R Comparing Presentation Summaries: Slides vs. Reading vs. Listening Liwei He, Elizabeth Sanocki Anoop Gupta, Jonathan Grudin Collaboration and Multimedia.

Slides:



Advertisements
Similar presentations
11/4/1999ACM Multimedia 991 Auto-Summarization of Audio-Video Presentations Li-wei He, Elizabeth Sanocki Anoop Gupta, Jonathan Grudin Collaboration and.
Advertisements

Critical Reading Strategies: Overview of Research Process
PowerPoint Presentations
Cornell Notes.
Microsoft Office 2007 Microsoft Excel Collaboration Feature Using SharePoint and Excel Services.
[Title of meeting] [Name of sponsor] [Date] For guidance on working with PowerPoint and reformatting slides, click on Help, then Microsoft PowerPoint Help,
DO NOT PLACE ANY TEXT OR GRAPHICS ABOVE THE GUIDELINE SHOWN DO NOT PLACE ANY TEXT OR GRAPHICS BELOW THE GUIDELINE SHOWN TO EDIT GRAPHICS IN THE MASTER.
Master Teachers’ Guild ATTENDANCE & LECTURE CAPTURE John H. Becker, Ph.D. 9/27/11.
Microsoft Excel Working with Excel Lists, Subtotals and Pivot Tables.
Evaluation of Speak Project 2b Due March 24th. Overview Experiments to evaluate performance of your audioconference (proj2) Focus not only on how your.
Paper Title Your Name CMSC 838 Presentation. CMSC 838T – Presentation Motivation u Problem paper is trying to solve  Characteristics of problem  … u.
Welcome to Turnitin.com’s Peer Review! This tour will take you through the basics of Turnitin.com’s Peer Review. The goal of this tour is to give you.
Video summarization by video structure analysis and graph optimization M. Phil 2 nd Term Presentation Lu Shi Dec 5, 2003.
1 Dr. Xiao Qin Auburn University Spring, 2011 COMP 7370 Advanced Computer and Network Security Homework.
Orientation to Online Learning An Instructors Guide.
The following sample slides are from two different presentations I created on telephone communications.  Slide 3 has hyperlinks embedded to allow the.
Jennifer O’Donnell EDUC 681 Survey of Instructional Technology Applications Adobe Captivate.
Simon Tucker NLP Presentation Efficient user-centred access to multimedia meeting content Simon Tucker and Steve Whittaker University.
PYP002 Intro.to Computer Science Microsoft Word1 Lab 07 Creating Documents with Efficiency and Consistency.
Introduction to the Periodic Table
User Benefits of Non-Linear Time Compression Liwei He and Anoop Gupta Microsoft Research.
Website Redesign Features: Simple Navigation New Professional Look Easily Edit Content on Every Page Post New Jobs / Apply From Website Integration of.
Instructional Design Process Connect Your Website: Application Program Interfaces Jullien Gordon Aneto Okonkwo Gilbert Zaragoza.
Research paper: Web Mining Research: A survey SIGKDD Explorations, June Volume 2, Issue 1 Author: R. Kosala and H. Blockeel.
Multimedia- Microsoft Power Point ADE100- Computer Literacy Lecture 22.
Unit Portfolio Presentation Linda Hill & Jonna Wallis
Michael Wybrow, 23 rd April 2009 Scrolling Behaviour with Single- and Multi-column Layout.
Collaboration and Education Group Anoop GuptaJonathan Grudin David BargeronSteven White Liwei HeYong Rui.
Academic Communication Lesson 4 Please pick up two handouts from the front desk. You will also need the previous handouts “Typical Organization of …”
The Browser Evaluation Test A Proposal Pierre Wellner, Mike Flynn IDIAP, September 2003.
What is Usability? Usability Is a measure of how easy it is to use something: –How easy will the use of the software be for a typical user to understand,
How People with Disabilities Access the Web Web Design – Sec 2-5 Part or all of this lesson was adapted from the University of Washington’s “Web Design.
Using Multimedia Tools Mark Grabe. Copyright © Houghton Mifflin Company. All rights reserved.7-2 Classification of Student Projects n Embellished documents.
Scientific Paper. Elements Title, Abstract, Introduction, Methods and Materials, Results, Discussion, Literature Cited Title, Abstract, Introduction,
Cornell note taking stimulates critical thinking skills. Note taking helps students remember what is said in class. A good set of notes can help students.
Insight from Interactions Business Analyzer 1 INSIGHT FROM INTERACTIONS Business Analyzer Overview.
Edmodo Made Easy By: Susan O’Day.
Welcome to the Seminar Professor Fred Bittner.  Review Key Terms  Introduce Yourself to your classmates  Read Chapters 1 and 2 in Criminal Investigation.
 Contact Information |  Objective |  Career Highlights  Work Experience |  Computer Skills |  Education |  Training |  Professional Affiliations.
LOGO Summarizing Conversations with Clue Words Giuseppe Carenini, Raymond T. Ng, Xiaodong Zhou (WWW ’07) Advisor : Dr. Koh Jia-Ling Speaker : Tu.
1 Enhancing E-Learning with Interactive Multimedia Information Resources Management Journal, 16(4), 1-14, Oct-Dec Reporter Yu-Wen Hsiao.
Reading for a Purpose: Strategies to Make Your Reading Time More Effective and Efficient Karen L. Wold, M.S.Ed. Learning Disabilities Specialist Division.
FORESTUR How to work… …with this training platform? …with this methodology?
The STAR Strategy for Cornell Notes
CSC USI Class Meeting 10 November 9, 2010.
How did you learn the skill of note taking? How can this skill contribute to your success? Quickly jot an answer to these questions: Now, QUICKLY, share.
ITCS 6265 Details on Project & Paper Presentation.
Guidelines for Development A Visual Guide. The Teacher: Innovative teaching methods More efficient student learning Need internet, software tools and.
Internet Literacy Evaluating Web Sites. Objective The Student will be able to evaluate internet web sites for accuracy and reliability The Student will.
How to be a successful APES student. Do Assigned Reading 1.Get perspective 2.First Reading 3.Review of First Reading 4.Second Reading.
MMM2005The Chinese University of Hong Kong MMM2005 The Chinese University of Hong Kong 1 Video Summarization Using Mutual Reinforcement Principle and Shot.
E-Learning: Concepts T.Mohammed Hassan. E-learning, Web-based learning E-learning is mostly associated with activities involving computers and interactive.
1301 Spring 2016 Day 4 Lessons. What to expect today: Questions over the reading Check Attendance Summary Thesis Statements First Draft of the summary.
SOC 110 TUTORIAL Innovative Education SOC 110 Entire Course (2 Set) FOR MORE CLASSES VISIT This Tutorial contains 2 Set of Papers.
SOC 110 TUTORIAL Success Secrets/ soc110tutorial.com
Computing Fundamentals
Simon Tucker and Steve Whittaker University of Sheffield
SCORM Compliant Authoring Tool
What you’ve always wanted to know about…
Flipped Learning for a MBA Marketing Project
ENG 1450 – September 30, 2015 (guest instructor)
Module 5: Data Cleaning and Building Reports
Your title Abstract Introduction: Background/Context Methods
Internet Literacy Evaluating Web Sites.
COURSE INSTRUCTIONS Minimum Requirements Microsoft Windows 2000
Your name Your faculty mentor’s name Department
Smart Subtitles with Personalized Quizzes for Vocabulary Building
SCORM Compliant Authoring Tool Developed at An-Najah University
Your name Your faculty mentor’s name Department
Presentation transcript:

r Comparing Presentation Summaries: Slides vs. Reading vs. Listening Liwei He, Elizabeth Sanocki Anoop Gupta, Jonathan Grudin Collaboration and Multimedia Group Microsoft Research Liwei He, Elizabeth Sanocki Anoop Gupta, Jonathan Grudin Collaboration and Multimedia Group Microsoft Research

CHI Motivation Multimedia presentations are being archived for on-demand access  University courses  Corporate training and seminars Effective summarization and skimming can help users utilize time better Multimedia presentations are being archived for on-demand access  University courses  Corporate training and seminars Effective summarization and skimming can help users utilize time better

CHI Video Skimming Techniques Time compression  1.5 – 2.5 saving factor at most Video summary  2.5+ saving factor is possible Time compression  1.5 – 2.5 saving factor at most Video summary  2.5+ saving factor is possible

CHI Previous Summarization Study Compared 4 video summary techniques  1 by authors of the presentation  3 by computer algorithms  Pre- and post quizzes and subjective ratings  More details in our paper in ACM Multimedia 99  “Auto-Summarization of Audio-Video Presentations” Compared 4 video summary techniques  1 by authors of the presentation  3 by computer algorithms  Pre- and post quizzes and subjective ratings  More details in our paper in ACM Multimedia 99  “Auto-Summarization of Audio-Video Presentations”

CHI Auto Summary Study Results All four summaries improve quiz scores  Human-generated summary is significantly better than computers  No difference among computer-generated summaries Overall, all are appreciated by subjects All four summaries improve quiz scores  Human-generated summary is significantly better than computers  No difference among computer-generated summaries Overall, all are appreciated by subjects

CHI Questions Raised What about other forms of summary?  Amount of information from slides?  Skimming text transcript vs. watching video?  Transcripts with key points highlighted vs. video summaries? What about other forms of summary?  Amount of information from slides?  Skimming text transcript vs. watching video?  Transcripts with key points highlighted vs. video summaries?

CHI Experimental Design (1) 4 summarization techniques  PowerPoint slides only  Raw text transcripts  Transcripts with key points highlighted  Author-generated video summaries 4 summarization techniques  PowerPoint slides only  Raw text transcripts  Transcripts with key points highlighted  Author-generated video summaries

CHI Experimental Design (2) To compare summarization techniques  Objective measure: quiz score improvement before and after watching a summary  Subjective measure: user ratings 4 talks chosen from Microsoft training site  Original presenters wrote quiz questions To compare summarization techniques  Objective measure: quiz score improvement before and after watching a summary  Subjective measure: user ratings 4 talks chosen from Microsoft training site  Original presenters wrote quiz questions

CHI Experimental Design (3) 24 Microsoft employees were subjects  Quiz before and after each summary  Watches 4 summaries, each of a different type  Summary types and talks are counter-balanced within each subject 24 Microsoft employees were subjects  Quiz before and after each summary  Watches 4 summaries, each of a different type  Summary types and talks are counter-balanced within each subject

CHI PowerPoint Slides Only

CHI Raw Text Transcript

CHI Text Transcript w/ Highlights

CHI Video Summary

CHI Four Presentations Used P1P2P3P4 Length (min) # of slides # of pages Highlighted19%24%25%20%

CHI Quiz Score Improvement (1) Plot by summary types

CHI Quiz Score Improvement (2) Highlight text and video summary > (at p (at p<0.001) slide only and raw text Highlight text and video summary > (at p (at p<0.001) slide only and raw text

CHI Quiz Score Improvement (3) Video summary > highlight text ? p = Video summary > highlight text ? p = 0.087

CHI Quiz Score Improvement (4) Plot by presentations

CHI Subjective Ratings (1) Slide only Raw text Highlight text Video summary Synopsis Key points 41%62%64%69% Skip talk Concise Coherent Table by summarization techniques

CHI Subjective Ratings (2) Highlight text and video summary > (at p=0.01) slide only and raw text Highlight text and video summary > (at p=0.01) slide only and raw text Slide only Raw text Highlight text Video summary Synopsis Key points 41%62%64%69% Skip talk Concise Coherent

CHI Subjective Ratings (3) Slide only Raw text Highlight text Video summary Synopsis Key points 41%62%64%69% Skip talk Concise Coherent Highlight text and video summary are not significantly different (at p=0.05) Highlight text and video summary are not significantly different (at p=0.05)

CHI Subjective Ratings (4) Slide only Raw text Highlight text Video summary Synopsis Key points 41%62%64%69% Skip talk Concise Coherent Raw text, highlight text, and video summary > (at p=0.05) slide only Raw text, highlight text, and video summary > (at p=0.05) slide only

CHI User Comments 13 out of 24 like video summaries  “It is more enjoyable listening and seeing the presenter.” 11 prefer highlighted transcripts  “I liked having the option of being able to get more detailed info when I need it.” 13 out of 24 like video summaries  “It is more enjoyable listening and seeing the presenter.” 11 prefer highlighted transcripts  “I liked having the option of being able to get more detailed info when I need it.”

CHI Conclusions Effective summary techniques are key This study compared 4 summarization techniques  Slide only does not work well for most talks  Raw text transcript is hard to read  Human produced summaries work better Effective summary techniques are key This study compared 4 summarization techniques  Slide only does not work well for most talks  Raw text transcript is hard to read  Human produced summaries work better

CHI Conclusions (cont.) Slide authoring style makes a difference What to do?  For authors: tools to generate summaries  For users: interactive and intelligent video browser Slide authoring style makes a difference What to do?  For authors: tools to generate summaries  For users: interactive and intelligent video browser

CHI Compare with AutoSum Study (1) Current study and auto summary study are comparable  4 talks and quiz are the same  Both have author-generated summary  Slides are shown in all conditions for both  Evaluation methods are the same Current study and auto summary study are comparable  4 talks and quiz are the same  Both have author-generated summary  Slides are shown in all conditions for both  Evaluation methods are the same

CHI Compare with AutoSum Study (2) AutoSum Study Current Study

CHI Compare with AutoSum Study (3) SA*ASO Synopsis Key points 56%76%69%41% Skip talk Concise Coherent Subject ratings (AutoSum vs. Current)

CHI Compare with AutoSum Study (4) SA*ASO Synopsis Key points 56%76%69%41% Skip talk Concise Coherent A* in AutoSum consistently > A

CHI Compare with AutoSum Study (3) SA*ASO Synopsis Key points 56%76%69%41% Skip talk Concise Coherent Slide-based summary (S) > slide only (SO)