{"id":"https://openalex.org/W2007278884","doi":"https://doi.org/10.1145/2505515.2505558","title":"Web news extraction via path ratios","display_name":"Web news extraction via path ratios","publication_year":2013,"publication_date":"2013-10-27","ids":{"openalex":"https://openalex.org/W2007278884","doi":"https://doi.org/10.1145/2505515.2505558","mag":"2007278884"},"language":"en","primary_location":{"id":"doi:10.1145/2505515.2505558","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2505515.2505558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Information & Knowledge Management","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/A5059939190","display_name":"Gongqing Wu","orcid":"https://orcid.org/0000-0003-2289-1679"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":true,"raw_author_name":"Gongqing Wu","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5100361421","display_name":"Li Li","orcid":"https://orcid.org/0009-0000-0437-6193"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Li Li","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5064347324","display_name":"Xuegang Hu","orcid":"https://orcid.org/0000-0001-5421-6171"},"institutions":[{"id":"https://openalex.org/I16365422","display_name":"Hefei University of Technology","ror":"https://ror.org/02czkny70","country_code":"CN","type":"education","lineage":["https://openalex.org/I16365422"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Xuegang Hu","raw_affiliation_strings":["Hefei University of Technology, Hefei, China"],"affiliations":[{"raw_affiliation_string":"Hefei University of Technology, Hefei, China","institution_ids":["https://openalex.org/I16365422"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5080738591","display_name":"Xindong Wu","orcid":"https://orcid.org/0000-0003-2396-1704"},"institutions":[{"id":"https://openalex.org/I111236770","display_name":"University of Vermont","ror":"https://ror.org/0155zta11","country_code":"US","type":"education","lineage":["https://openalex.org/I111236770"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Xindong Wu","raw_affiliation_strings":["University of Vermont, Burlington, USA"],"affiliations":[{"raw_affiliation_string":"University of Vermont, Burlington, USA","institution_ids":["https://openalex.org/I111236770"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5059939190"],"corresponding_institution_ids":["https://openalex.org/I16365422"],"apc_list":null,"apc_paid":null,"fwci":2.4269,"has_fulltext":false,"cited_by_count":19,"citation_normalized_percentile":{"value":0.90753133,"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":"2059","last_page":"2068"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":1.0,"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":1.0,"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/T11269","display_name":"Algorithms and Data Compression","score":0.9855999946594238,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"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/T11478","display_name":"Caching and Content Delivery","score":0.9785000085830688,"subfield":{"id":"https://openalex.org/subfields/1705","display_name":"Computer Networks and Communications"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7183160185813904},{"id":"https://openalex.org/keywords/path","display_name":"Path (computing)","score":0.622137188911438},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5726319551467896},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5226283073425293},{"id":"https://openalex.org/keywords/relevance","display_name":"Relevance (law)","score":0.4328681230545044},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.317241370677948}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7183160185813904},{"id":"https://openalex.org/C2777735758","wikidata":"https://www.wikidata.org/wiki/Q817765","display_name":"Path (computing)","level":2,"score":0.622137188911438},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5726319551467896},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5226283073425293},{"id":"https://openalex.org/C158154518","wikidata":"https://www.wikidata.org/wiki/Q7310970","display_name":"Relevance (law)","level":2,"score":0.4328681230545044},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.317241370677948},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2505515.2505558","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2505515.2505558","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 22nd ACM international conference on Information & Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W15548","https://openalex.org/W111639511","https://openalex.org/W1519606823","https://openalex.org/W1551178608","https://openalex.org/W1553229631","https://openalex.org/W1647671624","https://openalex.org/W1927338256","https://openalex.org/W2003107832","https://openalex.org/W2019577381","https://openalex.org/W2022605955","https://openalex.org/W2037504378","https://openalex.org/W2051141368","https://openalex.org/W2053045757","https://openalex.org/W2065568440","https://openalex.org/W2069388662","https://openalex.org/W2071628657","https://openalex.org/W2072936489","https://openalex.org/W2104086170","https://openalex.org/W2117209866","https://openalex.org/W2117694587","https://openalex.org/W2138405339","https://openalex.org/W2140204390","https://openalex.org/W2143309843","https://openalex.org/W2145404631","https://openalex.org/W2150721933","https://openalex.org/W2160196229","https://openalex.org/W2162340487","https://openalex.org/W2163072729","https://openalex.org/W2407338347","https://openalex.org/W2533495960","https://openalex.org/W3004954992","https://openalex.org/W3015882749","https://openalex.org/W6600000387","https://openalex.org/W6728505807"],"related_works":["https://openalex.org/W1967370444","https://openalex.org/W2150136235","https://openalex.org/W2085215424","https://openalex.org/W2088814244","https://openalex.org/W2157408137","https://openalex.org/W4312252109","https://openalex.org/W1488511360","https://openalex.org/W1781894645","https://openalex.org/W2894902932","https://openalex.org/W569715723"],"abstract_inverted_index":{"In":[0,125,156],"addition":[1],"to":[2,88,95,103,158],"the":[3,26,34,40,45,51,90,110,117,152,160,185,201],"news":[4,8,16,27,35,41,123,146,196,206,242],"content,":[5],"most":[6,246],"web":[7,71,122,205,241],"pages":[9,207],"also":[10,31],"contain":[11],"navigation":[12],"panels,":[13],"advertisements,":[14],"related":[15],"links":[17],"etc.":[18],"These":[19],"non-news":[20,149],"items":[21],"not":[22],"only":[23],"exist":[24],"outside":[25],"region,":[28],"but":[29,190],"are":[30],"present":[32,129],"in":[33,164,195],"content":[36,42,55,72,147,150],"region.":[37],"Effectively":[38],"extracting":[39,165],"and":[43,57,74,100,108,140,204,221,226,233],"filtering":[44],"noise":[46,192],"have":[47,63],"important":[48],"effects":[49],"on":[50,79,200],"follow-up":[52],"activities":[53],"of":[54,92,113,120,162,187],"management":[56],"analysis.":[58],"Our":[59],"extensive":[60],"case":[61],"studies":[62],"indicated":[64],"that":[65,214],"there":[66],"exists":[67],"potential":[68],"relevance":[69],"between":[70],"layouts":[73],"their":[75],"tag":[76,85,96,104,177],"paths.":[77],"Based":[78],"this":[80,126],"observation,":[81],"we":[82,128,168],"design":[83],"two":[84],"path":[86,178],"features":[87],"measure":[89],"importance":[91,186],"nodes:":[93],"Text":[94,102],"Path":[97,105,133],"Ratio":[98,106],"(TPR)":[99],"Extended":[101],"(ETPR),":[107],"describe":[109],"calculation":[111],"process":[112],"TPR":[114],"by":[115,151,175],"traversing":[116],"parsing":[118],"tree":[119],"a":[121,137,170,176],"page.":[124],"paper,":[127],"Content":[130],"Extraction":[131],"via":[132],"Ratios":[134],"(CEPR)":[135],"-":[136],"fast,":[138],"accurate":[139],"general":[141],"on-line":[142],"method":[143,173],"for":[144],"distinguishing":[145],"from":[148,210],"TPR/ETPR":[153],"histogram":[154],"effectively.":[155],"order":[157],"improve":[159],"ability":[161],"CEPR":[163,215,230],"short":[166],"texts,":[167],"propose":[169],"Gaussian":[171],"smoothing":[172],"weighted":[174],"edit":[179],"distance.":[180],"This":[181],"approach":[182],"can":[183,216],"enhance":[184],"internal-link":[188],"nodes":[189,193],"ignore":[191],"existing":[194,247],"content.":[197],"Experimental":[198],"results":[199],"CleanEval":[202],"datasets":[203],"randomly":[208],"selected":[209],"well-known":[211],"websites":[212],"show":[213],"extract":[217],"across":[218],"multi-resources,":[219],"multi-styles,":[220],"multi-languages.":[222],"The":[223],"average":[224,227],"F":[225],"score":[228],"with":[229],"is":[231],"8.69%":[232],"14.25%":[234],"higher":[235],"than":[236,245],"CETR,":[237],"which":[238],"demonstrates":[239],"better":[240],"extraction":[243],"performance":[244],"methods.":[248]},"counts_by_year":[{"year":2024,"cited_by_count":1},{"year":2023,"cited_by_count":2},{"year":2022,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}