The New Era of Education Big Data



Similar documents
2015 Workshops for Professors

MBA Data Mining & Knowledge Discovery

Data Mining with SAS. Mathias Lanner Copyright 2010 SAS Institute Inc. All rights reserved.

Overview, Goals, & Introductions

Index Contents Page No. Introduction . Data Mining & Knowledge Discovery

Easily Identify Your Best Customers

TDWI Best Practice BI & DW Predictive Analytics & Data Mining

Data Mining Techniques Chapter 9: Market Basket Analysis and Association Rules

Federico Rajola. Customer Relationship. Management in the. Financial Industry. Organizational Processes and. Technology Innovation.

Pathway help: Class Search/Browse Catalog

Keywords Big Data; OODBMS; RDBMS; hadoop; EDM; learning analytics, data abundance.

Data Mining Techniques in CRM

Social Media Implementations

City University of Hong Kong. Information on a Course offered by Department of Information Systems with effect from Semester B in 2013 / 2014

IT1104- Information Systems & Technology (Compulsory)

6. MATERIAL RESOURCE AND SUPPORT NEEDS OF TEACHERS

COURSE RECOMMENDER SYSTEM IN E-LEARNING

HOW EDUCATIONAL TECHNOLOGY TOOLS CAN SOLVE CHALLENGES IN TEACHING AN ONLINE FINANCE COURSE? Presented by: Laura Vatsala & Shubha P Asst.

Multichannel Customer Listening and Social Media Analytics

Predictive Analytics Techniques: What to Use For Your Big Data. March 26, 2014 Fern Halper, PhD

How to use Big Data in Industry 4.0 implementations. LAURI ILISON, PhD Head of Big Data and Machine Learning

How To Use Data Mining For Knowledge Management In Technology Enhanced Learning

QMB Business Analytics CRN Fall 2015 W 6:30-9:15 PM -- Lutgert Hall 2209

QMB Business Analytics CRN Fall 2015 T & R 9.30 to AM -- Lutgert Hall 2209

International Journal of World Research, Vol: I Issue XIII, December 2008, Print ISSN: X DATA MINING TECHNIQUES AND STOCK MARKET

269 Business Intelligence Technologies Data Mining Winter (See pages 8-9 for information about 469)

Master of Science in Health Information Technology Degree Curriculum

THE CHINESE UNIVERSITY OF HONG KONG DEPARTMENT OF TRANSLATION COURSE OUTLINE

Illinois State Board of Education

COURSE SPECIFICATION. Section 1 General Information

Beyond listening Driving better decisions with business intelligence from social sources

Driving Better Marketing Results with Big Data and Analytics David Corrigan, IBM, Director of Product Marketing

IBM Social Media Analytics

Building Data Cubes and Mining Them. Jelena Jovanovic

A SAS White Paper: Implementing a CRM-based Campaign Management Strategy

Course Syllabus. Purposes of Course:

Data Analytics: Exploiting the Data Warehouse

CSCI-599 DATA MINING AND STATISTICAL INFERENCE

Strategies. to Put Instruction Ahead of Technology PREVIEW. Lessons Learned

LAGUARDIA COMMUNITY COLLEGE CITY UNIVERSITY OF NEW YORK DEPARTMENT OF MATHEMATICS, ENGINEERING, AND COMPUTER SCIENCE

WebFOCUS RStat. RStat. Predict the Future and Make Effective Decisions Today. WebFOCUS RStat

Past, present, and future Analytics at Loyalty NZ. V. Morder SUNZ 2014

Framing Business Problems as Data Mining Problems

The Agile Teaching/Learning Methodology and its e-learning Platform

Faculty of Science School of Mathematics and Statistics

Analytics for cross-channel campaigns

CREATING ON-LINE MATERIALS FOR COMPUTER ENGINEERING COURSES

Marketing Strategies for Retail Customers Based on Predictive Behavior Models

City University of Hong Kong. Information on a Course offered by the Department of Management Sciences with effect from Semester A in 2012 / 2013

Data Mining & Knowledge Discovery: Personalization and Profiling Technologies

IBM SPSS Direct Marketing 23

INDIAN STATISTICAL INSTITUTE announces Training Program on Statistical Techniques for Data Mining & Business Analytics

Maximize Sales and Margins with Comprehensive Customer Analytics

Customer Segmentation in Online Shopping Mall

A NAFPhk Professional Development Programme Serving Principals Needs Analysis Programme 360 Feedback

Example application (1) Telecommunication. Lecture 1: Data Mining Overview and Process. Example application (2) Health

IMPORTANCE OF QUANTITATIVE TECHNIQUES IN MANAGERIAL DECISIONS

The Lee Kong Chian School of Business Academic Year 2014 /15 Term 2

MAKING FRIENDS WITH MATH

Big Data Strategies Creating Customer Value In Utilities

The University of Jordan

Predictive Analytics: Extracts from Red Olive foundational course

Choosing A Customer Data Platform

How Organisations Are Using Data Mining Techniques To Gain a Competitive Advantage John Spooner SAS UK

Course No. LW (51) Certificate in Legal Studies Professional Stream Fast Track Provisional Schedule ( )

Healthcare Measurement Analysis Using Data mining Techniques

Course Title: Advanced Topics in Quantitative Methods: Educational Data Science Practicum

Hong Kong University elearning

Hexaware E-book on Predictive Analytics

Class 10. Data Mining and Artificial Intelligence. Data Mining. We are in the 21 st century So where are the robots?

E-LEARNING EDUCATION SYSTEM IN UNIVERSITIES WITH INSTRUCTORS PERSPECTIVES AND A SURVEY IN TURKEY

CSE532 Theory of Database Systems Course Information. CSE 532, Theory of Database Systems Stony Brook University

An Empirical Study of Application of Data Mining Techniques in Library System

Using Data Mining and Machine Learning in Retail

The 7-Step Roadmap for Marketing Automation

Digital INCITE introduces its WiFi analytics platform

LINGNAN UNIVERSITY Department of Marketing and International Business

The Data Mining Process

IBM SPSS Direct Marketing 19

Big Data: Key Concepts The three Vs

Introduction to Data Mining and Machine Learning Techniques. Iza Moise, Evangelos Pournaras, Dirk Helbing

Information Management course

Transcription:

The New Era of Education Big Data Dr. Fok Wai Tung, Wilton Director, e-learning Technology Development Laboratory, Department of Electrical and Electronic Engineering, The University of Hong Kong

1 2 Evolution of ICT for learning Standalone content distribution on-line content distribution 3 interactive learning 4 Mobile Learning 5 Assessment for Learning 6 Educational Data Mining

Problems in traditional teaching Lack of interaction One-way teaching is boring Real-time interactions between teacher and students, students to students become difficult

Interactive teaching and learning for Collecting ideas and feedback Enable students to draw, write and share with class through The lecture screen The device of other students (Peer review) Past Present

Multiple dimension discussion Different groups can discuss different dimensions and share their views on the screen with proper classification, Strengths Weaknesses Opportunities Threats

Objectives of Assessment for Learning HKSAR Education Bureau to guide student approaches to study provide students with feedback on their progress to assess if students have achieved the Intended Learning Outcomes and the level

Formative vs Summative Assessment Formative assessment carry out informally or formally in daily classroom learning and teaching throughout the school term/year. to provide feedback to learning and teaching. Summative assessment conduct at the end of the learning and teaching process. focuses on the product of learning mainly and is primarily used for measuring what a student has learned and how much has been achieved at the end of the school term/yea

Problems in traditional assessment Long feedback loop Difficult to identify students mistakes on time Make learning ineffective Effective assessment demanded days weeks Wait for a few weeks to get teacher s feedback

Assessment as learning interactive quiz Students can answer quiz questions with different attribute and types (e.g. multiple choices and fill-inthe-blanks) Analytical tools: Question level Student level Class level

Analytical tools: Question level (Common mistakes) The common mistakes made by the students can be identified. Teachers can use this tool to know more about the learning progress and make appropriate reflections on the results.

Analytic tool: Class level (performance distribution) Display the distribution of the class performance result with histogram

In the next assessment 1 st Quiz 2 nd Quiz

Analyze the performance of individuals in different topics/areas (Radar chart) E.g. in the Maths e- textbook, it shows Score in each area Current score and cumulated score Changes across years Skill analysis ELEC2815 Macro economic Shape & Space Statistics Micro economic Financial Management Number Year 1 Year 2 Marketing Algebra Accounting Measure

Monitor the learning progress of students 100 90 80 70 60 50 40 30 Number Shape&Space Measure Statistic Algebra 20 10 0 P1 P2 P3 P4 P5 P6

Assessment as learning interactive quiz Advantages: Enhance assessment efficiency More statistical information Shorten Long feedback loop from weeks to minutes Conduct test Mark script Distribute result Explain answer Real-time assessment and give feedback

In book assessment EMADS E-textbook

Educational Data Mining

20 years ago When network point-of-sales machine became popular, customer shopping behavior can be easily captured Customer profiling/ segmentation Market basket analysis Loyalty program Personalized offering Sales prediction

Education data mining Training Institutes Schools E-publisher Cloud-based Educational Data Mining and Learning analytics Service Platform Big Data Warehouse Student profiling/ segmentation Question analysis/ association (Adaptive assessment) Personalized course/ Course Recommendation Learning State Analysis Performance prediction

I can read students brain now

Market Basket Analysis What is Market Basket Analysis? Market basket analysis is a tool of knowledge discovery about co-occurrence of nominal or categorical items. It is a data mining technique to derive association between two data sets.

Association rules criteria To obtain the association rules, we usually apply two criteria: Minimum support Minimum confidence E.g. We conclude there is an association when support is greater than a threshold, e.g. > 80% Buy\Al so buy A B C A - 20% 10% B 40% - 80% C 90% 30% - 0.9 0.8 0.7 0.6 0.5 0.4 0.3 0.2 0.1 0 A B C C B A Rule1: Buy C also buy B Rule2: Buy A also buy C (Ref: http://people.revoledu.com/kardi/tutorial/marketbasket/marketbasketanalysis.htm)

Application #1: Student profiling association of different subjects Demographic data Decision tree engine Assessment Skill analysis ELEC2815 Macro economic Skill analysis ELEC2815 Macro economic Skill analysis ELEC2815 Financial Management Financial Year 1 Management Year 2 Financial Year 1 Management Year 2 Accounting Year 1 Year 2 Accounting Macro economic Micro economic Micro economic Marketing Marketing Accounting Students Profile Micro economic Marketing

Application #2: Adaptive Question Adaptive Question Engine Engine

Application #3: Student clustering/ learning behavior analysis

Advantage of Education Data Mining

The next focus of e-learning development Hardware Devices Infrastructure WiFi Contents EMADS Educational Data Mining

Workshop Date: 24 Jan 2015 (Sat) Time: 10am-12pm 10am etextbook and education data mining 11am Mobile Device Management Venue: HKU Centennial Campus Room Registration: http://elearning.eee.hku.hk

Q&A