{"id":"https://openalex.org/W1515339153","doi":"https://doi.org/10.1007/978-3-540-69858-6_11","title":"Exploiting Multiple Features with MEMMs for Focused Web Crawling","display_name":"Exploiting Multiple Features with MEMMs for Focused Web Crawling","publication_year":2008,"publication_date":"2008-07-31","ids":{"openalex":"https://openalex.org/W1515339153","doi":"https://doi.org/10.1007/978-3-540-69858-6_11","mag":"1515339153"},"language":"en","primary_location":{"id":"doi:10.1007/978-3-540-69858-6_11","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-69858-6_11","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://nrc-publications.canada.ca/eng/view/accepted/?id=32528c1e-e4f6-40ce-ba06-414d5bd7f94c","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100773328","display_name":"Hongyu Liu","orcid":"https://orcid.org/0000-0002-4628-6388"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Hongyu Liu","raw_affiliation_strings":["National Research Council Institute for Information Technology, Canada Faculty of Computer Science, Dalhousie University, Canada","National Research Council Institute for Information Technology, Canada Faculty of Computer Science, Dalhousie University, Canada#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Research Council Institute for Information Technology, Canada Faculty of Computer Science, Dalhousie University, Canada","institution_ids":["https://openalex.org/I129902397"]},{"raw_affiliation_string":"National Research Council Institute for Information Technology, Canada Faculty of Computer Science, Dalhousie University, Canada#TAB#","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5013989913","display_name":"Evangelos Milios","orcid":"https://orcid.org/0000-0001-5549-4675"},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Evangelos Milios","raw_affiliation_strings":["National Research Council Institute for Information Technology, Canada Faculty of Computer Science, Dalhousie University, Canada","National Research Council Institute for Information Technology, Canada Faculty of Computer Science, Dalhousie University, Canada#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Research Council Institute for Information Technology, Canada Faculty of Computer Science, Dalhousie University, Canada","institution_ids":["https://openalex.org/I129902397"]},{"raw_affiliation_string":"National Research Council Institute for Information Technology, Canada Faculty of Computer Science, Dalhousie University, Canada#TAB#","institution_ids":["https://openalex.org/I129902397"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5083359080","display_name":"Larry Korba","orcid":null},"institutions":[{"id":"https://openalex.org/I129902397","display_name":"Dalhousie University","ror":"https://ror.org/01e6qks80","country_code":"CA","type":"education","lineage":["https://openalex.org/I129902397"]}],"countries":["CA"],"is_corresponding":false,"raw_author_name":"Larry Korba","raw_affiliation_strings":["National Research Council Institute for Information Technology, Canada Faculty of Computer Science, Dalhousie University, Canada","National Research Council Institute for Information Technology, Canada Faculty of Computer Science, Dalhousie University, Canada#TAB#"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"National Research Council Institute for Information Technology, Canada Faculty of Computer Science, Dalhousie University, Canada","institution_ids":["https://openalex.org/I129902397"]},{"raw_affiliation_string":"National Research Council Institute for Information Technology, Canada Faculty of Computer Science, Dalhousie University, Canada#TAB#","institution_ids":["https://openalex.org/I129902397"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I129902397"],"apc_list":{"value":5000,"currency":"EUR","value_usd":5392},"apc_paid":null,"fwci":null,"has_fulltext":true,"cited_by_count":4,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"99","last_page":"110"},"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":0.9521999955177307,"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/T12799","display_name":"Mobile and Web Applications","score":0.9408000111579895,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/crawling","display_name":"Crawling","score":0.9377862811088562},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.9147344827651978},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8721232414245605},{"id":"https://openalex.org/keywords/focused-crawler","display_name":"Focused crawler","score":0.6156851053237915},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5941346287727356},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.5741161108016968},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5454994440078735},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5200436115264893},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.5130742788314819},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.4590986371040344},{"id":"https://openalex.org/keywords/link-analysis","display_name":"Link analysis","score":0.4535965323448181},{"id":"https://openalex.org/keywords/static-web-page","display_name":"Static web page","score":0.22254037857055664},{"id":"https://openalex.org/keywords/web-development","display_name":"Web development","score":0.21873638033866882}],"concepts":[{"id":"https://openalex.org/C100368936","wikidata":"https://www.wikidata.org/wiki/Q1411725","display_name":"Crawling","level":2,"score":0.9377862811088562},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.9147344827651978},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8721232414245605},{"id":"https://openalex.org/C73340581","wikidata":"https://www.wikidata.org/wiki/Q5463958","display_name":"Focused crawler","level":5,"score":0.6156851053237915},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5941346287727356},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.5741161108016968},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5454994440078735},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5200436115264893},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.5130742788314819},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.4590986371040344},{"id":"https://openalex.org/C1173588","wikidata":"https://www.wikidata.org/wiki/Q6554294","display_name":"Link analysis","level":2,"score":0.4535965323448181},{"id":"https://openalex.org/C173576120","wikidata":"https://www.wikidata.org/wiki/Q2641220","display_name":"Static web page","level":4,"score":0.22254037857055664},{"id":"https://openalex.org/C79373723","wikidata":"https://www.wikidata.org/wiki/Q386275","display_name":"Web development","level":3,"score":0.21873638033866882},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C105702510","wikidata":"https://www.wikidata.org/wiki/Q514","display_name":"Anatomy","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C71924100","wikidata":"https://www.wikidata.org/wiki/Q11190","display_name":"Medicine","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1007/978-3-540-69858-6_11","is_oa":false,"landing_page_url":"https://doi.org/10.1007/978-3-540-69858-6_11","pdf_url":null,"source":{"id":"https://openalex.org/S106296714","display_name":"Lecture notes in computer science","issn_l":"0302-9743","issn":["0302-9743","1611-3349"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319900","host_organization_name":"Springer Science+Business Media","host_organization_lineage":["https://openalex.org/P4310319900","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Springer Science+Business Media","Springer Nature"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Lecture Notes in Computer Science","raw_type":"book-chapter"},{"id":"pmh:oai:cisti-icist.nrc-cnrc.ca:cistinparc:5765089","is_oa":true,"landing_page_url":"https://nrc-publications.canada.ca/eng/view/object/?id=32528c1e-e4f6-40ce-ba06-414d5bd7f94c","pdf_url":"https://nrc-publications.canada.ca/eng/view/accepted/?id=32528c1e-e4f6-40ce-ba06-414d5bd7f94c","source":{"id":"https://openalex.org/S7407055245","display_name":"NPARC","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.161.6645","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.161.6645","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://users.cs.dal.ca/~eem/cvWeb/pubs/hongyu-NLDB08.pdf","raw_type":"text"}],"best_oa_location":{"id":"pmh:oai:cisti-icist.nrc-cnrc.ca:cistinparc:5765089","is_oa":true,"landing_page_url":"https://nrc-publications.canada.ca/eng/view/object/?id=32528c1e-e4f6-40ce-ba06-414d5bd7f94c","pdf_url":"https://nrc-publications.canada.ca/eng/view/accepted/?id=32528c1e-e4f6-40ce-ba06-414d5bd7f94c","source":{"id":"https://openalex.org/S7407055245","display_name":"NPARC","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":null,"host_organization_name":null,"host_organization_lineage":[],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"article"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":true,"grobid_xml":true},"content_urls":{"pdf":"https://content.openalex.org/works/W1515339153.pdf","grobid_xml":"https://content.openalex.org/works/W1515339153.grobid-xml"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W1485536830","https://openalex.org/W1934019294","https://openalex.org/W2000900876","https://openalex.org/W2005579877","https://openalex.org/W2017224880","https://openalex.org/W2017726337","https://openalex.org/W2029341294","https://openalex.org/W2045998703","https://openalex.org/W2081128931","https://openalex.org/W2102942431","https://openalex.org/W2116224704","https://openalex.org/W2121294789","https://openalex.org/W2124673015","https://openalex.org/W2141825421","https://openalex.org/W2151007976","https://openalex.org/W2156515921","https://openalex.org/W2162502927","https://openalex.org/W2494048233","https://openalex.org/W2612085100","https://openalex.org/W2622248957","https://openalex.org/W3029645440","https://openalex.org/W4235996464","https://openalex.org/W4293775970"],"related_works":["https://openalex.org/W2375180657","https://openalex.org/W2042034567","https://openalex.org/W2026132847","https://openalex.org/W1506122440","https://openalex.org/W2358310581","https://openalex.org/W2274831913","https://openalex.org/W4385695127","https://openalex.org/W2137810919","https://openalex.org/W1999548128","https://openalex.org/W4254300012"],"abstract_inverted_index":null,"counts_by_year":[{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2014,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}
