understanding the searchers - emory universityeugene/cs190/lectures/feb21-web... · 2013. 2....

Understanding the Searchers

12/21/2013 CS190: Web Science and Technology, 2010

Today's Plan

Project 1 presentations

Understanding web searchers

Models, methods

Advertising

Next project: Google advertizing campaign

22/21/2013 CS190: Web Science and Technology, 2010

Student Projects

• Are available on the web here:http://www.mathcs.emory.edu/~eugene/cs190/project1solutions.html

• By end-of-week, will be findable by search engines

• Make sure your projects' homepage has:

– Title of project

– Names of team members

– Very brief (one sentence) subtitle/description

2/21/2013 CS190: Web Science and Technology, 2010 3

Models of Search Behavior

• Understanding user behavior at micro-, meso-, and macro- levels

• Theoretical models of information seeking

• Web search behavior:– Levels of detail

– Search Intent

– Variations in web searcher behavior

– Click models

4

Levels of Understanding User Behavior

• Micro (eye tracking): lowest level of detail, milliseconds

• Meso (field studies): mid-level, minutes to days

• Macro (session analysis):millions of observations, days to months

5

[Daniel M. Russell,

2007]

Models of Information Seeking

• “Information-seeking … includes recognizing … the information problem, establishing a plan of search, conducting the search, evaluating the results, and … iterating through the process.”-Marchionini, 1989

– Query formulation

– Action (query)

– Review results

– Refine query

6

Adapted from: M. Hearst, SUI,

2009

Cognitive Model of Information Seeking

• Static Info Need

– Goal

– Execution

– Evaluation

7

Dynamic “Berry Picking” Model

• Information needs change during interactions

8

[Bates, 1989] M.J. Bates. The design of browsing and berrypicking techniques for

the on-line search interface. Online Review, 13(5):407–431, 1989.

Eugene AgichteinEmory University

Goal: maximize rate of

information gain.Patches of information websites

Basic Problem: should I

continue in the current

patch or look for another

patch?

Expected gain from continuing

in current patch, how long to

continue searching in that patch

Information Foraging Theory

9

Hotel Search

10

Goal: Find

cheapest 4-star

hotel in Paris.

Step 1: pick hotel

search site

Step 3: goto 1

Step 2: scan list

Example: Hotel Search (cont’d)

Eugene AgichteinEmory University

11

Diminishing Returns Curve; 80% of users don’t scan past the 3rd

page of search results

R* = steepest slope from origin = tangent from origin

If tb is low, then people tend to switch more easily. (web snacking)

-Charnov’s Marginal Value Theorem

12

Browsing vs. Search

• Recognition over recall (I know it when I see it)

• Browsing hierarchies/facets more effective than querying

13

Orienteering

• Searcher issues a quick, imprecise to get to approximately the right information space region

• Searchers follow known paths that require small steps that move them closer to their goal

• Expert searchers starting to issue longer queries

14

Information Scent for Navigation

• Examine clues where to find useful information

15

Search results listings must

provide the user with clues

about which results to click

Web Searcher Behavior

• Meso-level: query, intent, and session characteristics

• Micro-level: how searchers interact with result pages

• Macro-level: patterns, trends, and interests

16

Web Search Architecture

Example centralized parallel architecture

Crawlers

Web

[from Baeza-Yates and Jones, WWW 2008

tutorial]

Information Retrieval Process (User view)

Eugene Agichtein, Emory University, IR Lab 18

Source

Selection

Search

Query

Selection

Ranked List

Examination

Documents

Delivery

Documents

Query

Formulation

Resource

query reformulation,

vocabulary learning,

relevance feedback

source reselection

Intent Classes (top level only)

User intent taxonomy (Broder 2002)

– Informational – want to learn about something (~40% / 65%)

– Navigational – want to go to that page (~25% / 15%)

– Transactional – want to do something (web-mediated) (~35% / 20%)

• Access a serviceDownloads

• Shop

– Gray areas

• Find a good hub

• Exploratory search “see what’s there”

Eugene Agichtein, Emory University, IR Lab

History nonya food

Singapore Airlines

Jakarta weather

Kalimantan satellite images

Nikon Finepix

Car rental Kuala Lumpur

[from SIGIR 2008 Tutorial, Baeza-Yates and Jones]

19

Web Search Queries

• Cultural and educational diversity

• Short queries and impatient interaction

– Few queries posed and few answers seen (first page)

– Reformulation common

• Smaller and different vocabulary

– Not “expert” searchers!

– “Which box do I type in?”

Eugene AgichteinEmory University 20

Classified Queries

Eugene AgichteinEmory University 21

[from SIGIR 2008 Tutorial, Baeza-Yates and Jones]

People Look at Only a Few Results

(Source: iprospect.com WhitePaper_2006_SearchEngineUserBehavior.pdf)‏

Eugene AgichteinEmory University 22

Snippet Views Depend on Rank

Mean: 3.07 Median: 2.00

Eugene AgichteinEmory University 23

Problem: Users click based on result “Snippets”

• Effect of Caption Features on Clickthrough Inversions, C. Clarke, E. Agichtien, S. Dumais, R. White, SIGIR 2007

[Clarke et al., 2007]

24

Clickthrough Inversions [Clarke et al., 2007]

25

Important Words in Snippet[Clarke et al., 2007]

26

Click Models Summary

Models proposed to simulate searcher click process

– Increasingly sophisticated and theories

– Assume searcher is rational and consistent

But, searchers are not rational or careful:

– Attracted/repelled by simple features of summaries

Can incorporate summary and browsing info to extract relevance information from clicks

27

“Eyes are a Window to the Soul”

• Eye tracking gives information about search interests:

– Eye position

– Pupil diameter

– Seekads and fixations

28

Reading

Visual

Search

Camera

Micro-level: Examining Results

• Users rapidly scan the search result page

• What they see in lower summaries may influence judgment of higher result

• Spend most time scrutinizing top results 1 and 2

– Trust the ranking

29

[Daniel M. Russell,

2007]

Result Examination (cont’d)

• Searchers might use the mouse to focus reading attention, bookmark promising results, or not at all.

• Behavior varies with task difficulty and user expertise

30

[K. Rodden, X. Fu, A. Aula, and I. Spiro, Eye-

mouse coordination patterns on web search

results pages, Extended Abstracts of ACM CHI

2008]

News: We can predict where the searcher is looking!

2/21/2013 CS190: Web Science and Technology, 2010 31

Guo & Agichtein,

CHI 2010

A

D

C

E

F

Macro-Level (Session) Analysis

• Can examine theoretical user models in light of empirical data:– Orienteering?– Foraging?– Multi-tasking?

• Search is often a multi-step process: – Find or navigate to a good site (“orienteering”)– Browse for the answer there: [actor most oscars] vs. [oscars]

• Teleporting – “I wouldn’t use Google for this, I would just go to…”

• Triangulation– Draw information from multiple sources and interpolate – Example: “how long can you last without food?”

32

Users (sometimes) Multi-task

33

[Daniel M. Russell, 2007]

Eugene AgichteinEmory University

Kinds of Search+Browsing Behavior

34

[Daniel M. Russell,

2007]

References and Further Reading

• Marti Hearst, Search User Interfaces, 2009, Chapter 3 “Models of the Information Seeking Process”: http://searchuserinterfaces.com/

35

Next Project

• Google advertising Challenge:

http://www.google.com/onlinechallenge/

1. Pick a team (not the same as last project)

2. Pick a non-profit organization/website to promote

3. Read about the challenge over the weekend

4. Will be due right after Spring break

2/21/2013 CS190: Web Science and Technology, 2010 36