SLOW SEARCH WITH PEOPLE Jaime Teevan, Microsoft In collaboration with Collins-Thompson, White, Dumais, Kim, Jeong, Morris, Liebling,

Slides:



Advertisements
Similar presentations
Beliefs & Biases in Web Search
Advertisements

Microsoft® Office Access® 2007 Training
Templates and Styles Excel Advanced. Templates are pre- designed and formatted spreadsheets –They provide consistency of layout/structure –They.
TAC Vista Security. Target  TAC Vista & Security Integration  Key customer groups –Existing TAC Vista users Provide features and hardware for security.
Interfaces for Querying Collections. Information Retrieval Activities Selecting a collection –Lists, overviews, wizards, automatic selection Submitting.
Enhance legal retrieval applications with an automatically induced knowledge base Ka Kan Lo.
Section 2: Finding and Refinding Jaime Teevan Microsoft Research 1.
Artificial Intelligence Research Centre Program Systems Institute Russian Academy of Science Pereslavl-Zalessky Russia.
Finding and Re-Finding Through Personalization Jaime Teevan MIT, CSAIL David Karger (advisor), Mark Ackerman, Sue Dumais, Rob Miller (committee), Eytan.
Information Re-Retrieval Repeat Queries in Yahoo’s Logs Jaime Teevan (MSR), Eytan Adar (UW), Rosie Jones and Mike Potts (Yahoo) Presented by Hugo Zaragoza.
SLOW SEARCH Jaime Teevan, Kevyn Collins-Thompson, Ryen White, Susan Dumais and Yubin Kim.
Social Network Question Asking. Sheila Brown Does anyone know if Keanu Reeves was born in Hawaii? Mon at 5:23pm ∙ Comment ∙ Like MethodToolUseAskerAskedSpeed.
TwitterSearch : A Comparison of Microblog Search and Web Search
Advanced Excel for Finance Professionals A self study material from South Asian Management Technologies Foundation.
Understanding and Predicting Graded Search Satisfaction Tang Yuk Yu 1.
1 Searching through the Internet Dr. Eslam Al Maghayreh Computer Science Department Yarmouk University.
Presented by Karen Porter UM School of Business Administration & ImpactOnlineMarketing.com Keywords: Research & Optimization ImpactOnlineMarketing.com.
Xiaoying Sharon Gao Computer Science Victoria University of Wellington Intelligent Agents COMP 423.
Searching the web Enormous amount of information –In 1994, 100 thousand pages indexed –In 1997, 100 million pages indexed –In June, 2000, 500 million pages.
Personalizing Search Jaime Teevan, MIT Susan T. Dumais, MSR and Eric Horvitz, MSR.
1 Lesson 18 Managing and Reporting Database Information Computer Literacy BASICS: A Comprehensive Guide to IC 3, 3 rd Edition Morrison / Wells.
SLOW SEARCH WITH PEOPLE Jaime Teevan, Microsoft In collaboration with Michael S. Bernstein, Kevyn Collins- Thompson, Susan T. Dumais,
UIC at TREC 2006: Blog Track Wei Zhang Clement Yu Department of Computer Science University of Illinois at Chicago.
1 A Methodology for automatic retrieval of similarly shaped machinable components Mark Ascher - Dept of ECE.
Big Data: Every Word Managing Data Data Mining TerminologyData Collection CrowdsourcingSecurity & Validation Universal Translation Monolingual Dictionaries.
Seesaw Personalized Web Search Jaime Teevan, MIT with Susan T. Dumais and Eric Horvitz, MSR.
Potential for Personalization Transactions on Computer-Human Interaction, 17(1), March 2010 Data Mining for Understanding User Needs Jaime Teevan, Susan.
Xiaoying Sharon Gao Computer Science Victoria University of Wellington Intelligent Agents COMP 423.
Section 3 Computing with confidence. The purpose of this section The purpose of this section is to develop your skills to achieve two goals: 1-Becoming.
SEARCH AND CONTEXT Susan Dumais, Microsoft Research INFO 320.
SLOW SEARCH Jaime Teevan, Microsoft In collaboration with Michael S. Bernstein, Kevyn Collins- Thompson, Susan T. Dumais, Shamsi T.
 1- Definition  2- Helpdesk  3- Asset management  4- Analytics  5- Tools.
SEARCH ENGINE by: by: B.Anudeep B.Anudeep Y5CS016 Y5CS016.
Digital Assistants – a brand’s best friend?
Sampath Jayarathna Cal Poly Pomona
Human Computer Interaction Lecture 21 User Support
بازاریابی دیجیتال در یک نگاه
Evaluation Anisio Lacerda.
mi·cro·pro·duc·tiv·i·ty /ˈmīkrō prōˌdəkˈtivətē/ noun
Designing Cross-Language Information Retrieval System using various Techniques of Query Expansion and Indexing for Improved Performance  Hello everyone,
Improving searches through community clustering of information
With Microsoft FrontPage 2000
Lesson 23 Managing and Reporting Database Information
Simultaneous Support for Finding and Re-Finding
System Design Ashima Wadhwa.
Advantages of ICT over Manual Methods of Processing Data
Supporting Big Tasks through Microtasks
Digital Marketing Overview
Elsevier Activity Range
Internet Networking recitation #12
Digital Marketing Overview
Collaboration with Google Docs
Database Management Systems
Database Management System (DBMS)
Supporting Collaborative Writing with Microtasks
Slow Search With People
How Students Navigate a Test and Use Test Tools
Navya Thum February 13, 2013 Day 7: MICROSOFT EXCEL Navya Thum February 13, 2013.
Introduction to Information Retrieval
Ryen White, Ahmed Hassan, Adish Singla, Eric Horvitz
CHI 2016 workshop on Microproductivity
Introduction to Access
University of Melbourne, Australia
Security of People, Property and Information
Designing Your Performance Task Assessment
The Winograd Schema Challenge Hector J. Levesque AAAI, 2011
mi·cro·pro·duc·tiv·i·ty /ˈmīkrō prōˌdəkˈtivətē/ noun
Discussion Class 9 Google.
Discussion Class 9 Informedia.
Tutorial Introduction to help.ebsco.com.
Presentation transcript:

SLOW SEARCH WITH PEOPLE Jaime Teevan, Microsoft In collaboration with Collins-Thompson, White, Dumais, Kim, Jeong, Morris, Liebling, Bernstein, Horvitz, Salehi, Iqbal, Kamar, Lasecki, Organisciak, Miller, Kalai, and Panovich

Slow Movements

Speed Focus in Search Reasonable

Not All Searches Need to Be Fast Long-term tasks Long search sessions Multi-session searches Social search Question asking Technologically limited Mobile devices Limited connectivity Search from space

Making Use of Additional Time

CROWDSOURCING Using human computation to improve search

Replace Components with People Search process Understand query Retrieve Understand results Machines are good at operating at scale People are good at understanding with Kim, Collins-Thompson

Understand Query: Query Expansion Original query: hubble telescope achievements Automatically identify expansion terms: space, star, astronomy, galaxy, solar, astro, earth, astronomer Best expansion terms cover multiple aspects of the query Ask crowd to relate expansion terms to a query term Identify best expansion terms: astronomer, astronomy, star spacestarastronomygalaxysolarastroearthastronomer hubble telescope achievements

Understand Results: Filtering Remove irrelevant results from list Ask crowd workers to vote on relevance Example: hubble telescope achievements

People Are Not Good Components Test corpora Difficult Web queries TREC Web Track queries Query expansion generally ineffective Query filtering Improves quality slightly Improves robustness Not worth the time and cost Need to use people in new ways

Understand Query: Identify Entities Search engines do poorly with long, complex queries Query: Italian restaurant in Squirrel Hill or Greenfield with a gluten-free menu and a fairly sophisticated atmosphere Crowd workers identify important attributes Given list of potential attributes Option add new attributes Example: cuisine, location, special diet, atmosphere Crowd workers match attributes to query Attributes used to issue a structured search with Kim, Collins-Thompson

Understand Results: Tabulate Crowd workers used to tabulate search results Given a query, result, attribute and value Does the result meet the attribute?

People Can Provide Rich Input Test corpus: Complex restaurant queries to Yelp Query understanding improves results Particularly for ambiguous or unconventional attributes Strong preference for the tabulated results People who liked traditional results valued familiarity People asked for additional columns (e.g., star rating)

Create Answers from Search Results Understand query Use log analysis to expand query to related queries Ask crowd if the query has an answer Retrieve: Identify a page with the answer via log analysis Understand results: Extract, format, and edit an answer with Bernstein, Dumais, Liebling, Horvitz

Community Answers with Bing Distill

Create Answers to Social Queries Understand query: Use crowd to identify questions Retrieve: Crowd generates a response Understand results: Vote on answers from crowd, friends with Jeong, Morris, Liebling

Working with an UNKNOWN CROWD Addressing the challenges of crowdsourcing search

Communicating with the Crowd How to tell the crowd what you are looking for? Trade off: Minimize the cost of giving information for the searcher Maximize the value of the information for the crowd with Salehi, Iqbal, Kamar

Finding Like-Minded Crowd Workers ? with Organisciak, Kalai, Dumais, Miller

Matching Workers versus Guessing Matching workers Requires many workers to find a good match Easy for workers Data reusable Guessing Requires fewer workers Fun for workers Hard to capture complex preferences Rand.MatchGuess Salt shakers Food (Boston) Food (Seattle) (RMSE for 5 workers)

Extraction and Manipulation Threats with Lasecki, Kamar

Information Extraction Target task: Text recognition Attack task Complete target task Return answer from target: %32.8%

gun (36%), fun (26%), sun (12%) Task Manipulation Target task: Text recognition Attack task Enter “sun” as the answer for the attack task sun (75%)sun (28%)

Payment for Extraction Task

FRIENDSOURCING Using friends as a resource during the search process

Searching versus Asking

Friends respond quickly 58% of questions answered by the end of search Almost all answered by the end of the day Some answers confirmed search findings But many provided new information Information not available online Information not actively sought Social content with Morris, Panovich

Shaping the Replies from Friends Should I watch E.T.?

Shaping the Replies from Friends Larger networks provide better replies Faster replies in the morning, more in the evening Question phrasing important Include question mark Target the question at a group (even at anyone) Be brief (although context changes nature of replies) Early replies shape future replies Opportunity for friends and algorithms to collaborate to find the best content with Morris, Panovich

Summary

Further Reading in Slow Search Slow search Teevan, J., Collins-Thompson, K., White, R., Dumais, S.T. & Kim, Y. Slow Search: Information Retrieval without Time Constraints. HCIR Teevan, J., Collins-Thompson, K., White, R. & Dumais, S.T. Slow Search. CACM Crowdsourcing Jeong, J.W., Morris, M.R., Teevan, J. & Liebling, D. A Crowd-Powered Socially Embedded Search Engine. ICWSM Bernstein, M., Teevan, J., Dumais, S.T., Libeling, D. & Horvitz, E. Direct Answers for Search Queries in the Long Tail. CHI Working with an unknown crowd Salehi, N., Iqbal, S., Kamar, E. & Teevan. Talking to the Crowd: Communicating Context in Crowd Work. CHI 2016 (under submission). Lasecki, W., Teevan, J. & Kamar, E. Information Extraction and Manipulation Threats in Crowd- Powered Systems. CSCW Organisciak, P., Teevan, J., Dumais, S.T., Miller, R.C. & Kalai, A.T. Personalized Human Computation. HCOMP Friendsourcing Morris, M.R., Teevan, J. & Panovich, K. A Comparison of Information Seeking Using Search Engines and Social Networks. ICWSM Teevan, J., Morris, M.R. & Panovich, K. Factors Affecting Response Quantity, Quality and Speed in Questions Asked via Online Social Networks. ICWSM 2011.

QUESTIONS? Slow Search with People Jaime Teevan, Microsoft