Jozef Tvarožek Fifth European Conference on Technology Enhanced Learning Sustaining TEL EC-TEL 2010, Barcelona September 28 – October 1, 2010.

Slides:



Advertisements
Similar presentations
4th International Conference on e-Learning and
Advertisements

IB Portfolio Tasks 20% of final grade
Web Passive Voice Tutor: an Intelligent Computer Assisted Language Learning System over the WWW Maria Virvou & Victoria Tsiriga Department of Informatics,
Creating a Similarity Graph from WordNet
Lesson 5: Describing a Distribution Displayed in a Histogram
Congruency to Math Standards How do we successfully monitor and support our teachers when we can’t be an expert in every content area?
GENERATING AUTOMATIC SEMANTIC ANNOTATIONS FOR RESEARCH DATASETS AYUSH SINGHAL AND JAIDEEP SRIVASTAVA CS DEPT., UNIVERSITY OF MINNESOTA, MN, USA.
Student simulation and evaluation DOD meeting Hua Ai 03/03/2006.
Coding Schemes for Collaborative Learning Dialogs Chih-yu Chao Dialogs on Dialogs Reading Group March 4 th, 2005.
Web as Graph – Empirical Studies The Structure and Dynamics of Networks.
BTW (“By The Way…”) Information Annotation By Rudd Stevens, Jason Endo University of San Francisco.
What can humans do when faced with ASR errors? Dan Bohus Dialogs on Dialogs Group, October 2003.
Cognitive Linguistics Croft & Cruse 10 An overview of construction grammars (part 1, through )
1 error handling – Higgins / Galatea Dialogs on Dialogs Group July 2005.
Providing Tutoring Service through Accumulating Interaction Data Chi-Jen LIN Fo Guang University, Taiwan.
1 CS 430 / INFO 430 Information Retrieval Lecture 24 Usability 2.
Steering Group. Past work Ideas From Visits Strategies –what are strategies –how do they relate to interactional properties Discreet states & transition.
BTW Information Annotation By Rudd Stevens, Jason Endo.
Taxonomy of Effortless Creation of Algorithm Visualizations Petri Ihantola, Ville Karavirta, Ari Korhonen and Jussi Nikander HELSINKI UNIVERSITY OF TECHNOLOGY.
Assuming Accurate Layout Information for Web Documents is Available, What Now? Hassan Alam, Rachmat Hartono, Aman Kumar, Fuad Rahman, Yuliya Tarnikova.
Xiaomeng Su & Jon Atle Gulla Dept. of Computer and Information Science Norwegian University of Science and Technology Trondheim Norway June 2004 Semantic.
Strategies to Promote Motivation in the Mathematics Classroom
The Social Web: A laboratory for studying s ocial networks, tagging and beyond Kristina Lerman USC Information Sciences Institute.
Enhance legal retrieval applications with an automatically induced knowledge base Ka Kan Lo.
Development of New Science Standards:
Integrating Educational Technology into Teaching Integrating Instructional Software into Teaching & Learning.
Interactive Science Notebooks: Putting the Next Generation Practices into Action
10 December, 2013 Katrin Heinze, Bundesbank CEN/WS XBRL CWA1: DPM Meta model CWA1Page 1.
Good Slide vs. Bad Slide - The Bad 1.Title is not changed. 2.The Challenge statement is not "stated as an instructional dilemma or problem." 3.Although.
Glassner, A., Cohen (Sayag), E., Nathan, N., & Vardi-Rath, E. Kaye Academic College of Education, Israel The 35 th ATEE Conference Budapest, 26 August,
Semantic Interoperability Jérôme Euzenat INRIA & LIG France Natasha Noy Stanford University USA.
Path C: The Integrated Classroom Lead Teacher: Wendy Freebersyser.
UCDMP Saturday Series Secondary Session 3 January 26, 2013.
THE PEDAGOGICAL DESIGN OF TECHNOLOGY ENHANCED COLLABORATIVE LEARNING Minna Lakkala Centre for Research on Networked Learning and Knowledge Building, University.
Jozef Tvarožek and Mária Bieliková Enhancing Learning with Off-Task Social Dialogues EC-TEL 2010, Barcelona September 30, 2010 Slovak University of Technology.
Seeking and providing assistance while learning to use information systems Presenter: Han, Yi-Ti Adviser: Chen, Ming-Puu Date: Sep. 16, 2009 Babin, L.M.,
1 A Local and Remote Radio Frequency Identification Learning Environment Andrew Shields & David Butcher Wireless and Mobility Research Group, Institute.
CONCEPT DEVELOPMENT LESSONS Region 5 Mathematics Network Conference September 16, 2013.
ENGL 1101 A LIBRARY SKILLS PRACTICE SEPT SEMINAR Chapter 5 pp (Choosing a topic & preparing for research) pp (Research resources &
An-Te NGUYEN, Bich-Thuy DONG THI, Duc-Long LE 1 Fifth European Conference on Technology Enhanced Learning (EC-TEL 2010) Sustaining TEL: From Innovation.
Theory and Application of Database Systems A Hybrid Approach for Extending Ontology from Text He Wei.
Asking better questions Asking questions better. 1.Why do you ask questions in lessons? 2.What do you think is a strength of your current questioning.
A Word at a Time: Computing Word Relatedness using Temporal Semantic Analysis Kira Radinsky (Technion) Eugene Agichtein (Emory) Evgeniy Gabrilovich (Yahoo!
Beyond the Basics Alan Shurling. More Software tools are available than your basic suit We as teacher must utilize these tools.
Mining fuzzy domain ontology based on concept Vector from wikipedia category network.
Chapter 3 Teaching with Instructional Software Indiana Wesleyan University Former Student (used by permission)
PIER Research Methods Protocol Analysis Module Hua Ai Language Technologies Institute/ PSLC.
Modeling Student Benefits from Illustrations and Graphs Michael Lipschultz Diane Litman Intelligent Tutoring Systems Conference (2014)
How People Learn – Brain, Mind, Experience, and School (Bransford, Brown, & Cocking, 1999) Three core principles 1: If their (students) initial understanding.
Endangered Species A Collaborative Teaching Unit.
Shridhar Bhalerao CMSC 601 Finding Implicit Relations in the Semantic Web.
Working Memory and Learning Underlying Website Structure
Evaluation of the NSDL and Google for Obtaining Pedagogical Resources Frank McCown, Johan Bollen, and Michael L. Nelson Old Dominion University Computer.
Harvesting Social Knowledge from Folksonomies Harris Wu, Mohammad Zubair, Kurt Maly, Harvesting social knowledge from folksonomies, Proceedings of the.
Named Entity Disambiguation on an Ontology Enriched by Wikipedia Hien Thanh Nguyen 1, Tru Hoang Cao 2 1 Ton Duc Thang University, Vietnam 2 Ho Chi Minh.
THE SEMANTIC WEB By Conrad Williams. Contents  What is the Semantic Web?  Technologies  XML  RDF  OWL  Implementations  Social Networking  Scholarly.
HMS Academy HMS Academy Medical Education Day Critical Thinking October 2011.
1 Model-based Development and Evolution of Information Systems Quality of models and modeling languages John Krogstie Professor, IDI, NTNU UPC,
Stories and lessons from a study of the enhancement of learning process on a social work degree programme Gary Clapton University of Edinburgh.
Integrating new technology into the classroom can be beneficial to teachers and can also improve student achievement By Kelly Mason.
Using Natural Language Processing to Analyze Tutorial Dialogue Corpora Across Domains and Modalities Diane Litman, University of Pittsburgh, Pittsburgh,
4:00 – 4:05pm Welcome and Introductions 4:05 – 4:20pm Ice Breaker 4:20-4:30 pm Norms 4:30 – 5:00pm Journaling 5:00 – 5:30 pm Enquiry activity stations.
CALL. Assignment Assignment 2. Write a paper on one aspect of CALL. Due June 12th 2500 words (target) Check yellow sheet for departmental policy on late.
The 15th International Semantic Web Conference Kobe, Japan.
Irene-Angelica Chounta, Bruce M. McLaren Carnegie Mellon University
Human Computer Interaction Lecture 21,22 User Support
Kenneth Baclawski et. al. PSB /11/7 Sa-Im Shin
SMA5422: Special Topics in Biotechnology
Dialogue-Learning Correlations in Spoken Dialogue Tutoring
KNOWLEDGE MANAGEMENT (KM) Session # 37
Presentation transcript:

Jozef Tvarožek Fifth European Conference on Technology Enhanced Learning Sustaining TEL EC-TEL 2010, Barcelona September 28 – October 1, 2010

EC-TEL 2010, September 28 – October 1, 2010, Barcelona, Spain2

Keynote – Judy Kay EC-TEL 2010, September 28 – October 1, 2010, Barcelona, Spain3

Best paper Myroslava O. Dzikovska et al: Content, Social, and Metacognitive Statements: An Empirical Study Comparing Human-Human and Human- Computer Tutorial Dialogue pp. 93–108. EC-TEL 2010, September 28 – October 1, 2010, Barcelona, Spain4

Design Three conditions: – ITS that asks students for explanations – ITS that gives away correct answer – Human tutor in computer-mediated setting Explored the role of: – Student produced content to predict learning – Social and metacognitive utterances EC-TEL 2010, September 28 – October 1, 2010, Barcelona, Spain5

Learning environment Constructed a computer mediated learning environment in which students work on exercises and human tutor can help them Based on the human-human interaction data, they created a tutorial dialog system that replaces human tutor with automatically generated feedback EC-TEL 2010, September 28 – October 1, 2010, Barcelona, Spain6

Dialog coding Content: – There is a batter and bulb in circuit 1. Metacognition – Positive: I get it. ; Oh, o.k. – Negative: I don’t understand. Social – Positive: Haha; Hi, how are you doing? – Negative: Because I said so.; No.; You’re stupid. EC-TEL 2010, September 28 – October 1, 2010, Barcelona, Spain7

Results – content words H-H: 5.68 words per turn – Percentage of content words positively correlated with learning gain H-C: 6.13, 5.66 words per turn – content words BASE:not / FULL:positively correlated with learning gain – In BASE, students may be struggling with terminology; is the tutor’s feedback important or trivial? EC-TEL 2010, September 28 – October 1, 2010, Barcelona, Spain8

Results – metacognitive/social H-H: mostly positive (acks, rapport) – Positive statements negatively correlated with learning gain H-C: mostly negative (frustration; interpret.) – BASE:almost none; FULL:mostly negative; Both negative and positive were negatively correlated with learning gain – Avg. learning gain of students who generated any negative social dialog (52%) vs those that did not (67%) … EC-TEL 2010, September 28 – October 1, 2010, Barcelona, Spain9

Poster session EC-TEL 2010, September 28 – October 1, 2010, Barcelona, Spain10

Selected paper (1) Phillip Scholl et al: Extended Explicit Semantic Analysis for Calculating Semantic Relatedness of Web Resources (pp. 324–339) Explicit Semantic Analysis (ESA) – similarities between documents or terms based on similarities to documents of a reference corpus. Extended ESA uses further semantic properties of Wikipedia (link structure and categorization) EC-TEL 2010, September 28 – October 1, 2010, Barcelona, Spain11

Typically we do term similarity What if you don’t know the domain’s terminology used by experts … concepts similarity Crokodil – learning materials organized in Knowledge Network (Semantic Network) Snippets (more specific that pages, 120 vs 1600 terms) EC-TEL 2010, September 28 – October 1, 2010, Barcelona, Spain12

Extended ESA Extension of ESA: – Utilize Wikipedia’s article link graph 7% improvement – Utilize Wikipedia’s category structure 5.4% improvement – Combination of these two -5% to -8% improvement ESA results: avg. precision: (sd=0.252) EC-TEL 2010, September 28 – October 1, 2010, Barcelona, Spain13

Conference dinner EC-TEL 2010, September 28 – October 1, 2010, Barcelona, Spain14

Selected paper (2) Dimitra Tsovaltzi et al: Learning from Erroneous Examples: When and How Do Students Benefit from Them? (pp. 357–373) Erroneous examples are worked solutions that include one or more errors that the student is asked to detect and/or correct. – Teachers are reluctant to discuss errors in classroom to prevent assimilation as good. – TIMMS, Japan outperforms western world. EC-TEL 2010, September 28 – October 1, 2010, Barcelona, Spain15

Internet as a learning resource EC-TEL 2010, September 28 – October 1, 2010, Barcelona, Spain16

EC-TEL 2010, September 28 – October 1, 2010, Barcelona, Spain17

EC-TEL 2010, September 28 – October 1, 2010, Barcelona, Spain18

EC-TEL 2010, September 28 – October 1, 2010, Barcelona, Spain19

Jozef Tvarožek Fifth European Conference on Technology Enhanced Learning Sustaining TEL EC-TEL 2010, Barcelona September 28 – October 1, 2010