{"id":"https://openalex.org/W2058201162","doi":"https://doi.org/10.1145/1772690.1772713","title":"The paths more taken","display_name":"The paths more taken","publication_year":2010,"publication_date":"2010-04-26","ids":{"openalex":"https://openalex.org/W2058201162","doi":"https://doi.org/10.1145/1772690.1772713","mag":"2058201162"},"language":"en","primary_location":{"id":"doi:10.1145/1772690.1772713","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1772690.1772713","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th international conference on World wide web","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5078048346","display_name":"Deepayan Chakrabarti","orcid":"https://orcid.org/0000-0002-3863-4928"},"institutions":[{"id":"https://openalex.org/I4210134091","display_name":"Yahoo (United States)","ror":"https://ror.org/040dkzz12","country_code":"US","type":"company","lineage":["https://openalex.org/I4210134091"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Deepayan Chakrabarti","raw_affiliation_strings":["Yahoo! Research, Sunnyvale, CA, USA"],"affiliations":[{"raw_affiliation_string":"Yahoo! Research, Sunnyvale, CA, USA","institution_ids":["https://openalex.org/I4210134091"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5065369619","display_name":"Rupesh Mehta","orcid":null},"institutions":[{"id":"https://openalex.org/I1325784139","display_name":"Yahoo (United Kingdom)","ror":"https://ror.org/038p3gq39","country_code":"GB","type":"company","lineage":["https://openalex.org/I1325784139","https://openalex.org/I4210134091"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Rupesh Mehta","raw_affiliation_strings":["Yahoo! Labs, Bangalore, India","[Yahoo! Labs, Bangalore, India]"],"affiliations":[{"raw_affiliation_string":"Yahoo! Labs, Bangalore, India","institution_ids":[]},{"raw_affiliation_string":"[Yahoo! Labs, Bangalore, India]","institution_ids":["https://openalex.org/I1325784139"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5078048346"],"corresponding_institution_ids":["https://openalex.org/I4210134091"],"apc_list":null,"apc_paid":null,"fwci":3.4685,"has_fulltext":false,"cited_by_count":15,"citation_normalized_percentile":{"value":0.93802024,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"211","last_page":"220"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9998999834060669,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T13976","display_name":"Web visibility and informetrics","score":0.9850000143051147,"subfield":{"id":"https://openalex.org/subfields/1710","display_name":"Information Systems"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10064","display_name":"Complex Network Analysis Techniques","score":0.9830999970436096,"subfield":{"id":"https://openalex.org/subfields/3109","display_name":"Statistical and Nonlinear Physics"},"field":{"id":"https://openalex.org/fields/31","display_name":"Physics and Astronomy"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.8421429395675659},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.7774749398231506},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.716693639755249},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5730200409889221},{"id":"https://openalex.org/keywords/matching","display_name":"Matching (statistics)","score":0.5266155004501343},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.4404246211051941},{"id":"https://openalex.org/keywords/hierarchical-clustering","display_name":"Hierarchical clustering","score":0.41355279088020325},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.4128313660621643},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.34705376625061035},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.31270524859428406},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.15648812055587769},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.08524394035339355}],"concepts":[{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.8421429395675659},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.7774749398231506},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.716693639755249},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5730200409889221},{"id":"https://openalex.org/C165064840","wikidata":"https://www.wikidata.org/wiki/Q1321061","display_name":"Matching (statistics)","level":2,"score":0.5266155004501343},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.4404246211051941},{"id":"https://openalex.org/C92835128","wikidata":"https://www.wikidata.org/wiki/Q1277447","display_name":"Hierarchical clustering","level":3,"score":0.41355279088020325},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.4128313660621643},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.34705376625061035},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.31270524859428406},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.15648812055587769},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.08524394035339355},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1772690.1772713","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1772690.1772713","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 19th international conference on World wide web","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/10","score":0.5199999809265137,"display_name":"Reduced inequalities"}],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":22,"referenced_works":["https://openalex.org/W22683294","https://openalex.org/W135761774","https://openalex.org/W602980269","https://openalex.org/W1553019137","https://openalex.org/W2008690976","https://openalex.org/W2013725398","https://openalex.org/W2021088858","https://openalex.org/W2023094000","https://openalex.org/W2035582095","https://openalex.org/W2040075907","https://openalex.org/W2049365470","https://openalex.org/W2051834357","https://openalex.org/W2102694093","https://openalex.org/W2104086170","https://openalex.org/W2129595335","https://openalex.org/W2138405339","https://openalex.org/W2145805921","https://openalex.org/W2147909264","https://openalex.org/W2152565070","https://openalex.org/W2156049581","https://openalex.org/W2160196229","https://openalex.org/W4235169531"],"related_works":["https://openalex.org/W4298130764","https://openalex.org/W2804364458","https://openalex.org/W2132641928","https://openalex.org/W4310225030","https://openalex.org/W2090259340","https://openalex.org/W1926736923","https://openalex.org/W2393816671","https://openalex.org/W2158836806","https://openalex.org/W2083665254","https://openalex.org/W3200375535"],"abstract_inverted_index":{"An":[0],"unsupervised":[1],"clustering":[2,40,112],"of":[3,30,54,61,82,93,104],"the":[4,48,62,101],"webpages":[5],"on":[6,37,76,84,96],"a":[7,10,52],"website":[8],"is":[9],"primary":[11],"requirement":[12],"for":[13],"most":[14],"wrapper":[15],"induction":[16],"and":[17],"automated":[18],"data":[19],"extraction":[20],"methods.":[21],"Since":[22],"page":[23],"content":[24],"can":[25],"vary":[26],"drastically":[27],"across":[28],"pages":[29,36,74,94],"one":[31],"cluster":[32],"(e.g.,":[33,79,106],"all":[34],"product":[35,86],"amazon.com),":[38],"traditional":[39],"methods":[41],"typically":[42],"use":[43],"some":[44],"distance":[45,68],"function":[46],"between":[47,72],"DOM":[49,63,102],"trees":[50,103],"representing":[51],"pair":[53],"webpages.":[55],"However,":[56],"without":[57],"knowing":[58],"which":[59],"portions":[60],"tree":[64],"are":[65],"\"important,\"":[66],"such":[67],"functions":[69],"might":[70],"discriminate":[71],"similar":[73],"based":[75,95],"trivial":[77],"features":[78,98],"differing":[80],"number":[81],"reviews":[83],"two":[85],"pages),":[87],"or":[88],"club":[89],"together":[90],"distinct":[91],"types":[92],"superficial":[97],"present":[99],"in":[100],"both":[105],"matching":[107],"footer/copyright),":[108],"leading":[109],"to":[110],"poor":[111],"performance.":[113]},"counts_by_year":[{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}