IERI educational data mining panel

Slides:



Advertisements
Similar presentations
Wynne Harlen. What do you mean by assessment? Is there assessment when: 1. A teacher asks pupils questions to find out what ideas they have about a topic.
Advertisements

Understanding the ESLRS
Project Title Name(s) School Grade(s). Question An excellent question will be interesting, creative, worded scientifically and relevant to the world today.
Navigation and Ancillary Information Facility NIF Motivation for Developing SPICE November 2014.
Developing your Assessment Judy Cohen Curriculum Developer Unit for the Enhancement of Learning and Teaching.
6/1/2015WM-001 Planning for Measurement - copyright Paul Sorenson slide 1 Planning for Measurement WM Software Process and Quality Measurement is.
MED  Problem of the Day: SEND +MORE MONEY.
Mining Data from Randomized Within-Subject Experiments in an Automated Reading Tutor Joseph E. Beck and Jack Mostow Project LISTEN (
Prelude to the Research Validity Lecture A RH: is a guess about the relationships between behaviors In order to test our RH: we have to decide on a research.
Lesson planning? It can’t be that difficult! Svetla Tashevska, NBU.
Regression testing Tor Stållhane. What is regression testing – 1 Regression testing is testing done to check that a system update does not re- introduce.
How to Fill Out the CARD Form (Course Assessment Reporting Data Form)
This presentation will guide you though the initial stages of installation, through to producing your first report Click your mouse to advance the presentation.
1. An Overview of the Data Analysis and Probability Standard for School Mathematics? 2.
Information and Data What’s the difference between two? Information systems = hardware and software working together… It will take DATA that has been put.
Testing. Definition From the dictionary- the means by which the presence, quality, or genuineness of anything is determined; a means of trial. For software.
Computational Reasoning in High School Science and Mathematics A collaboration between Maryland Virtual High School and the Pittsburgh Supercomputing Center.
1 / 27 California Educational Research Association 88 th Annual Conference Formative Assessment: Implications for Student Learning San Francisco, CA November.
Planning for the Solution
Improving the Help Selection Policy in a Reading Tutor that Listens Cecily Heiner, Joseph E. Beck, Jack Mostow Project LISTEN
Lesson 3 McManus COP  You have to tell them ◦ what to do ◦ what to use ◦ in what order to do itand ◦ what to do if your user does not do what.
Monitoring & Evaluation: The concepts and meaning Day 9 Session 1.
Measuring What Matters: Technology & the Assessment of all Students Jim Pellegrino.
MBA7020_01.ppt/June 13, 2005/Page 1 Georgia State University - Confidential MBA 7020 Business Analysis Foundations Introduction - Why Business Analysis.
© 2009 All Rights Reserved Jody Underwood Chief Scientist
Task Analysis Methods IST 331. March 16 th
LInfoVis Winter 2011 Chris Culy Evaluation of visualizations.
 There isn’t a single scientific method, but there is a style of investigation that can be called scientific methodology.  There are 5 main parts that.
Advanced Work with Embedded and Summative Assessment Dr. Steve Broskoske Misericordia University EDU 533 Computer-based Education.
Learning Targets January 21, 2008 Londa Richter & Jo Hartmann TIE.
Walking Through Grade 9 English
Computer Science, Algorithms, Abstractions, & Information CSC 2001.
Of An Expert System.  Introduction  What is AI?  Intelligent in Human & Machine? What is Expert System? How are Expert System used? Elements of ES.
Module 12: Experimental and theoretical probabilities.
1 Taking Notes. 2 STOP! Have I checked all your Source cards yet? Do they have a yellow highlighter mark on them? If not, you need to finish your Source.
When could two experimental probabilities be equal? Question of the day.
Improve Own Learning and Performance This is a very important skill If you can analyse how you work – you can make improvements, which will help you in.
Virtual Fair Template Go through each page and replace the text with your own project information. Each slide gives instruction about how many words can.
GCSE COMPUTER SCIENCE Practical Programming using Python
Plus: Exam Scoring How is it done. How many questions are there
Understanding the ESLRS
Introduction to Eclipse
Lesson Objectives Aims You should be able to:
Database Systems Unit 16.
Requirements Analysis and Specification
Research Methods in Computer Science
Sue Sentance & Philip Howlett
Chapter 12: Automated data collection methods
Experimental Probability Vs. Theoretical Probability
Office of Education Improvement and Innovation
Understanding Randomness
Virtual Fair Template Go through each page and replace the text with your own project information. Each slide gives instruction about how many words can.
Welcome to E-Prime E-Prime refers to the Experimenter’s Prime (best) development studio for the creation of computerized behavioral research. E-Prime is.
An Embedded Experiment to Evaluate the Effectiveness of Vocabulary Previews in an Automated Reading Tutor Jack Mostow, Joe Beck, Juliet Bey, Andrew Cuneo,
Introduction. Conducting statistical investigations to develop learner statistical thinking.

Chapter 23 Deciding how to collect data
What Inquiry Skills Do Scientists Use?
Experimenting with Plants! Facilitator: Kendall Moen
TESTs about a population mean
General Tips for Taking a Science Test
Jack Mostow* and Joseph Beck Project LISTEN (
Regression testing Tor Stållhane.
Implementation of ICT-related solutions
Scientific Method.
A1: Into The Field Grade 6.
Educational Data Mining Success Stories
General Tips for Taking a Science Test
General Tips for Taking a Science Test
General Tips for Taking a Science Test
Presentation transcript:

IERI educational data mining panel Joseph E. Beck Project LISTEN Center for Automated Learning and Discovery Carnegie Mellon University Funding: National Science Foundation

Discussion question “What do data mining tools and methods provide as output, what do they require in terms of input and expertise, which ones seem especially appropriate for educational data mining, and why?”

Discussion question “What do data mining tools and methods provide as output, what do they require in terms of input and expertise, which ones seem especially appropriate for educational data mining, and why?”

Overview Focusing on input since first step Providing three big lessons learned Work done in context of Project LISTEN’s Reading Tutor

Project LISTEN’s Reading Tutor

Why isn’t educational data mining process smoother? Problems with data collection Not collecting sufficiently detailed data Data are a mess Data are observational

Problem: not collecting sufficiently detailed data Solution: Instrument your software! Record everything you can think of You’ll probably find a use for it later Common to think of research questions after the fact It’s nice to be able to answer them

Examples of data to collect Start/end times for sessions, modules, help, etc. Every item the tutor displays/says Why the tutor did that output What else the tutor could have done Student typed input Student mouse clicks 7,600 hours of fine grained data required only 15 GB of disk space (320 GB disk is only $140)

Problem: Data are a mess You’ve recorded everything you can think of, and wind up with something like 16466, Notice, "Tue Apr 10 12:30:20.387 2001", 10763200, "CListener::FinalizeUtterance", "EndUtterance" 16467, Notice, "Tue Apr 10 12:30:20.417 2001", 10763200, "CCapture::WriteWaveFile(int)", "Wrote File: d:\\listen\\cd\\Tue-Sep-19-23-44-58.093-2000\\Capture\\fAT6-6-1994-08-01\\dec-fAT6-6-1994-08-01-Apr10-01-12-30-14-902.wav"

Solution: use a database Database enables tabular representation of data Greatly speeds analyses Removes problem of parsing logfiles

Problem: data are observational Many possible questions Does an intervention work? (What is an intervention?) For whom? In what contexts? Difficult to answer such questions observationally Need experimental trials

Solution Design intervention carefully to answer questions about its effectiveness Two properties Assess its own effectiveness Enable causal conclusions “Embedded experiments”

Example Have intervention to teach student to pronounce a word

Student 3rd grade reading proficiency Intervention How to pronounce a word

Select good intervention words Student 3rd grade reading proficiency Intervention How to pronounce a word Select good intervention words Travelers, Borrowed

3rd grade reading proficiency Intervention How to pronounce a word Student 3rd grade reading proficiency Intervention How to pronounce a word Select good intervention words Travelers, Borrowed Flip coin to decide randomly which word to teach

3rd grade reading proficiency Intervention How to pronounce a word Student 3rd grade reading proficiency Intervention How to pronounce a word Select good intervention words Travelers, Borrowed Flip coin to decide randomly which word to teach Don’t teach “tails” word travelers Teach “heads” word borrowed

3rd grade reading proficiency Intervention How to pronounce a word Student 3rd grade reading proficiency Intervention How to pronounce a word Select good intervention words Travelers, Borrowed Flip coin to decide randomly which word to teach Don’t teach “tails” word travelers Teach “heads” word borrowed Assess both words “Please pronounce ‘travelers’” “Please pronounce ‘borrowed’”

3rd grade reading proficiency Intervention How to pronounce a word Student 3rd grade reading proficiency Intervention How to pronounce a word Select good intervention words Travelers, Borrowed Flip coin to decide randomly which word to teach Don’t teach “tails” word travelers Teach “heads” word borrowed Assess both words “Please pronounce ‘travelers’” “Please pronounce ‘borrowed’” Record details of trial Student, words, success on assessment, type of intervention, etc.

3rd grade reading proficiency Intervention How to pronounce a word Student 3rd grade reading proficiency Intervention How to pronounce a word Select good intervention words Travelers, Borrowed Flip coin to decide randomly which word to teach Don’t teach “tails” word travelers Teach “heads” word borrowed Assess both words “Please pronounce ‘travelers’” “Please pronounce ‘borrowed’” Record details of trial Student, words, success on assessment, type of intervention, etc.

3rd grade reading proficiency Intervention How to pronounce a word Student 3rd grade reading proficiency Intervention How to pronounce a word Select good intervention words Travelers, Borrowed Flip coin to decide randomly which word to teach Don’t teach “tails” word travelers Teach “heads” word borrowed Assess both words “Please pronounce ‘travelers’” “Please pronounce ‘borrowed’” Record details of trial Student, words, success on assessment, type of intervention, etc.

(Trimmed) Example of recorded data User Word Intervention Test performance User3 travelers Pronunciation Correct borrowed None User1 disbelief Spelling delegated Incorrect Can use preferred modeling approach (e.g. logistic regression, decision tree, etc.)

Lessons Instrument and record everything Use a database You can't analyze what isn’t there Use a database Most analysis techniques require tabular format An intervention should be able to assess itself So embed randomized controlled trials in it to allow causal inference