Brendan JouHongzhi LiJoe EllisDan Morozoff-AbezgauzShih-Fu Chang Exploring Multi-Granular News Events (Broadcast Video + Curated Web)

Slides:

Advertisements

Similar presentations

Cindy Royal Associate Professor Texas State University facebook.com/cindyroyal linkedin.com/in/cindyroyal Curating Stories with.

Advertisements

PROQUEST SIRS ISSUES RESEARCHER INSIGHT INTO TODAYS LEADING ISSUES Online Tutorial sks.sirs.com | proquestk12.com.

Data Mining and the Web Susan Dumais Microsoft Research KDD97 Panel - Aug 17, 1997.

Support.ebsco.com Nursing Reference Center Tutorial.

Generation of Multimedia TV News Contents for WWW Hsin Chia Fu, Yeong Yuh Xu, and Cheng Lung Tseng Department of computer science, National Chiao-Tung.

Telling Your Story Through the Media

Automatic Timeline Generation from News Articles Josh Taylor and Jessica Jenkins.

Types of News Stories It is important to distinguish the various types of news stories because the term “news” is very broad. In categorizing news, we.

Yansong Feng and Mirella Lapata

Exploring the news | Always multi- source, multimodal and personalized.

Real Time Information.

“How Can Research Help Me?” Please make SURE your notes are similar to what I have written in mine.

The Storyline Ontology

1.Accuracy of Agree/Disagree relation classification. 2.Accuracy of user opinion prediction. 1.Task extraction performance on Bing web search log with.

DSPIN: Detecting Automatically Spun Content on the Web Qing Zhang, David Y. Wang, Geoffrey M. Voelker University of California, San Diego 1.

Automatic Discovery of Useful Facet Terms Wisam Dakka – Columbia University Rishabh Dayal – Columbia University Panagiotis G. Ipeirotis – NYU.

Web 2.0 The Read/Write Web. History Tim Berners-Lee: World Wide Web 1989 Dream of sharing information back and forth Mosaic Web browser in 1993 Writing.

Possible Research Sources Stage #2 Which resources are the best to use for my topic or project?

Dee Lucas Linda Dean Cocoa Beach Jr/Sr High WEB 2.0.

Web 2.0 The Read/Write Web. Marc Prensky Terms Digital Natives Digital Natives Digital Immigrants--maintain a pre-digital accent Digital Immigrants--maintain.

Mining the web to improve semantic-based multimedia search and digital libraries

Daniela Cappetta Csc 101 Week 2. Blogs A blog (a contraction of the term "Web log") is a Web site, usually maintained by an individual [1], with regular.

Blogosphere  What is blogosphere?  Why do we need to study Blog-space or Blogosphere?

MCJ 131 Interactive Media Design Candace Lee Egan Exploring Convergence and the Web Documentary.

Video summarization by graph optimization Lu Shi Oct. 7, 2003.

Blogs. Short for Weblog Blogs are simple web pages often made up short, informal and frequently updated posts.

1 Lessons Learned From Building a Terabyte Digital Video Library Presented by Jia Yao Multimedia Communications and Visualization Laboratory Department.

SOCIAL NETWORKS AND THEIR IMPACTS ON BRANDS Edwin Dionel Molina Vásquez.

Beyond Google Search Using Google Search tools to their potential.

TO RECOGNIZE HOW BIAS MAY OCCUR IN NEWS REPORTING Bias In The News.

The PrestoSpace Project Valentin Tablan. 2 Sheffield NLP Group, January 24 th 2006 Project Mission The 20th Century was the first with an audiovisual.

Title Your Name Date Teacher, Class, and Period. Type in key words from your research question Example of an event in the novel that answers your research.

Pete Bohman Adam Kunk. What is real-time search? What do you think as a class?

Incident Threading for News Passages (CIKM 09) Speaker: Yi-lin,Hsu Advisor: Dr. Koh, Jia-ling. Date:2010/06/14.

Journalism 105: Newspaper Design Vocabulary. large letter usually at the start of an article.

Comparative Text Mining Q. Mei, C. Liu, H. Su, A. Velivelli, B. Yu, C. Zhai DAIS The Database and Information Systems Laboratory. at The University of.

1 WCAG2 for ICT Working Draft.

Web-Assisted Annotation, Semantic Indexing and Search of Television and Radio News (proceedings page 255) Mike Dowman Valentin Tablan Hamish Cunningham.

Contextual Ranking of Keywords Using Click Data Utku Irmak, Vadim von Brzeski, Reiner Kraft Yahoo! Inc ICDE 09’ Datamining session Summarized.

Prof. Thomas Sikora Technische Universität Berlin Communication Systems Group Thursday, 2 April 2009 Integration Activities in “Tools for Tag Generation“

Discovering Computers Fundamentals, Third Edition CGS 1000 Introduction to Computers and Technology Spring 2007.

Mike Tung - founder+ceo. What is diffbot? We apply computer vision techniques to analyzing web pages, making web data useful for content applications.

Template by Modified by Bill Arcuri, WCSD Chad Vance, CCISD Click Once to Begin JEOPARDY! Seventh Grade Benchmark One.

WEBSITE CRITIQUE On Scientific News Websites. IFLSCIENCE.com.

1 Applications of video-content analysis and retrieval IEEE Multimedia Magazine 2002 JUL-SEP Reporter: 林浩棟.

2015/12/121 Extracting Key Terms From Noisy and Multi-theme Documents Maria Grineva, Maxim Grinev and Dmitry Lizorkin Proceeding of the 18th International.

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.

Using Web 2.0 Technologies to Create Classroom Websites: Session 3.

Pascal Kelm Technische Universität Berlin Communication Systems Group Thursday, 2 April 2009 Video Key Frame Extraction for image-based Applications.

Twitter: What can you do in 140 characters or less? COM 160: New Communications Technologies.

Web 2.0 is the second generation of Internet-based services that emphasize online collaboration and sharing among users.

Improving Your County CMS Topics & Events Pages Jeanne Wiebke Extension Information Technology November 30, 2006.

Author’s Purpose (Why? Just why?). Author’s Purpose: the reason an author writes a particular work. A writer’s purpose could be any one of the following:

AQUAINT Mid-Year PI Meeting – June 2002 Integrating Robust Semantics, Event Detection, Information Fusion, and Summarization for Multimedia Question Answering.

A POCKET GUIDE TO PUBLIC SPEAKING 4 TH EDITION Chapter 9 Locating Supporting Material.

Social Media & Social Networking 101 Canadian Society of Safety Engineering (CSSE)

Find Latest News A collection of innovative and powerful news brands that deliver compelling, diverse and visually engaging.

LECTURE 10: TEXT AS DATA April 13, 2015 SDS 136 Communicating with Data Portions of this slide deck adapted from J.Chuang University of Washington.

Data Management: Data Analysis Types of Data Analysis at USGS There are several ways to classify Data Analysis activities at USGS, and here are some of.

Literary Genres are a category or certain kind of literature or writing. These categories are identified by examining the characteristics of each piece.

Multi-Source Information Extraction Valentin Tablan University of Sheffield.

A Side Discussion: The Power of Characters

Reading Genres.

Quick Write Do you prefer fiction text vs. non-fiction text? Explain your answer.

Description and/or Definition

Description and/or Definition

Content Augmentation for Mixed-Mode News Broadcasts Mike Dowman

Description and/or Definition

ProQuest Databases.

Presentation transcript:

Brendan JouHongzhi LiJoe EllisDan Morozoff-AbezgauzShih-Fu Chang Exploring Multi-Granular News Events (Broadcast Video + Curated Web)

News Rover’s Unique Capabilities 1. Event-based organization of news content 1. Video-based events 2. Wikipedia-based events 2. Broadcast television news aggregation 3. Analysis of “Major Players” in news events

Two Types of News Events Long Running News Event : ”2014 Northern Iraq Offensive” Breaking News Events Civilians FleeingU.S. AirstrikesReport of Killings Local News Event Boston Building on Fire Breaking News Event A specific event at a particular moment in time. Long Running News Event: A collection of related events and commentary that occurs over a longer span of time.

News Rover Events Video-Based EventsWikipedia-Based Events Address the need for coverage of breaking news events, and one-off stories that are not covered by curated news sources. Addresses the need for coverage of long-term news stories that pertain to a broad topic or unify many smaller news events. Ebola Patient Treated in NYC Isreal-Hamas Cease Fire Voided Historic New York Snow Storm New U.S. Airstrikes in Iraq Real Examples 2014 Northern Iraq Offensive 2014 West Africa Ebola Outbreak Pro-Russian Conflict in Ukraine Israel-Gaza Conflict Real Examples

Video-Based News Events Find Candidate Events Detect key phrases on-screen Extract OCR Text as Video Feature Cluster News Videos Based on Temporal and Text Similarity Generate News Rover Video Event

Wikipedia-Based News Event Event Discovery Wikipedia Current Events Page Event Description Related Wikipedia Article News Rover Content ArticlesVideos Extracted Features Link News Content based on Temporal and Text Similarity Article Text Generate Wikipedia Event

Differences in Event Types Video Events Video Event Characteristics Specific event in time Contain less videos than Wiki Events Videos very closely related Do not persist over time Wikipedia Event Characteristics Consists of articles and videos Can contain many videos Videos are loosely related Can persist for months or days at a time Wikipedia Events

News Rover Content Collection Video ProgramsVideo StoriesVideo Events 62,840268, Video ProgramsVideo StoriesSimultaneous Channels ~90~40012 Total Available Content (Aug 2012 – Date) Daily Collection Statistics Number of Videos per News Rover Event

Major Players in the News Major Players Definition: People within each news event that appear frequently on news broadcasts commenting on that event. Current Statistics 10, 313 unique visual speakers in videos 44,464 video speech segments Performance 86% precision Frequent Speakers More Influential on Opinions?

Finding “Major Players” MethodologyImplementation Video of selected “Major Player” discussing the event.

Explore News Rover! rover.cs.columbia.edu