SLIDE 1IS 202 – FALL 2003 Lecture 21: Web Search Issues and Algorithms Prof. Ray Larson & Prof. Marc Davis UC Berkeley SIMS Tuesday and Thursday 10:30 am - 12:00 pm Fall SIMS 202: Information Organization and Retrieval

SLIDE 2IS 202 – FALL 2003 Lecture Overview Review –Evaluation of IR systems Precision vs. Recall Cutoff Points Test Collections/TREC Blair & Maron Study Web Crawling Web Search Engines and Algorithms Credit for some of the slides in this lecture goes to Marti Hearst

SLIDE 3IS 202 – FALL 2003 What can be measured that reflects users’ ability to use system? (Cleverdon 66) –Coverage of information –Form of presentation –Effort required/ease of use –Time and space efficiency –Recall Proportion of relevant material actually retrieved –Precision Proportion of retrieved material actually relevant What to Evaluate? Effectiveness

SLIDE 4IS 202 – FALL 2003 Precision vs. Recall Relevant Retrieved All Docs

SLIDE 5IS 202 – FALL 2003 Retrieved vs. Relevant Documents Very high precision, very low recall Relevant

SLIDE 6IS 202 – FALL 2003 Retrieved vs. Relevant Documents Very low precision, very low recall (0 in fact) Relevant

SLIDE 7IS 202 – FALL 2003 Retrieved vs. Relevant Documents High recall, but low precision Relevant

SLIDE 8IS 202 – FALL 2003 Retrieved vs. Relevant Documents High precision, high recall (at last!) Relevant

SLIDE 9IS 202 – FALL 2003 Precision/Recall Curves Difficult to determine which of these two hypothetical results is better: precision recall x x x x

SLIDE 10IS 202 – FALL 2003 Test Collections Cranfield 2 –1400 Documents, 221 Queries –200 Documents, 42 Queries INSPEC – 542 Documents, 97 Queries UKCIS – >10000 Documents, multiple sets, 193 Queries ADI – 82 Document, 35 Queries CACM – 3204 Documents, 50 Queries CISI – 1460 Documents, 35 Queries MEDLARS (Salton) 273 Documents, 18 Queries

SLIDE 11IS 202 – FALL 2003 TREC Text REtrieval Conference/Competition –Run by NIST (National Institute of Standards & Technology) –1999 was the 8th year - 9th TREC in early November Collection: >6 Gigabytes (5 CRDOMs), >1.5 Million Docs –Newswire & full text news (AP, WSJ, Ziff, FT) –Government documents (federal register, Congressional Record) –Radio Transcripts (FBIS) –Web “subsets” (“Large Web” separate with 18.5 Million pages of Web data – 100 Gbytes) –Patents

SLIDE 12IS 202 – FALL 2003 TREC (cont.) Queries + Relevance Judgments –Queries devised and judged by “Information Specialists” –Relevance judgments done only for those documents retrieved—not entire collection! Competition –Various research and commercial groups compete (TREC 6 had 51, TREC 7 had 56, TREC 8 had 66) –Results judged on precision and recall, going up to a recall level of 1000 documents Following slides from TREC overviews by Ellen Voorhees of NIST

SLIDE 13IS 202 – FALL 2003 Sample TREC Query (Topic) Number: 168 Topic: Financing AMTRAK Description: A document will address the role of the Federal Government in financing the operation of the National Railroad Transportation Corporation (AMTRAK) Narrative: A relevant document must provide information on the government’s responsibility to make AMTRAK an economically viable entity. It could also discuss the privatization of AMTRAK as an alternative to continuing government subsidies. Documents comparing government subsidies given to air and bus transportation with those provided to AMTRAK would also be relevant.

SLIDE 14IS 202 – FALL 2003

SLIDE 15IS 202 – FALL 2003

SLIDE 16IS 202 – FALL 2003

SLIDE 17IS 202 – FALL 2003 Lecture Overview Review –Evaluation of IR systems Precision vs. Recall Cutoff Points Test Collections/TREC Blair & Maron Study Web Crawling Web Search Engines and Algorithms Credit for some of the slides in this lecture goes to Marti Hearst

SLIDE 18IS 202 – FALL 2003 Standard Web Search Engine Architecture crawl the web create an inverted index Check for duplicates, store the documents Inverted index Search engine servers user query Show results To user DocIds

SLIDE 19IS 202 – FALL 2003 Web Crawling How do the web search engines get all of the items they index? Main idea: –Start with known sites –Record information for these sites –Follow the links from each site –Record information found at new sites –Repeat

SLIDE 20IS 202 – FALL 2003 Web Crawlers How do the web search engines get all of the items they index? More precisely: –Put a set of known sites on a queue –Repeat the following until the queue is empty: Take the first page off of the queue If this page has not yet been processed: –Record the information found on this page »Positions of words, links going out, etc –Add each link on the current page to the queue –Record that this page has been processed In what order should the links be followed?

SLIDE 21IS 202 – FALL 2003 Page Visit Order Animated examples of breadth-first vs depth-first search on trees: – Structure to be traversed

SLIDE 22IS 202 – FALL 2003 Page Visit Order Animated examples of breadth-first vs depth-first search on trees: – Breadth-first search (must be in presentation mode to see this animation)

SLIDE 23IS 202 – FALL 2003 Page Visit Order Animated examples of breadth-first vs depth-first search on trees: – Depth-first search (must be in presentation mode to see this animation)

SLIDE 24IS 202 – FALL 2003 Page Visit Order Animated examples of breadth-first vs depth-first search on trees:

SLIDE 25IS 202 – FALL 2003 Sites Are Complex Graphs, Not Just Trees Page 1 Page 3 Page 2 Page 1 Page 2 Page 1 Page 5 Page 6 Page 4 Page 1 Page 2 Page 1 Page 3 Site 6 Site 5 Site 3 Site 1 Site 2

SLIDE 26IS 202 – FALL 2003 Web Crawling Issues Keep out signs –A file called robots.txt tells the crawler which directories are off limits Freshness –Figure out which pages change often –Recrawl these often Duplicates, virtual hosts, etc –Convert page contents with a hash function –Compare new pages to the hash table Lots of problems –Server unavailable –Incorrect html –Missing links –Infinite loops Web crawling is difficult to do robustly!

SLIDE 27IS 202 – FALL 2003 Searching the Web Web Directories versus Search Engines Some statistics about Web searching Challenges for Web Searching Search Engines –Crawling –Indexing –Querying

SLIDE 28IS 202 – FALL 2003 Directories vs. Search Engines Directories –Hand-selected sites –Search over the contents of the descriptions of the pages –Organized in advance into categories Search Engines –All pages in all sites –Search over the contents of the pages themselves –Organized after the query by relevance rankings or other scores

SLIDE 29IS 202 – FALL 2003 Search Engines vs. Internal Engines Not long ago HotBot, GoTo, Yahoo and Microsoft were all powered by Inktomi Today Google is the search engine behind many other search services (such as Yahoo and AOL’s search service)

SLIDE 30IS 202 – FALL 2003 Statistics from Inktomi Statistics from Inktomi, August 2000, for one client, one week –Total # queries: –Number of repeated queries: –Number of queries with repeated words: –Average words/ query: 2.39 –Query type: All words: ; Any words: ; Some words: –Boolean: ( AND / OR / NOT) –Phrase searches: –URL searches: –URL searches w/http: – searches: –Wildcards: ( '?'s ) frac '?' at end of query: interrogatives when '?' at end: composed of: –who: what: when: why: how: where where-MIS can,etc.: do(es)/did: 0.0

SLIDE 31IS 202 – FALL 2003 What Do People Search for on the Web? Topics –Genealogy/Public Figure:12% –Computer related:12% –Business:12% –Entertainment: 8% –Medical: 8% –Politics & Government 7% –News 7% –Hobbies 6% –General info/surfing 6% –Science 6% –Travel 5% –Arts/education/shopping/images 14% (from Spink et al. 98 study)

SLIDE 32 Visits (last year)

SLIDE 33IS 202 – FALL 2003 Visits (this year)

SLIDE 34 Directory Sizes (Last Year)

SLIDE 35IS 202 – FALL 2003 Directory Sizes

SLIDE 36IS 202 – FALL 2003

SLIDE 37IS 202 – FALL 2003

SLIDE 38 Searches Per Day (2000)

SLIDE 39IS 202 – FALL 2003 Searches Per Day (2001)

SLIDE 40IS 202 – FALL 2003 Searches per day (current) Don’t have exact numbers for Google, but they state in their “press” section that they handle 200 Million searches per day They index over 3 Billion web pages and 3 trillion words –

SLIDE 41IS 202 – FALL 2003 Challenges for Web Searching: Data Distributed data Volatile data/”Freshness”: 40% of the web changes every month Exponential growth Unstructured and redundant data: 30% of web pages are near duplicates Unedited data Multiple formats Commercial biases Hidden data

SLIDE 42IS 202 – FALL 2003 Challenges for Web Searching: Users Users unfamiliar with search engine interfaces (e.g., Does the query “apples oranges” mean the same thing on all of the search engines?) Users unfamiliar with the logical view of the data (e.g., Is a search for “Oranges” the same things as a search for “oranges”?) Many different kinds of users

SLIDE 43IS 202 – FALL 2003 Web Search Queries Web search queries are SHORT –~2.4 words on average (Aug 2000) –Has increased, was 1.7 (~1997) User Expectations –Many say “the first item shown should be what I want to see”! –This works if the user has the most popular/common notion in mind

SLIDE 44IS 202 – FALL 2003 Search Engines Crawling Indexing Querying

SLIDE 45IS 202 – FALL 2003 Web Search Engine Layers From description of the FAST search engine, by Knut Risvik

SLIDE 46IS 202 – FALL 2003 Standard Web Search Engine Architecture crawl the web create an inverted index Check for duplicates, store the documents Inverted index Search engine servers user query Show results To user DocIds

SLIDE 47IS 202 – FALL 2003 More detailed architecture, from Brin & Page 98. Only covers the preprocessing in detail, not the query serving.

SLIDE 48IS 202 – FALL 2003 Indexes for Web Search Engines Inverted indexes are still used, even though the web is so huge Most current web search systems partition the indexes across different machines –Each machine handles different parts of the data (Google uses thousands of PC-class processors) Other systems duplicate the data across many machines –Queries are distributed among the machines Most do a combination of these

SLIDE 49IS 202 – FALL 2003 Search Engine Querying In this example, the data for the pages is partitioned across machines. Additionally, each partition is allocated multiple machines to handle the queries. Each row can handle 120 queries per second Each column can handle 7M pages To handle more queries, add another row. From description of the FAST search engine, by Knut Risvik

SLIDE 50IS 202 – FALL 2003 Querying: Cascading Allocation of CPUs A variation on this that produces a cost- savings: –Put high-quality/common pages on many machines –Put lower quality/less common pages on fewer machines –Query goes to high quality machines first –If no hits found there, go to other machines

SLIDE 51IS 202 – FALL 2003 Google Google maintains (currently) the worlds largest Linux cluster (over 15,000 servers) These are partitioned between index servers and page servers –Index servers resolve the queries (massively parallel processing) –Page servers deliver the results of the queries Over 3 Billion web pages are indexed and served by Google

SLIDE 52IS 202 – FALL 2003 Search Engine Indexes Starting Points for Users include Manually compiled lists –Directories Page “popularity” –Frequently visited pages (in general) –Frequently visited pages as a result of a query Link “co-citation” –Which sites are linked to by other sites?

SLIDE 53IS 202 – FALL 2003 Starting Points: What is Really Being Used? Todays search engines combine these methods in various ways –Integration of Directories Today most web search engines integrate categories into the results listings Lycos, MSN, Google –Link analysis Google uses it; others are also using it Words on the links seems to be especially useful –Page popularity Many use DirectHit’s popularity rankings

SLIDE 54IS 202 – FALL 2003 Web Page Ranking Varies by search engine –Pretty messy in many cases –Details usually proprietary and fluctuating Combining subsets of: –Term frequencies –Term proximities –Term position (title, top of page, etc) –Term characteristics (boldface, capitalized, etc) –Link analysis information –Category information –Popularity information

SLIDE 55IS 202 – FALL 2003 Ranking: Hearst ‘96 Proximity search can help get high- precision results if >1 term –Combine Boolean and passage-level proximity –Proves significant improvements when retrieving top 5, 10, 20, 30 documents –Results reproduced by Mitra et al. 98 –Google uses something similar

SLIDE 56IS 202 – FALL 2003 Ranking: Link Analysis Assumptions: –If the pages pointing to this page are good, then this is also a good page –The words on the links pointing to this page are useful indicators of what this page is about –References: Page et al. 98, Kleinberg 98

SLIDE 57IS 202 – FALL 2003 Ranking: Link Analysis Why does this work? –The official Toyota site will be linked to by lots of other official (or high-quality) sites –The best Toyota fan-club site probably also has many links pointing to it –Less high-quality sites do not have as many high-quality sites linking to them

SLIDE 58IS 202 – FALL 2003 Ranking: PageRank Google uses the PageRank We assume page A has pages T1...Tn which point to it (i.e., are citations). The parameter d is a damping factor which can be set between 0 and 1. d is usually set to C(A) is defined as the number of links going out of page A. The PageRank of a page A is given as follows: PR(A) = (1-d) + d (PR(T1)/C(T1) PR(Tn)/C(Tn)) Note that the PageRanks form a probability distribution over web pages, so the sum of all web pages' PageRanks will be one

SLIDE 59IS 202 – FALL 2003 PageRank T2Pr=1 T1Pr=.725 T6Pr=1 T5Pr=1 T4Pr=1 T3Pr=1 T7Pr=1 T8Pr= X1 X2 APr= Note: these are not real PageRanks, since they include values >= 1

SLIDE 60IS 202 – FALL 2003 PageRank Similar to calculations used in scientific citation analysis (e.g., Garfield et al.) and social network analysis (e.g., Waserman et al.) Similar to other work on ranking (e.g., the hubs and authorities of Kleinberg et al.) Computation is an iterative algorithm and converges to the principle eigenvector of the link matrix

SLIDE 61IS 202 – FALL 2003 Jesse Mendelsohn Questions Many companies today complain that Google hurts their business by giving their web sites low PageRanks. Other companies have emerged that claim to be able to manipulate Google's PageRank. Do you think PageRank is fair? Is a web site's usefulness and relevance really proportional to where and how often is it cited? Also, does the ability to manipulate PageRank degrade its reliablity?

SLIDE 62IS 202 – FALL 2003 Jesse Mendelsohn Questions What are the moral ramifications of Google's system of web crawling? The paper mentions that people have gotten upset that their pages have been indexed by Google without permission, but brushes this criticism aside. Is this an invasion of privacy? If so, should Google's crawler be given enough "intelligence" to read warnings about indexing on web sites?

SLIDE 63IS 202 – FALL 2003 Jesse Mendelsohn Questions Google purports to be very good at returning relevant results for single topic queries or for single words (such as "Bill Clinton" or "CD- ROMs") and to retrieve specific relevant information, but what if you are searching for a wide area of information on a vast topic? For example, if you are writing a paper on an extremely vague subject such as "South America." Is google's search more or less efficient than, say, Yahoo!'s system of narrowing categories?

SLIDE 64IS 202 – FALL 2003 Yuri Takhteyev Questions ???

SLIDE 65IS 202 – FALL 2003 Next Time User Interfaces for Information Retrieval Readings/Discussion: –Modern Information Retrieval, Chapter (Marti Hearst) Alison –Vannevar Bush, As We May Think Jeff ( f.htm) f.htm Memex II denise Memex Revisited ryan –Don Norman, Why Interfaces Don’t Work danah