{"id":"https://openalex.org/W2083394121","doi":"https://doi.org/10.1109/icde.2010.5447932","title":"On supporting effective web extraction","display_name":"On supporting effective web extraction","publication_year":2010,"publication_date":"2010-01-01","ids":{"openalex":"https://openalex.org/W2083394121","doi":"https://doi.org/10.1109/icde.2010.5447932","mag":"2083394121"},"language":"en","primary_location":{"id":"doi:10.1109/icde.2010.5447932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2010.5447932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th International Conference on Data Engineering (ICDE 2010)","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/A5035744252","display_name":"Wook-Shin Han","orcid":"https://orcid.org/0000-0001-9206-9563"},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":true,"raw_author_name":"Wook-Shin Han","raw_affiliation_strings":["Department of Computer Engineering, Kyungpook National University, South Korea","Department of Computer Engineering, Kyungpook National University, Korea.#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Kyungpook National University, South Korea","institution_ids":["https://openalex.org/I31419693"]},{"raw_affiliation_string":"Department of Computer Engineering, Kyungpook National University, Korea.#TAB#","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5027400468","display_name":"Wooseong Kwak","orcid":null},"institutions":[{"id":"https://openalex.org/I31419693","display_name":"Kyungpook National University","ror":"https://ror.org/040c17130","country_code":"KR","type":"education","lineage":["https://openalex.org/I31419693"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Wooseong Kwak","raw_affiliation_strings":["Department of Computer Engineering, Kyungpook National University, South Korea","Department of Computer Engineering, Kyungpook National University, Korea.#TAB#"],"affiliations":[{"raw_affiliation_string":"Department of Computer Engineering, Kyungpook National University, South Korea","institution_ids":["https://openalex.org/I31419693"]},{"raw_affiliation_string":"Department of Computer Engineering, Kyungpook National University, Korea.#TAB#","institution_ids":["https://openalex.org/I31419693"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5045521125","display_name":"Hwanjo Yu","orcid":"https://orcid.org/0000-0002-7510-0255"},"institutions":[{"id":"https://openalex.org/I123900574","display_name":"Pohang University of Science and Technology","ror":"https://ror.org/04xysgw12","country_code":"KR","type":"education","lineage":["https://openalex.org/I123900574"]}],"countries":["KR"],"is_corresponding":false,"raw_author_name":"Hwanjo Yu","raw_affiliation_strings":["Department of Computer Science and Engineering, Pohang University of Science and Technology, South Korea","[Dept. of Computer Science and Engineering, POSTECH, Korea]"],"affiliations":[{"raw_affiliation_string":"Department of Computer Science and Engineering, Pohang University of Science and Technology, South Korea","institution_ids":["https://openalex.org/I123900574"]},{"raw_affiliation_string":"[Dept. of Computer Science and Engineering, POSTECH, Korea]","institution_ids":["https://openalex.org/I123900574"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5035744252"],"corresponding_institution_ids":["https://openalex.org/I31419693"],"apc_list":null,"apc_paid":null,"fwci":0.7142,"has_fulltext":false,"cited_by_count":2,"citation_normalized_percentile":{"value":0.83612318,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":90,"max":94},"biblio":{"volume":null,"issue":null,"first_page":"773","last_page":"775"},"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":0.9869999885559082,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9868999719619751,"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/xpath","display_name":"XPath","score":0.864020824432373},{"id":"https://openalex.org/keywords/tuple","display_name":"Tuple","score":0.8297549486160278},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8255405426025391},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5883960723876953},{"id":"https://openalex.org/keywords/joins","display_name":"Joins","score":0.5409520268440247},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5333188772201538},{"id":"https://openalex.org/keywords/tree","display_name":"Tree (set theory)","score":0.5105217695236206},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.44958025217056274},{"id":"https://openalex.org/keywords/spatial-database","display_name":"Spatial database","score":0.4351135492324829},{"id":"https://openalex.org/keywords/database","display_name":"Database","score":0.33960238099098206},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.32151493430137634},{"id":"https://openalex.org/keywords/xml","display_name":"XML","score":0.25020045042037964},{"id":"https://openalex.org/keywords/spatial-analysis","display_name":"Spatial analysis","score":0.23482158780097961},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1028205156326294},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.07607224583625793},{"id":"https://openalex.org/keywords/xml-database","display_name":"XML database","score":0.07431969046592712}],"concepts":[{"id":"https://openalex.org/C2780213375","wikidata":"https://www.wikidata.org/wiki/Q16340","display_name":"XPath","level":4,"score":0.864020824432373},{"id":"https://openalex.org/C118930307","wikidata":"https://www.wikidata.org/wiki/Q600590","display_name":"Tuple","level":2,"score":0.8297549486160278},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8255405426025391},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5883960723876953},{"id":"https://openalex.org/C2778692605","wikidata":"https://www.wikidata.org/wiki/Q4041866","display_name":"Joins","level":2,"score":0.5409520268440247},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5333188772201538},{"id":"https://openalex.org/C113174947","wikidata":"https://www.wikidata.org/wiki/Q2859736","display_name":"Tree (set theory)","level":2,"score":0.5105217695236206},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.44958025217056274},{"id":"https://openalex.org/C203689450","wikidata":"https://www.wikidata.org/wiki/Q2302053","display_name":"Spatial database","level":3,"score":0.4351135492324829},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.33960238099098206},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.32151493430137634},{"id":"https://openalex.org/C8797682","wikidata":"https://www.wikidata.org/wiki/Q2115","display_name":"XML","level":2,"score":0.25020045042037964},{"id":"https://openalex.org/C159620131","wikidata":"https://www.wikidata.org/wiki/Q1938983","display_name":"Spatial analysis","level":2,"score":0.23482158780097961},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1028205156326294},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.07607224583625793},{"id":"https://openalex.org/C183068750","wikidata":"https://www.wikidata.org/wiki/Q357393","display_name":"XML database","level":3,"score":0.07431969046592712},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.0},{"id":"https://openalex.org/C118615104","wikidata":"https://www.wikidata.org/wiki/Q121416","display_name":"Discrete mathematics","level":1,"score":0.0},{"id":"https://openalex.org/C134306372","wikidata":"https://www.wikidata.org/wiki/Q7754","display_name":"Mathematical analysis","level":1,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1109/icde.2010.5447932","is_oa":false,"landing_page_url":"https://doi.org/10.1109/icde.2010.5447932","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2010 IEEE 26th International Conference on Data Engineering (ICDE 2010)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.632.4074","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.632.4074","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://rosaec.snu.ac.kr/publish/2010/T3/HaKwYu-ICDE-2010.pdf","raw_type":"text"},{"id":"pmh:oai:oasis.postech.ac.kr:2014.oak/92224","is_oa":false,"landing_page_url":"https://oasis.postech.ac.kr/handle/2014.oak/92224","pdf_url":null,"source":{"id":"https://openalex.org/S4306401965","display_name":"Open Access System for Information Sharing (Pohang University of Science and Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I123900574","host_organization_name":"Pohang University of Science and Technology","host_organization_lineage":["https://openalex.org/I123900574"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":14,"referenced_works":["https://openalex.org/W173943678","https://openalex.org/W1927338256","https://openalex.org/W2001959118","https://openalex.org/W2102189859","https://openalex.org/W2133669904","https://openalex.org/W2148210463","https://openalex.org/W2151192680","https://openalex.org/W2158237121","https://openalex.org/W2161484642","https://openalex.org/W4206873214","https://openalex.org/W6681973738","https://openalex.org/W6682207236","https://openalex.org/W6807234295","https://openalex.org/W6959696218"],"related_works":["https://openalex.org/W1983953208","https://openalex.org/W2016456293","https://openalex.org/W2161128265","https://openalex.org/W1997896902","https://openalex.org/W2138101384","https://openalex.org/W2140894225","https://openalex.org/W2080819440","https://openalex.org/W2125826941","https://openalex.org/W4212828571","https://openalex.org/W2045235113"],"abstract_inverted_index":{"Commercial":[0],"tuple":[1,51,129],"extraction":[2,52,121,130],"systems":[3,33],"have":[4],"enjoyed":[5],"some":[6],"success":[7],"to":[8,22,37,87],"extract":[9,88],"tuples":[10,26],"by":[11,101,110],"regarding":[12],"HTML":[13,29],"pages":[14],"as":[15,76,117,119],"tree":[16],"structures":[17],"and":[18,83,122],"exploiting":[19],"XPath":[20,63],"queries":[21,64],"find":[23],"attributes":[24],"of":[25,65],"in":[27,72,79,97],"the":[28,41,62,66,73,80],"pages.":[30,43],"However,":[31],"such":[32],"would":[34],"be":[35,116],"vulnerable":[36],"small":[38],"changes":[39],"on":[40],"web":[42,99],"In":[44],"this":[45],"paper,":[46],"we":[47],"propose":[48],"a":[49,98],"robust":[50,118,126],"system":[53,69,107],"which":[54],"utilizes":[55],"spatial":[56,77,85,104,112],"relationships":[57,113],"among":[58],"elements":[59,71,109],"rather":[60],"than":[61,127],"elements.":[67,90],"Our":[68],"regards":[70],"rendered":[74],"page":[75,100],"objects":[78],"2-D":[81],"space":[82],"executes":[84],"joins":[86],"target":[89],"Since":[91],"humans":[92],"also":[93],"identify":[94],"an":[95],"element":[96],"its":[102],"relative":[103],"location,":[105],"our":[106],"extracting":[108],"their":[111],"could":[114],"possibly":[115],"manual":[120],"is":[123],"far":[124],"more":[125],"existing":[128],"systems.":[131]},"counts_by_year":[{"year":2014,"cited_by_count":1}],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}
