{"id":"https://openalex.org/W1974425785","doi":"https://doi.org/10.4304/jsw.6.12.2421-2425","title":"Segmenting Webpage with Gomory-Hu Tree Based Clustering","display_name":"Segmenting Webpage with Gomory-Hu Tree Based Clustering","publication_year":2011,"publication_date":"2011-12-01","ids":{"openalex":"https://openalex.org/W1974425785","doi":"https://doi.org/10.4304/jsw.6.12.2421-2425","mag":"1974425785"},"language":"en","primary_location":{"id":"doi:10.4304/jsw.6.12.2421-2425","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jsw.6.12.2421-2425","pdf_url":null,"source":{"id":"https://openalex.org/S114141714","display_name":"Journal of Software","issn_l":"1796-217X","issn":["1796-217X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318660","host_organization_name":"Academy Publisher","host_organization_lineage":["https://openalex.org/P4310318660"],"host_organization_lineage_names":["Academy Publisher"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Software","raw_type":"journal-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/A5114594132","display_name":"Xinyue Liu","orcid":"https://orcid.org/0000-0002-4063-5129"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Xinyue Liu","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"middle","author":{"id":"https://openalex.org/A5023931221","display_name":"Hongfei Lin","orcid":"https://orcid.org/0000-0003-0872-7688"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Hongfei Lin","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]},{"author_position":"last","author":{"id":"https://openalex.org/A5089331963","display_name":"Ye Tian","orcid":"https://orcid.org/0000-0002-0981-6677"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ye Tian","raw_affiliation_strings":[],"raw_orcid":null,"affiliations":[]}],"institutions":[],"countries_distinct_count":0,"institutions_distinct_count":0,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":7.5889,"has_fulltext":false,"cited_by_count":23,"citation_normalized_percentile":{"value":0.96733982,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":"6","issue":"12","first_page":null,"last_page":null},"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/T11269","display_name":"Algorithms and Data Compression","score":0.9943000078201294,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9932000041007996,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7295316457748413},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.5954651832580566},{"id":"https://openalex.org/keywords/spanning-tree","display_name":"Spanning tree","score":0.529626190662384},{"id":"https://openalex.org/keywords/graph","display_name":"Graph","score":0.5172420144081116},{"id":"https://openalex.org/keywords/minimum-spanning-tree","display_name":"Minimum spanning tree","score":0.460782915353775},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.46063172817230225},{"id":"https://openalex.org/keywords/gomory\u2013hu-tree","display_name":"Gomory\u2013Hu tree","score":0.44576725363731384},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3746054768562317},{"id":"https://openalex.org/keywords/theoretical-computer-science","display_name":"Theoretical computer science","score":0.365001916885376},{"id":"https://openalex.org/keywords/combinatorics","display_name":"Combinatorics","score":0.3639428913593292},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.30499035120010376},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.2589147686958313},{"id":"https://openalex.org/keywords/k-ary-tree","display_name":"K-ary tree","score":0.24678072333335876},{"id":"https://openalex.org/keywords/tree-structure","display_name":"Tree structure","score":0.2384926974773407},{"id":"https://openalex.org/keywords/binary-tree","display_name":"Binary tree","score":0.07407516241073608}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7295316457748413},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.5954651832580566},{"id":"https://openalex.org/C64331007","wikidata":"https://www.wikidata.org/wiki/Q831672","display_name":"Spanning tree","level":2,"score":0.529626190662384},{"id":"https://openalex.org/C132525143","wikidata":"https://www.wikidata.org/wiki/Q141488","display_name":"Graph","level":2,"score":0.5172420144081116},{"id":"https://openalex.org/C13743678","wikidata":"https://www.wikidata.org/wiki/Q240464","display_name":"Minimum spanning tree","level":2,"score":0.460782915353775},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.46063172817230225},{"id":"https://openalex.org/C147517495","wikidata":"https://www.wikidata.org/wiki/Q5581241","display_name":"Gomory\u2013Hu tree","level":5,"score":0.44576725363731384},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3746054768562317},{"id":"https://openalex.org/C80444323","wikidata":"https://www.wikidata.org/wiki/Q2878974","display_name":"Theoretical computer science","level":1,"score":0.365001916885376},{"id":"https://openalex.org/C114614502","wikidata":"https://www.wikidata.org/wiki/Q76592","display_name":"Combinatorics","level":1,"score":0.3639428913593292},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.30499035120010376},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.2589147686958313},{"id":"https://openalex.org/C100560664","wikidata":"https://www.wikidata.org/wiki/Q3608019","display_name":"K-ary tree","level":4,"score":0.24678072333335876},{"id":"https://openalex.org/C163797641","wikidata":"https://www.wikidata.org/wiki/Q2067937","display_name":"Tree structure","level":3,"score":0.2384926974773407},{"id":"https://openalex.org/C197855036","wikidata":"https://www.wikidata.org/wiki/Q380172","display_name":"Binary tree","level":2,"score":0.07407516241073608}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.4304/jsw.6.12.2421-2425","is_oa":false,"landing_page_url":"https://doi.org/10.4304/jsw.6.12.2421-2425","pdf_url":null,"source":{"id":"https://openalex.org/S114141714","display_name":"Journal of Software","issn_l":"1796-217X","issn":["1796-217X"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318660","host_organization_name":"Academy Publisher","host_organization_lineage":["https://openalex.org/P4310318660"],"host_organization_lineage_names":["Academy Publisher"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Journal of Software","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":19,"referenced_works":["https://openalex.org/W74636658","https://openalex.org/W938539187","https://openalex.org/W1581477759","https://openalex.org/W2008597108","https://openalex.org/W2020254000","https://openalex.org/W2030724586","https://openalex.org/W2040075907","https://openalex.org/W2059586463","https://openalex.org/W2090359754","https://openalex.org/W2100184871","https://openalex.org/W2101909884","https://openalex.org/W2102372499","https://openalex.org/W2115049345","https://openalex.org/W2133814403","https://openalex.org/W2140204390","https://openalex.org/W2146486820","https://openalex.org/W2154484245","https://openalex.org/W2167138081","https://openalex.org/W2610179052"],"related_works":["https://openalex.org/W2015718828","https://openalex.org/W2130375301","https://openalex.org/W3081212354","https://openalex.org/W2943635264","https://openalex.org/W2020381385","https://openalex.org/W2353822696","https://openalex.org/W2122848400","https://openalex.org/W3141326665","https://openalex.org/W2519759404","https://openalex.org/W2911818503"],"abstract_inverted_index":{"We":[0],"propose":[1],"a":[2,14,24,29],"novel":[3],"web":[4,25],"page":[5,26],"segmentationalgorithm":[6],"based":[7,58],"on":[8],"finding":[9],"the":[10,35,42,45,53,55,76],"Gomory-Hu":[11,56],"tree":[12,40,57],"in":[13],"planargraph.":[15],"The":[16],"algorithm":[17],"firstly":[18],"distills":[19],"vision":[20],"and":[21,41,82,84],"structureinformation":[22],"from":[23],"to":[27],"construct":[28],"weightedundirected":[30],"graph,":[31],"whose":[32],"vertices":[33],"are":[34],"leaf":[36],"nodes":[37],"of":[38,92],"theDOM":[39],"edges":[43],"represent":[44],"visible":[46],"positionrelationship":[47],"between":[48],"vertices.":[49],"Then":[50],"it":[51],"partitions":[52],"graphwith":[54],"clustering":[59],"algorithm.Experimental":[60],"results":[61],"show":[62],"that,":[63],"compared":[64],"with":[65,79],"VIPS":[66],"andChakrabarti":[67],"et":[68,94],"al.\u2019s":[69,95],"graph":[70,96],"theoretic":[71,97],"algorithm,":[72],"ouralgorithm":[73],"improves":[74],"upon":[75],"other":[77],"two":[78],"much":[80],"higherprecision":[81],"recall,":[83],"its":[85],"running":[86],"time":[87],"is":[88],"far":[89],"lower":[90],"thanthat":[91],"Chakrabarti":[93],"algorithm.":[98]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":3},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":2},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2014,"cited_by_count":7},{"year":2013,"cited_by_count":3}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
