Tracking Knowledge Proficiency of Students with Educational Priors - - PowerPoint PPT Presentation
The 26th ACM International Conference on Information and Knowledge Management (CIKM) 2017/11/06-2017/11/10, Singapore, Singapore Tracking Knowledge Proficiency of Students with Educational Priors Yuying Chen 1 , Qi Liu 1 , Zhenya Huang 1 , Le Wu
1
Yuying Chen1, Qi Liu1, Zhenya Huang1, Le Wu2, Enhong Chen1*, Runze Wu1, Yu Su3, Guoping Hu4
1 University of Science and Technology of China 2 Hefei University of Technology 3Anhui University 4iFLYTEK Research
The 26th ACM International Conference on Information and Knowledge Management (CIKM) 2017/11/06-2017/11/10, Singapore, Singapore
p
Backgroud and Related Work
p
Problem Statement
p
Methodology
p
Experiments
p
Conclusion
2
¨ Traditional teaching method
n The teacher’s energy is limited. n The same learning strategy, same exercises,
impersonality.
n Teaching quality is difficult to guarantee n A higher cost
3
4
¨ E-Learning(Online learning)
p Education Service Systems
p Various online tutoring systems allow students to learn
and do exercises individually.
5
dynamic loop
6
they are only good at predicting student’s proficiency from a static perspective.
7
p
Backgroud and Related Work
p
Problem Statement
p
Methodology
p
Experiments
p
Conclusion
8
¨ Problem: How to track students’ knowledge
proficiency over time. (TKP task)?
¨ Opportunity
¨ Focus on Math problem
9
shadow
¨ Given the students’ response tensor R and Q-
matrix labelled by educational experts
¨ our goal is two-fold: p modeling the change of students’ knowledge
proficiency from time 1 to T .
p predicting students’ knowledge proficiency and
responses in time T + 1.
¨ Challenge: p 1. How to get a student’s knowledge proficiency? p 2. How to explain the change of knowledge proficiency
10
¨ A showcase of KPD task on mathematical exercises
related to the knowledge points of Function and Inequality
11
learn? forget?
explain:
p
Backgroud and Related Work
p
Problem Statement
p
Methodology
p Probabilistic Modeling with Priors p Model Learning and Prediction p
Experiments
p
Conclusion
12
13
¨
14
p Probabilistic Modeling with Priors
p for each student and each exercise, we model
the response tensor R as:
p
is the knowledge proficiency of student i
p
denotes the relationship between exercises and knowledge points
p How to establish the corresponding
relationship between students, exercises and knowledge points?
¨ Q-matrix
probabilistic modeling well.
15
Function Solid Geometry Arithmetic Progression Inequation exercise1 1 exercise2 1 1 1 exercise3 1 1 exercise4 1
¨ for exercise j, if a knowledge point q is marked as 1,
then we assume that q is more relevant to exercise j than p with mark 0
¨ After that, we can transform the original Q-matrix
into a set of comparability by:
16
Partial order
¨ we define the probability that exercise j is more
relevant to knowledge point q than knowledge point p as:
¨ the log of the posterior distribution
17
¨ we assume a student’s current knowledge proficiency
is mainly influenced by two underlying reasons:
p She forgets her previous knowledge proficiency over time. p The more exercises she does, the higher level of related
knowledge proficiency she will get.
p We model the two effects of each student’s knowledge
proficiency in time window t = 2; 3; :::; T as:
18
forgetting learning
¨
19
20
p graphical representation of the proposed latent model
¨
21
¨
22
p
Backgroud and Related Work
p
Problem Statement
p
Methodology
p
Experiments
p
Conclusion
23
¨ Dataset
exercise records of high school students
“Non-skill builder”
24
¨ Two evaluations:
n proved the rationality of three priors for prediction
accuracy
n proved that the effectiveness of associating each
exercise and student with a knowledge vector in the same knowledge space .
25
¨ Evaluation Metrics
n RMSE MAE
n IRT n DINA n PMF n LFA n BKT n QMIRT (MIRT+partial order) n QPMF (PMF+Partial order)
26
n KPT performs best
n DOA-of each specific knowledge point k n DOA-average of all knowledge points
n DINA n BKT n QMIRT (MIRT+partial order) n QPMF (PMF+Partial order)
27
28
¨ KPT performs best on KPD
task for all knowledge points, followed by QPMF and QIRT, which indicates that the educational prior of Q-matrix does effectively.
¨ The diagnosis results of a student on six knowledge
points at three particular time in Math2
¨ It clearly demonstrated the explanatory power of our
proposed KPT model
29
p
Backgroud and Related Work
p
Problem Statement
p
Methodology
p
Experiments
p
Conclusion
30
¨ Problem: track students’ knowledge proficiency mastery
¨ Method: probabilistic model with three educational priors ¨ Contributions:
model for solving the TKP task
with the Q-matrix prior.
priors to capture the change of each student’s proficiency over time.
31
¨ First, we will consider to combine more kinds’ of
users’ behaviors (e.g., reading records) for the TKP task.
¨ Second, as students may learn difficult knowledge
points (e.g., Function) after some basic ones (e.g., Set), it is interesting to take this kind of knowledge relationship into account for TKP
32
¨ We thanks for:
n url: http://sigir.org/general-information/travel-grants/
n url: https://cmt3.research.microsoft.com/CIKMTA2017
33
34
cyy33222@mail.ustc.edu.cn
Reporter: Yuying Chen