Learning SQL with a Computerized Tutor (Centered on SQL-Tutor)

1
Learning SQL with a Computerized Tutor (Centered
on SQL-Tutor)

• Antonija Mitrovic
• (University of Canterbury)
• Presented by Danielle H. Lee

2
Agenda

• Problem regarding to learning SQL
• Purpose of SQL-Tutor System
• Architecture of SQL-Tutor
• Evaluation of SQL-Tutor

3
Problem regarding to learning SQL

• Burden of having to memorize database schemas
  (incorrect table or attribute names)
• Misconceptions in students understanding of the
  elements of SQL and the relational data model in
  general
• Not easy to learn SQL directly by working with a
  DBMS
• Inadequacy of feedback from a RDBMS
• Example (in Ingres) E_USOB63 line 1, the columns
  in the SELECT clause must be contained in the
  GROUP BY clause.
• Inability of a RDBMS to deal with semantic errors

4
Research By the Univ. of Canterbury

• DatabasePlace
• Web portal for database related lectures.
• SQL-tutor teaches the SQL database query
  language
• NORMIT data normalization tutor
• ER-tutor teaches database design using the
  Entity-Relationship data model
• Constraint-based tutors

5
Automated Tutoring System

• The School of Computing, Dublin City University
• Developed for an online course name the
  introduction to databases
• To Provide a certain level advice and guide by
  using feedback, assessment, and personalized
  guidance
• Limited the contents to the SQL SELECT sentence.
• The most fundamental of the SQL
• Simple but having the capacity to become quite
  complex
• There are correction model and pedagogical model.
  
• Correction model Multi-level error
  categorization scheme according to three aspects
  (from, where, select)
• Pedagogical model analyses the information
  stored by the students answers, it provides
  feedback, assessment, and guidance

6
Purpose of Project

• Personalized ITS for Database Courses
• Personalized tutoring system for learning SQL
• To adapt SQL-tutor technology for use with a
  different audience and to explore some ways to
  maximize the educational value for every student.
  
• Exploration of personalized guidance technology
  based on the ideas of adaptive hypermedia

7
Purpose of SQL-Tutor system

• To explore and extend constraint based modeling
• Problem-solving environment intended to
  complement classroom instruction.
• Problem sets with nine levels of complexity
  defined by a human expert
• Students have a assigned educational level and
  the level is updated by observing the students
  behavior.
• Novice, intermediate, or experienced

8
System Demo

• http//ictg.cosc.canterbury.ac.nz8000/sql-tutor/l
  ogin

9
Architecture of SQL-Tutor
10
Constraint-based model (contd.)

• Ohlssons theory of learning from errors (1996)
• Error recognition
• Error correction
• Conceptual domain knowledge is represented in
  terms of over 500 constraints
• Constraints define equivalence classes of problem
  states
• Equivalence class triggers the same instructional
  action
• A students solution is matched to constraints to
  identify any that are violated.
• Neutral with respect to the pedagogy and
  knowledge domain

11
Constraint-based model

• Example specifying the SELECT clause of a SQL
  query cannot be empty

(p 2 The SELECT clause is a mandatory one.
Specify the attributes/expressions to retrieve
from the database. (not (null (select-clause
ss))) SELECT)
Unique No.
Instructional Message
Part of the constraint
12
Evaluation

• Computer Science students, Univ. of Canterbury
• Three experiments for evaluation
• First (April 1998) to evaluation how well CBM
  supports student learning and to evaluate the
  interface and constraint base of SQL-Tutor
• Subject No 20
• Second (May 1999) to evaluate the effectiveness
  of various types of feedback in the system
• Subject No 33
• Third (October 1999) to evaluate the advanced
  pedagogical agent (no explanation)

13
Results of subjective evaluation
14
Mastery of constraints

• The degree of mastery of a given constraint is a
  function of the amount of practice on that
  constraint
• Measured the number of occasions relevant to each
  constraint and calculate the probability of
  violating a given constraint.

15
Evaluation results of learning effects
16
Result of first experiment
Group Mean Std Dev.
Experimental 82.75 8.76
Control 71.23 17.56
Total 76.24 15.39
17
Kinds of feedback

• Positive/negative feedback
• Error flag
• Hint
• All errors
• Partial solution
• Complete solution

18
Result of second experiment (contd.)
19
Result of second experiment

• CBM-based general feedback is superior to
  offering a correct solution.
• Among six feedbacks, the initial learning rate is
  highest for all errors (0.44) and error flag
  (0.40), closely followed by positive/negative
  (0.29) and hint (0.26). The learning rate for
  partial (0.15) and full solution (0.13) are low.

20

• Thank you