint sequences
– Delayed feedback + student or tutor controlled debriefing
– Adaptive, especially decision theoretic & fading
All correct steps in all orders
Response patterns for each student step
Helper
The assessor’s computation Given
– Response patterns for each step taken by the student
– Old P(mastery) for each knowledge component
Calculate– New P(mastery)
P(mastery) for each knowledge compo.
Problem to be solved
All correct steps in all orders
Response patterns for each student step
Expert
Assessor
Helper
Currently, Andes doesn’t do such assessment
Where’s the scale-up bottleneck?
Number of problems
Cod
e si
ze
Expert
Helper
Assessor
Userinterface
Other scaling up issues= same as other reforms
Coordination with curriculum & standards Teacher buy-in and training Support Etc…
Implementation: Summary
Expert– Expert system,
not humans Helper
– Matching student equations is challenging
Assessor– Dynamic
Bayesian networksP(mastery) for each knowledge component
Problem to be solved
All correct steps in all orders
Response patterns for each student step
Expert
Assessor
Helper
49
Outline
Goals of the Andes project Andes – the core Andes – the surroundings Andes – technology Evaluation Why does Andes succeed?
Next
50
Prior work with answer-only homework helpers
Compared to ordinary paper-based homework– Modest effect size: 0.42 (Kulik et al., 1983)
Compared to paper-based homework that iscollected & graded– No benefits (Pascarella, 2002; Dufresne, Mestre & Rath, 2002)
Interpretation – Motivating students to do their homework provides
benefits– But answer-only feedback & hints provides no
additional benefits
51
Prior work with step-based homework helpers
Lisp Tutor (Corbett, 2001) and many others– Same homework problems & text– Experimenter’s exams only– Not a whole semester (only 5 lessons)
Cognitive Tutors (Koedinger et al; Carnegie Learning)
– Whole year of high-school algebra, geometry– Both experimenter’s exams & standard exams– Curriculum confounded with tutoring system
52
Evaluation of Andes at the US Naval Academy
Fall semesters 2000, 2001, 2002 & 2003 Only the homework modality was varied:
Andes vs. paper-based– Same textbook
– Similar lectures, labs, recitations
– Similar homework problems
– Same exams
Students were motivated to do paper-based homework– Either collected and graded
– Or 1 homework problem on each quiz
53
Exams Midterm exam
– 1 hour, 4 problems– Scored on derivation & answer
» Drawings (30%)» Variable definitions (20%)» Equations (40%)» Answers (10%)
Final exam– 3 hours, 50 problems– Multiple choice
54
Subjects; non-random assignment
Prior competence equal, all 4 years– Grade-point averages equal – Distribution of majors equal
2000 2001 2002 2003
N Andes 140 129 93 93
N control 135 44 53 44
55
Midterm exam results(All differences reliable, p < .01)
50
55
60
65
70
75
2000 2001 2002 2003
ControlAndes
Effect size: 0.61
56
Final exam: Methodological details
Andes coverage of the course increased to 70% by 2003, so used only that year’s final exam
Non-random sample– 89 Andes students (3 sections)– 823 non-Andes students (rest of course)– GPAs, Majors reliably different
Regressed out incoming GPA, Major
57
Final exam results
-1
-0.5
0
0.5
1
1.5
2
2.5
Control Andes
Difference is reliable (p = 0.028)
Effect size = 0.25
58
Effect sizes for subscores of midterm exam
-1
-0.5
0
0.5
1
1.5
Drawings Variables Equations Answers
The more conceptual the subscore, the greater the benefit
59
Andesy = 0.9473x - 2.4138
R2 = 0.2882
Controlsy = 0.7956x - 2.5202
R2 = 0.2048
-3.0000
-2.0000
-1.0000
0.0000
1.0000
2.0000
3.0000
1 1.5 2 2.5 3 3.5 4
GPA
Z-s
core
on
exam
ANDES
CONTROLS
Linear (ANDES)
Linear (CONTROLS)
Benefits same regardless of GPA
60
Benefits varied by major on final exam but not on midterm exam
Midterm exam results
-0.5
-0.4
-0.3
-0.2
-0.1
0
0.1
0.2
0.3
Engineers Scientists Others
Control Andes
Final exam results
-1
-0.5
0
0.5
1
1.5
2
2.5
3
3.5
4
4.5
Engineers Scientists Others Overall
Non-Andes Andes
61
Interpretation of results Engineering & science majors knew
red path & preferred it for answer-only– Andes didn’t affect their final exam scores
Other majors did not have red path, so they used the blue path on answer-only– Andes increased their final exam scores
Everyone used blue path on midterms– Andes increased everyone’s midterm exam
scores– Biggest benefit for diagrams & variables– Smaller on equations; none on answer
Problem
Diagram & variables
Equations
Answer
Andes
Andes
Prior math & physics
62
Summary of results Main result: Replacing graded paper homework with
Andes provides benefits– Midterm exam effect size: 0.61 – Final exam effect size: 0.25
Andes helps students learn conceptual skills– Effect sizes on conceptual subscores: 1.21 & 0.69– Effect sizes on calculational subscores: 0.11 & -0.08
Engineering & Science majors appear to have a non-conceptual method for solving problems– Competes with the conceptual method taught by Andes– They use it on the (answer-only) final exam– This dilutes the benefit of Andes on final exam
63
Andes’ effect sizes are typical of other step-based homework helpers
0
0.2
0.4
0.6
0.8
1
1.2
1.4
Experimenter'sexam:
Conceptualparts
Experimenter'sexam: Lessconceptual
parts
Standard exam
Lisp tutorCognitive tutorAndes
64
Take-home message on homework helpers
Baseline:– Paper-based with light or no human grading
Better: – Answer-based e.g., WebAssign
Best: – Step-based e.g., Andes–
65
Outline
Goals of the Andes project Andes – the core Andes – the surroundings Andes – technology Evaluation Why does Andes succeed?
Next
66
Why these results? Hypotheses:
Baseline:– Paper-based with light or no human grading– Students often do not do their homework
Better: – Answer-based e.g., WebAssign – Students do homework, but with non-optimal methods
Best: – Step-based e.g., Andes– Students do homework with optimal method
67
3 methods for doing homework
1. Get answers from friends
2. Copy & edit another problem’s solution
3. Generate each step oneself
68
1. Getting answers from friends
No learning, so should be discouraged Even if the numbers in a problem are
randomly generated, students circulate spreadsheets that calculate answers
Andes requires that students “show their work”– Andes can analyze time per step, too.– So Andes can make this kind of cheating very
difficult
69
2. Copy and edit another problem’s solution
Students learn general solution schemas– E.g., for pulley problems, a = g(m1-m2)/(m1+m2)– Good for learning to solve algebra word problems– High math students tend to use it (cf. USNA)– But should learn physics principles, not problems
Andes mildly discourages– Must close current problem in order to open an old one– Example solutions are videos, not paper
Andes should implement “fading”
70
3. Generate each step oneself
If stuck, get hints (from Andes), or refer to textbook or videos of examples– Should focus on learning the principle, not just
getting unstuck– Hint sequences start vague, become specific
Causes learning of principles, not problems
71
Hypothesized distributions of solution methods explains results
0%
20%
40%
60%
80%
100%
Light or no grading
Answer-based
Step-based e.g., Andes
Fre
qu
en
ce
of
so
luti
on
me
tho
d
Type of homework helper
3. Each step oneself
2. Copy & edit solutions
1. Copy answers
No solution
72
Take-home message, again
Baseline:– Paper-based with light or no human grading– Students often do not do their homework
Better: – Answer-based e.g., WebAssign – Students do homework, but with non-optimal methods
Best: – Step-based e.g., Andes– Students do homework with optimal method
73
Outline
Goals of the Andes project Andes – the core Andes – the surroundings Evaluation Why does Andes succeed? Future work
Next
74
Future work
Andes3– Client/server (no downloading necessary)– Client runs in any browser & any OS– User interface ≈ PowerPoint (for familiarity)– Compatible with WebAssign & other services
Help others to author Andes problems Support conceptual problem solving
75
Quantitative problem solving is necessary but not sufficient for deep understanding
Necessary– Avoids inert knowledge
Not sufficient– Question:
» If a massive truck and a lightweight car have a head-on collision, on which vehicle is the impact force greater?
– Students who got A’s say: The car– Correct answer: Equal (Newton’s third law)
Many concept inventories (exams) exist
76
Does Andes improve scores on concept inventories?
Learning principles instead of problems should help
But not enough– USNA: FCI not significantly different
77
Why so little transfer from quantitative to conceptual problem solving?
Conceptual prob. solving knowledge
Quantitative prob. solving knowledge
Traditional assumption lots of transfer
Quantitative prob. solving knowledge
Cognitive modeling little transfer
Conceptual prob. solving knowledge
78
Solution: Add conceptual problem solving practice
Question: In the problem you just solved, what would be different if the car had no mass?
Quantitative prob. solving knowledge
Conceptual prob. solving knowledge
W=m*gIf no mass, then no weight
79
Katz & Connelly’s experimental addition to Andes After students have finished an Andes problem,
use a natural language dialogue system to discuss the problem’s solution
System asks lots of conceptual questions
80
Students first solve an Andes problem
81
Andes then asks about principles, alternative situations…
Andes: Which major principle did you need to solve the problem? Student: Newton's 2nd law Andes: Yes. The main difference between this problem and most of the
previous Newtons 2nd law problems is the fact that the direction of acceleration is __________. (fill in the blank)
Student: centripetal Andes: Correct. All else being the same, how would the velocity at the
lowest point of the swing change if the length of the rope were doubled to 4.0 m?
Student: it would also double Andes: Well, it would increase, but it would not double. Recall that the
formula for centripetal acceleration involves the square of the velocity. …
82
Results of Katz/Connelly expt. Successes
Treatment students significantly outperformed control students on a mostly qualitative post-test
Instructors would like reflective dialogue to become a permanent feature of Andes
Limitations Currently covers only 8 weeks of Andes No significant effect on FCI at the end of the
semester Next steps
Revise content to target FCI Cover whole semester
83
Thanks for your attention!
At www.andestutor.org you can…– Download the stand-alone version of Andes– Try the OLI version of Andes– Download papers on Andes– View videos of Andes being used
Questions?
84
P(mastery) for each knowledge compo.
Problem to be solved
All correct steps in all orders
Response pattern for each student step
Expert
Assessor
Helper
Use
r in
terf
ace
Andesy = 0.9473x - 2.4138
R2 = 0.2882
Controlsy = 0.7956x - 2.5202
R2 = 0.2048
-3.0000
-2.0000
-1.0000
0.0000
1.0000
2.0000
3.0000
1 1.5 2 2.5 3 3.5 4
GPA
Z-s
core
on
exam
ANDES
CONTROLS
Linear (ANDES)
Linear (CONTROLS)