{"id":"https://openalex.org/W2482705506","doi":"https://doi.org/10.1142/9789812775375_0003","title":"WEB STRUCTURE ANALYSIS FOR INFORMATION MINING","display_name":"WEB STRUCTURE ANALYSIS FOR INFORMATION MINING","publication_year":2003,"publication_date":"2003-12-01","ids":{"openalex":"https://openalex.org/W2482705506","doi":"https://doi.org/10.1142/9789812775375_0003","mag":"2482705506"},"language":"en","primary_location":{"id":"doi:10.1142/9789812775375_0003","is_oa":false,"landing_page_url":"https://doi.org/10.1142/9789812775375_0003","pdf_url":null,"source":{"id":"https://openalex.org/S4210240769","display_name":"Series in machine perception and artificial intelligence","issn_l":"1793-0839","issn":["1793-0839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Series in Machine Perception and Artificial Intelligence","raw_type":"book-chapter"},"type":"book-chapter","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/A5053135863","display_name":"Vijjappu Lakshmi","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":true,"raw_author_name":"Vijjappu Lakshmi","raw_affiliation_strings":["School of Computing, National University of Singapore, 3 Science Drive 2, Singapore 117543, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, 3 Science Drive 2, Singapore 117543, Singapore","institution_ids":["https://openalex.org/I165932596"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5004167801","display_name":"Ah\u2010Hwee Tan","orcid":"https://orcid.org/0000-0003-0378-4069"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"Ah-Hwee Tan","raw_affiliation_strings":["Laboratories for Information Technology, 21 Heng Mui Keng Terrace, Singapore 119613, Singapore"],"affiliations":[{"raw_affiliation_string":"Laboratories for Information Technology, 21 Heng Mui Keng Terrace, Singapore 119613, Singapore","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037577367","display_name":"Chew-Lim Tan","orcid":null},"institutions":[{"id":"https://openalex.org/I165932596","display_name":"National University of Singapore","ror":"https://ror.org/01tgyzw49","country_code":"SG","type":"education","lineage":["https://openalex.org/I165932596"]}],"countries":["SG"],"is_corresponding":false,"raw_author_name":"Chew-Lim Tan","raw_affiliation_strings":["School of Computing, National University of Singapore, 3 Science Drive 2, Singapore 117543, Singapore"],"affiliations":[{"raw_affiliation_string":"School of Computing, National University of Singapore, 3 Science Drive 2, Singapore 117543, Singapore","institution_ids":["https://openalex.org/I165932596"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5053135863"],"corresponding_institution_ids":["https://openalex.org/I165932596"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":7,"citation_normalized_percentile":{"value":0.27187948,"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":"39","last_page":"57"},"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/T12479","display_name":"Web Application Security Vulnerabilities","score":0.9739000201225281,"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/T11241","display_name":"Advanced Malware Detection Techniques","score":0.9308000206947327,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"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":0.5974324345588684},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.39470598101615906},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.38510996103286743},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.375033438205719},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.36545801162719727}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5974324345588684},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.39470598101615906},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.38510996103286743},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.375033438205719},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.36545801162719727}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1142/9789812775375_0003","is_oa":false,"landing_page_url":"https://doi.org/10.1142/9789812775375_0003","pdf_url":null,"source":{"id":"https://openalex.org/S4210240769","display_name":"Series in machine perception and artificial intelligence","issn_l":"1793-0839","issn":["1793-0839"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Series in Machine Perception and Artificial Intelligence","raw_type":"book-chapter"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.1.1508","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.1.1508","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.csc.liv.ac.uk/~wda2001/Papers/18_lakshmi_wda2001.pdf","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":8,"referenced_works":["https://openalex.org/W1502749598","https://openalex.org/W1553019137","https://openalex.org/W1553229631","https://openalex.org/W1564978311","https://openalex.org/W2126185232","https://openalex.org/W2137096228","https://openalex.org/W2161077873","https://openalex.org/W4285719527"],"related_works":["https://openalex.org/W2899084033","https://openalex.org/W2748952813","https://openalex.org/W2390279801","https://openalex.org/W2358668433","https://openalex.org/W2376932109","https://openalex.org/W2001405890","https://openalex.org/W2382290278","https://openalex.org/W2350741829","https://openalex.org/W2130043461","https://openalex.org/W2530322880"],"abstract_inverted_index":{"Our":[0],"approach":[1],"to":[2,39],"extracting":[3],"information":[4,19],"from":[5],"the":[6,9,17,36,43],"web":[7,13],"analyzes":[8],"structural":[10],"content":[11],"of":[12,35,51],"pages":[14],"through":[15,69],"exploiting":[16],"latent":[18],"given":[20],"by":[21],"HTML":[22,52],"tags.":[23],"For":[24],"each":[25],"specific":[26],"extraction":[27,45,57,64],"task,":[28],"an":[29],"object":[30],"model":[31],"is":[32],"created":[33],"consisting":[34],"salient":[37],"fields":[38],"be":[40],"extracted":[41],"and":[42,62],"corresponding":[44],"rules":[46,58],"based":[47],"on":[48],"a":[49],"library":[50],"parsing":[53],"functions.":[54],"We":[55],"derive":[56],"for":[59],"both":[60],"single-slot":[61],"multiple-slot":[63],"tasks":[65],"which":[66],"we":[67],"illustrate":[68],"two":[70],"sample":[71],"domains.":[72]},"counts_by_year":[{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
