Register now to access 7 million high quality study materials (What's Course Hero?) Course Hero is the premier provider of high quality online educational resources. With millions of study documents, online tutors, digital flashcards and free courseware, Course Hero is helping students learn more efficiently and effectively. Whether you're interested in exploring new subjects or mastering key topics for your next exam, Course Hero has the tools you need to achieve your goals.
39 Pages
Document Preview
to Introduction Evaluation of Information Retrieval Systems Ray Larson & Marti Hearst University of California, Berkeley School of Information Management and Systems SIMS 202: Information Organization and Retrieval 10/3/2000 Information Organization and Retrieval Today Evaluation of IR Systems Precision vs. Recall Cutoff Points Test Collections/TREC Blair & Maron Study 10/3/2000 Information...
Unformatted Document Excerpt
Coursehero >> California >> Berkeley >> IS 202Course Hero has millions of student submitted documents similar to the one
below including study guides, practice problems, reference materials, practice exams, textbook help and tutor support.
Course Hero has millions of student submitted documents similar to the one
below including study guides, practice problems, reference materials, practice exams, textbook help and tutor support.
to Introduction Evaluation of Information Retrieval Systems
Ray Larson & Marti Hearst University of California, Berkeley School of Information Management and Systems SIMS 202: Information Organization and Retrieval
10/3/2000 Information Organization and Retrieval
Today
Evaluation of IR Systems
Precision vs. Recall Cutoff Points Test Collections/TREC Blair & Maron Study
10/3/2000
Information Organization and Retrieval
Evaluation
Why Evaluate? What to Evaluate? How to Evaluate?
10/3/2000
Information Organization and Retrieval
Why Evaluate?
Determine if the system is desirable Make comparative assessments Others?
10/3/2000
Information Organization and Retrieval
What to Evaluate?
How much of the information need is satisfied. How much was learned about a topic. Incidental learning:
How much was learned about the collection. How much was learned about other topics.
How inviting the system is.
10/3/2000 Information Organization and Retrieval
Relevance
In what ways can a document be relevant to a query?
Answer precise question precisely...
Textbooks related to the document above:
Find millions of documents on Course Hero - Study Guides, Lecture Notes, Reference Materials, Practice Exams and more.
Course Hero has millions of course specific materials providing students with the best way to expand
their education.
Below is a small sample set of documents:
Below is a small sample set of documents:
Berkeley - IS - 202
Information Structures and MetadataUniversity of California, Berkeley School of Information Management and Systems SIMS 202: Information Organization and Retrieval10/24/2000 Information Organization and RetrievalReview The Course Information Hi
Berkeley - IS - 202
Symbols and Language Lexical RelationsSIMS 202 Profs. Hearst & Larson UC Berkeley SIMS Fall 2000TodayqS bols and Language ym q Le xical Re lationsWhat is a symbol?qS e om thing that stands for or sugge som thing sts e e . lse q An arbitra
Berkeley - IS - 202
Information Structures and MetadataUniversity of California, Berkeley School of Information Management and Systems SIMS 202: Information Organization and Retrieval11/9/2000 Information Organization and RetrievalReview Change of schedule. (The
Berkeley - IS - 202
Introduction to Databases and Database DesignUniversity of California, Berkeley School of Information Management and Systems SIMS 202: Information Organization and Retrieval11/28/2000 Information Organization and RetrievalReview Thesaurus Design
Berkeley - IS - 202
Final Exam ReviewSIMS 202 Profs. Hearst & Larson UC Berkeley SIMS Fall 2000Final ExamqMonday De 11 c 9:30-12:30 Room202 and 205qBringns/pe ncils Pe alculator C s/Books (optional) NoteFinal ExamqTopicsom he , C pre nsive but pha
Berkeley - IS - 230
62dbb404332be5c202431a69160e1b5955d08dcc.xlsTAX SHIELD CALCULATION a. Uses circular references to calculate PV of after-tax cash flows b. Note that after-tax discount rate is not exactly pre-tax rate times (1 - tax rate) c. Model needs a starting v
Berkeley - IS - 213
LightsOn Test ScriptIntroduction Greet volunteer and introduce him or her to the team. Read over project goal statement: Our goal is to build a web-based interface that will allow facility mangers finegrain control over lighting behavior, scheduling
Berkeley - IS - 213
John Rolle (March 3, Friday 2006)T Task1: Post- weekend Lighting Problemsr recent list doesnt show nature of problem w what is that last one on the list? s should show the date assoc, with the issue p please pop em up in date order, reverse orde
Berkeley - IS - 213
UI Design Patterns Interview Analysis & ReportKelly Snow, Mano Marks, Tim Dennis, David Hong February 9, 2006IntroductionOn February 1-3, 2006, we interviewed nine UC Berkeley staff web developers as a follow-up to a survey on user interface desi
Berkeley - IS - 213
2/10/06 four big ideas from today's interviews. 1) NAVIGATION BY PROBLEM, NOT PATTERN NAME: users should be able to someone find a pattern based on the problem they're trying to solve, not just the name of the pattern. 2) FIND BERKELEY SPECIFIC PAT
Idaho - CORS - 219
HAMILTON'S RULE Hamilton, W.D. 1964. The genetical evolution of social behaviour. I. Journal of Theoretical Biology 7: 1-16. Develops a concept, inclusive fitness, which is an extension of traditional, individual fitness Individual fitness: lifeti
Berkeley - IS - 213
Tofer Merritt HE for UI Design PatternsHeuristic Evaluation for UI Design Patterns1. [H8 Aesthetic and Minimalist Design] (Severity 2) The location and wording of the "Common Problems that Patterns Can Solve" section seems to be a little misleadin
Berkeley - IS - 213
Heuristic Evaluation for Web UI Patterns Project IS213 Assignment Lois Wei 5/17/2009Heuristic Evaluation for Web UI Design Patterns ProjectNote: I am following the Usability Heuristics by Jakob Nielen in chapter 5 of his Usability Engineering book
Idaho - CORS - 219
Social Dominance "All animals are equal. But some animals are more equal than others" George Orwell Animal Farm "We come into the world equipped with a nervous system that worries about rank." Robert Frank 1985: Choosing the right pond: Human be
Berkeley - IS - 296
%!PS-Adobe-2.0 %Creator: dvipsk 5.55a Copyright 1986, 1994 Radical Eye Software %Title: paper.dvi %Pages: 6 %PageOrder: Ascend %BoundingBox: 0 0 612 792 %EndComments %DVIPSCommandLine: dvips paper %DVIPSParameters: dpi=300, compressed, comments remov
Berkeley - IS - 296
%!PS-Adobe-2.0 %Creator: dvipsk 5.58f Copyright 1986, 1994 Radical Eye Software %Title: thesis.dvi %Pages: 32 %PageOrder: Ascend %BoundingBox: 0 0 612 792 %EndComments %BeginProcSet: tex.pro /TeXDict 250 dict def TeXDict begin /N{def}def /B{bind def}
Berkeley - IS - 213
SIMS 213: User Interface Design & DevelopmentMarti Hearst Thurs, Jan 29, 2004DiscussionKent Sullivan, The Windows 95 User Interface: A Case Study in Usability Engineering, CHI 1996. A case study of the iterative design process.Sullivan Case Stu
Berkeley - IS - 213
SIMS 213: User Interface Design & DevelopmentMarti Hearst Tues, Feb 3, 2004Participatory DesignA subset of user-centered design User actively participates in design of the system Pros: potentially more accurate information about the tasks more
Berkeley - IS - 213
SIMS 213: User Interface Design & DevelopmentMarti Hearst Thurs, Feb 26, 2004TodayDiscuss Assignment 3 Wireframing Card SortingWireframingWhat is the main idea? Separate content from layout and display Next week: Use the page layout to sign
Berkeley - IS - 213
SIMS 213: User Interface Design & DevelopmentMarti Hearst March 9 & 11, 2004Formal Usability StudiesOutlineExperiment Design Factoring Variables InteractionsSpecial considerations when involving human participants Example: Marking Menus
Idaho - CORS - 219
Same-Sex ParentsUnnatural enough to be banned?Homosexuality You'd think homosexuality wouldn't be able to subsist, it hinders fitness. So why? In bonobo chimpanzees, homosexual interactions are a form of social cement. It is possible that homos
Berkeley - IS - 296
SIMS 296a3: Current Topics in Information AccessMarti Hearst Fall `98Todays s s sIntroductions Goals and Course Requirements Administrivia Topics s What is Information Access s Current Topics (an outline) s Intro to IAGoalsssBecome expe
Berkeley - IS - 296
SIMS 296a3: Aids for Source SelectionCarol Butler Fall `98OutlineqIA Interfacesq DesignPrinciplesqAids for Source Selectionq SavvySearch q HITS q KohonenmapsqImplications for New ResearchCarol Butler Fall 98IA Interface should
Berkeley - IS - 296
Support for the dynamic process history mechanismsVijayshankar RamanGeneral comments Search is a dynamic process berry picking useful information = total of all that is collected along the path. "halffinished ideas and partly explored paths ca
Idaho - CORS - 219
Samoan Sex LifeJillian Tierney Jessica Mullins Jessica WileyComing of Age in SomoaBy Margaret MeadWilliam Morrow & Company 1928Margaret Mead Anthropologist 1925 Student of Franz Boas Set out to find why Americans' adolescence is so storm
Idaho - CORS - 219
The Human Mating SystemIntroduction and Male StrategiesWhat is a Mating System? A mating system is the species-specific way in which matings are allocated among the members of a population Mating: the process leading to the fusion of haploid gam
Idaho - CORS - 219
The Human Mating SystemII Female StrategiesWhat do Women Want?The Evolution of Female Sexual Preferences In contrast to males, who are selected to seek many matings with as many females as possible . Females are selected to maximize the lifeti
Idaho - CORS - 219
The Human Mating SystemIII Preferences, Strategies, Sexual ConflictPair Bonds Social bonds are common in mammals The mechanism by which a bond is formed is unknown Social bonding is an adaptation Bonding is a mechanism that allows animals to b
Berkeley - IS - 213
Second round of Low fi prototype testing #1Name of user: Prof. Clancy Relation to the UC-HIPO project: The primary user of the metadata tagging tool Procedure: We explain the project and the scope of the project. Then we explain the procedure and pu
Berkeley - IS - 213
Low_Fi prototype testing # 3Name of user : Nate Relation to the UCHIPO project: Nate isa post doctorate on the UCWISE project. He is currently the instructor for CS3. He is especially interested in using the metadata tagging tool and has many idea
Berkeley - IS - 213
Low_Fi prototype testing # 2Name of user : Hiroki Relation to the UCHIPO project: Hiroki is a junior majoring in computer science at UC Berkeley. He was the head TA for CS3 (a computer science course taught using the UCWISE system). He worked as a
Berkeley - IS - 213
Final PresentationIvan Tam Lindsay Tabas Katrina Rhoads John Mark JoslingProblem Statement & GoalsGoal: To develop an interface for facility managers to control and monitor a building's entire wirelesscontrolled lighting system. Key Functionality
Idaho - CORS - 219
Child Development I Maternal Investment and Reproductive DecisionsNatural Human SurvivorshipLife History Adaptations Age of first reproduction Litter size Litter Mass Intervals between reproduction Level of parental care per offspring Vari
Berkeley - IS - 208
Systems & ProjectsYale BraunsteinSchool of Information Management & Systems UC Berkeley12"Blackbox" modelsINPUTSRequests for service Items to process Something to be transformedOUTPUTS Products Services Information Other outcomes External
Berkeley - IS - 208
Introduction to Statistical AnalysisYale Braunstein School of Information Management & Systems1Approximate (!) Schedule Today Data, data collection instruments (e.g., surveys) Research design Sample size, sources of error (maybe) Wednesda
Berkeley - IS - 208
Statistical Analysis Part 2Yale Braunstein School of Information Management & Systems1Sources of Error The respondent The investigator Sampling error Change in the system itself Coding & analysis Other2Measures of Central Tendency D
Berkeley - IS - 208
Cost AnalysisYale Braunstein School of Information Management & Systems1How does this course differ from all other project-related courses at SIMS? We explicitly look at alternatives. We care about economic feasibility. [others ?]2Why do
Berkeley - IS - 208
IS208A: Analysis of Information SystemsThe Final Report There is no single approach that works for all projects, but the following Table of Contents both gives you an idea of what we expect and is a useful "default." In almost every case, your proje
Berkeley - IS - 296
Untangling Text Data MiningMarti Hearst UC Berkeley SIMSACL'99 Plenary Talk June 23, 1999OutlineqUntangling se ral diffe nt fie ve re ldsL, DM, C I A, TDMq qTDM e ple xam s TDM as Exploratory Data Analysisw m om Ne Proble s for C puta
Berkeley - IS - 296
Mathe atical Foundations mEle e m ntary Probability The ory Esse ntial Inform ation The ory05/17/09 By Barbara Rosario 1MotivationsS tatistical NLP aim to do statistical infe ncefor s re thefie of NL ld S tatistical infe nceconsists of takin
Berkeley - IS - 296
Chapter 6: Statistical Inference: n-gram Models over Sparse DataTDM Seminar Jonathan Henke http:/www.sims.berkeley.edu/~jhenke/Tdm/TDM-Ch6.pptBasic Idea: Examine short sequences of words How likely is each sequence? "Markov Assumption" word i
Berkeley - IS - 230
Yale Braunstein IS 230 Fall 2002 Introduction to Financial Statements or "One Year in the Life of a Small Firm" Three Balance Sheets Jan. 1, 2002 Assets Cash $1,000 Liabilities $Net Worth Com. Stock $1,000 "Before" Jan. 2, 2002 Assets Cash Plant & Eq
Berkeley - IS - 230
Graphical Approach to Linear Programming(A standard optimization technique)The ABC's of optimization problemsA What can you adjust? B What do you mean by best? C What constraints must be obeyed?The "SHOE" problem We want to use standard inputs
Berkeley - IS - 213
Lo-Fi Prototype Assignment User Testing ScriptIntroduction Thank you for participating in our study today. We are graduate students trying to understand how UI design patterns might be a helpful resource. We would like your honest feedback throughou
Berkeley - IS - 213
Web Patterns Survey Part I Naming Page ElementsIn this section, you are asked to review this web page, then name each section numbered and highlighted in red.What is the best name for the design element highlighted on the Web Page? 1_ 2_ 3_ 4_ 5_
Berkeley - IS - 213
UC HIPO (Help for Instructor Portal) : Metadata tagging tool for UCWISE Instructor portal Follow-up Interview questions General Questions_ 1 I found the metadata Tagging tool intuitive and easy to use 1 Disagree 2 Somewhat disagree 3 Neutral 4 Somewh
Berkeley - IS - 208
zone 4 8 11 9 5 8 11party A B A B A A A<- Fictional data set: 7 registered voters in Oakland, CA. "Zone" = postal zone (last two digits of Zip Code) as proxy for "n "Party" is the political party. (There are actually more than two, aip Code) as
Berkeley - IS - 208
Name U of Nebraska/Lincoln International Inst. of the Ameri Berea College Cooper Union Elon College Oklahoma Panhandle State U University of Virgin Islands Sonoma State University California State University/Chic California State U/Fresno U of Texas
Berkeley - IS - 231
PROPERTY RIGHTS, COASE'S THEOREM, IPR & DATABASE PROTECTION Yale M. Braunstein School of Information Mgt. & Systems University of California, Berkeley 20041Today's Presentation1. 2. 3. 4.Economic logic for IPR & "Coase's Theorem" Economics
Berkeley - IS - 231
Pricing Interconnection and Universal Service in a Liberalized NetworkSchool of Information Management & Systems University of California Berkeley, CA 94720 (U.S.A.) November 2004Yale M. Braunstein As new entrants enter a telecommunications ma
Berkeley - IS - 231
b61c5d31222bc1a34c61026f9bda7fffdc765f97.xlsIS 231Fall 2004The following is a highly aggregated input-output model of a small open economy. All entries are in billions of U.S.D. Purchasing Sectors Intermediate Demand Final Demand Information Ag
Berkeley - IS - 231
b5412f0628399d054d0384d14fcd6605cdde3a54.xlsIS 231Fall 2004The following is a highly aggregated input-output model of a small open economy. All entries are in billions of U.S.D. Purchasing Sectors Intermediate Demand Final Demand Information Ag
Berkeley - IS - 255
7-FEB-19947-FEB-19947-FEB-19948-AUG-199415-APR-199415-APR-199420-MAY-19946-JUN-19948-AUG-199411-FEB-199421-SEP-1994|23-SEP-199415-APR-199415-JUN-199415-JUL-199421-SEP-1994|23-SEP-199414-FEB-19946-NOV-1994|9-NOV-199415-JUL-199419-AUG
Berkeley - A - 255
7-FEB-19947-FEB-19947-FEB-19948-AUG-199415-APR-199415-APR-199420-MAY-19946-JUN-19948-AUG-199411-FEB-199421-SEP-1994|23-SEP-199415-APR-199415-JUN-199415-JUL-199421-SEP-1994|23-SEP-199414-FEB-19946-NOV-1994|9-NOV-199415-JUL-199419-AUG
Berkeley - A - 255
Jane Lee IS255 Assignment 8 Regular Expressions Annotations String month = "(jan|feb|mar|april|may|jun|jul|aug|sep|oct|nov|dec|january|february| march|april|may|june|july|august|september|october|november|december),?"; This regex identifies months us
Berkeley - IS - 231
Broadband Industry Structure: Policy, Pricing & PenetrationYale M. Braunstein20021My Approach 1 Industry structure firm conduct (pricing) broadband penetration Policies and regulation can affect outcomes Therefore, we need to consider
Alabama - CS - 124
CS 124 Test 2 28Spring 2008Thursday, FebName: _ CWID: _ Section: (circle one) 11:00 12:302:001. What changes are needed to the following Person.h file if it is going to be used in a multi-file project with other header files and several cpp
U. Houston - CUIN - 3113
I used observation as an evaluation instrument. I looked to make sure each student was able to control the mouse. I also looked for students to be able to make the correct transitions to each slide. The group I was working with did an excellent job s
U. Houston - CUIN - 3111
Number 7654 Number 3210 Apples Oranges Grapes Bananas CherriesFruit Number Apples 5 Oranges 3 Grapes 6 Bananas 4 Cherries 2 Strawberries 7Kindergarten Favorite Fruits8 7 6 5 4 3 2 1 0 Apples Oranges Grapes Bananas Strawberries Cherri
Stanford - EXP - 080118
#SYSTEM = acdCalib#instrument= LAT#timestamp = Mon Jan 28 16:05:57 2008#calibType = 1#algorithm = P5#DTDVersion = v1r1#fmtVersion = v1r1#startTime = -1073780552:58983996#stopTime = -1073780552:58983996#triggers = 2299994/2930332/2930332#sou
Stanford - EXP - 080118
%!PS-Adobe-2.0 %Title: test_gain_lin_rib_A.ps: rib_A %Creator: ROOT Version 5.16/00 %CreationDate: Mon Jan 28 16:13:51 2008 %Orientation: Landscape %EndComments %BeginProlog /s {stroke} def /l {lineto} def /m {moveto} def /t {translate} def /sw {stri