INFO 4300 / CS4300
Information Retrieval
slides adapted from Hinrich Sch¨utze’s,
linked from
http://informationretrieval.org/
IR 17/25: Web Search BasicsPaul Ginsparg
Cornell University, Ithaca, NY
2 Nov 2010
Administrativa
Assignment 3 due Sun 7 Nov
Overview
1 Big picture
2 Ads
Outline
1 Big picture
2 Ads
Web search overview
Search is a top activity on the web
Without search engines, the web wouldn’t work
Without search, content is hard to find.
→ Without search, there is no incentive to create content.Why publish something if nobody will read it?
Why publish something if I don’t get ad revenue from it?Somebody needs to pay for the web.
Servers, web infrastructure, content creationA large part today is paid by search ads.
Interest aggregation
Unique feature of the web: A small number of geographicallydispersed people with similar interests can find each other.Elementary school kids with hemophilia
People interested in translating R5R5 Scheme into relativelyportable C (open source project)
Search engines are the key enabler for interest aggregation.
Summary
On the web, search is not just a nice feature.Search is a key enabler of the web: . . .
. . . financing, content creation, interest aggregation etc.
Outline
1 Big picture
2 Ads
First generation of search ads: Goto (1996)
First generation of search ads: Goto (1996)
Buddy Blake bid the maximum ($0.38) for this search.He paid $0.38 to Goto every time somebody clicked on thelink.
Pages are simply ranked according to bid – revenuemaximization for Goto.
No separation of ads/docs. Only one result list!Upfront and honest. No relevance ranking, . . .. . . but Goto did not pretend there was any.
Second generation of search ads: Google (2000/2001)
Strict separation of search results and search ads
Two ranked lists: web pages (left) and ads (right)
SogoTrade ap-pears in searchresults.SogoTrade ap-pears in ads.Do search enginesrank advertis-ers higher thannon-advertisers?
All major searchengines claim no.
Do ads influence editorial content?
Similar problem at newspapers / TV channels
A newspaper is reluctant to publish harsh criticism of itsmajor advertisers.
The line often gets blurred at newspapers / on TV.No known case of this happening with search engines yet?
How are the ads on the right ranked?
How are ads ranked?
Advertisers bid for keywords – sale by auction.
Open system: Anybody can participate and bid on keywords.Advertisers areonly charged when somebody clickson your ad.How does the auction determine an ad’s rankand thepricepaidfor the ad?
Basis is a second price auction, but with twists
Squeeze an additional fraction of a cent from each admeansbillions of additional revenue for the search engine.
How are ads ranked?
First cut: according to bid priceBad idea: open to abuse
Example: query [accident]→adbuy a new carWe don’t want to show nonrelevant ads.Instead: rank based on bid price and relevanceKey measure of ad relevance: clickthrough rateResult: A nonrelevant ad will be ranked low.
Even if this decreases search engine revenue short-termHope: Overall acceptance of the system and overall revenue ismaximized if users get useful information.
Other ranking factors: location, time of day, quality andloading speed of landing page
The main factor of course is the query.
Google’s second price auction
advertiser bid CTR ad rank rank paid
A $4.00 0.01 0.04 4 (minimum)
B $3.00 0.03 0.09 2 $2.68
C $2.00 0.06 0.12 1 $1.51
D $1.00 0.08 0.08 3 $0.51
bid: maximum bid for a click by advertiser
CTR: click-through rate: when an ad is displayed, whatpercentage of time do users click on it? CTR is a measure ofrelevance.
ad rank: bid×CTR: this trades off (i) how much money theadvertiser is willing to pay against (ii) how relevant the ad isrank: rank in auction
paid: second price auction price paid by advertiserHal Varian explains Google second price auction:
http://www.youtube.com/watch?v=K7l0a2PVhPQ
Google’s second price auction
advertiser bid CTR ad rank rank paid
A $4.00 0.01 0.04 4 (minimum)
B $3.00 0.03 0.09 2 $2.68
C $2.00 0.06 0.12 1 $1.51
D $1.00 0.08 0.08 3 $0.51
Second price auction: The advertiser pays the minimum amountnecessary to maintain their position in the auction (plus 1 cent).price1 × CTR1 = bid2 × CTR2 (this will result in rank1=rank2)
price1 = bid2 ×CTR2 / CTR1
p1 =b2CTR2/CTR1 = 3.00·0.03/0.06 = 1.50
p2 =b3CTR3/CTR2 = 1.00·0.08/0.03 = 2.67
p3 =b4CTR4/CTR3 = 4.00·0.01/0.08 = 0.50
Keywords with high bids
According to http://www.cwire.org/highest-paying-search-terms/$69.1 mesothelioma treatment options
$65.9 personal injury lawyer michigan$62.6 student loans consolidation$61.4 car accident attorney los angeles$59.4 online car insurance quotes$59.4 arizona dui lawyer
$46.4 asbestos cancer
$40.1 home equity line of credit$39.8 life insurance quotes$39.2 refinancing
$38.7 equity line of credit
$38.0 lasik eye surgery new york city$37.0 2nd mortgage
$35.9 free car insurance quote
Search ads: A win-win-win?
The search enginecompany gets revenue every timesomebody clicks on an ad.
The useronly clicks on an ad if they are interested in the ad.Search engines punish misleading and nonrelevant ads.As a result, users are often satisfied with what they find afterclicking on an ad.
The advertiserfinds new customers in a cost-effective way.
Exercise
Why is web search potentially more attractive for advertisersthan TV spots, newspaper ads or radio spots?
The advertiser pays for all this. How can the system berigged? How can the advertiser be cheated?
Not a win-win-win: Keyword arbitrage
Buy a keyword on Google
Then redirect traffic to a third party that is paying much morethan you are paying Google.
E.g., redirect to a page full of adsThis rarely makes sense for the user.Ad spammers keep inventing new tricks.
The search engines need time to catch up with them.
Not a win-win-win: Violation of trademarks
Example: geico
During part of 2005: The search term “geico” on Google wasbought by competitors.
Geico lost this case in the United States.
Currently in the courts: Louis Vuitton case in EuropeSeehttp://google.com/tm complaint.html
It’s potentially misleading to users to trigger an ad off of atrademark if the user can’t buy the product on the site.
