{"id":"https://openalex.org/W2005257090","doi":"https://doi.org/10.1145/1810617.1810685","title":"Automatic extraction of structure, content and usage data statistics of web sites","display_name":"Automatic extraction of structure, content and usage data statistics of web sites","publication_year":2010,"publication_date":"2010-06-13","ids":{"openalex":"https://openalex.org/W2005257090","doi":"https://doi.org/10.1145/1810617.1810685","mag":"2005257090"},"language":"en","primary_location":{"id":"doi:10.1145/1810617.1810685","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1810617.1810685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM conference on Hypertext and hypermedia","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/A5003547538","display_name":"Ioannis Paparrizos","orcid":null},"institutions":[{"id":"https://openalex.org/I5124864","display_name":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne","ror":"https://ror.org/02s376052","country_code":"CH","type":"education","lineage":["https://openalex.org/I2799323385","https://openalex.org/I5124864"]}],"countries":["CH"],"is_corresponding":true,"raw_author_name":"Ioannis Paparrizos","raw_affiliation_strings":["\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland"],"affiliations":[{"raw_affiliation_string":"\u00c9cole Polytechnique F\u00e9d\u00e9rale de Lausanne, Lausanne, Switzerland","institution_ids":["https://openalex.org/I5124864"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053612789","display_name":"Vassiliki Koutsonikola","orcid":null},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Vassiliki Koutsonikola","raw_affiliation_strings":["Aristotle University, Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Aristotle University, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5008070273","display_name":"Lefteris Angelis","orcid":"https://orcid.org/0000-0002-6677-4039"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Lefteris Angelis","raw_affiliation_strings":["Aristotle University, Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Aristotle University, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002623428","display_name":"Athena Vakali","orcid":"https://orcid.org/0000-0002-0666-6984"},"institutions":[{"id":"https://openalex.org/I21370196","display_name":"Aristotle University of Thessaloniki","ror":"https://ror.org/02j61yw88","country_code":"GR","type":"education","lineage":["https://openalex.org/I21370196"]}],"countries":["GR"],"is_corresponding":false,"raw_author_name":"Athena Vakali","raw_affiliation_strings":["Aristotle University, Thessaloniki, Greece"],"affiliations":[{"raw_affiliation_string":"Aristotle University, Thessaloniki, Greece","institution_ids":["https://openalex.org/I21370196"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":4,"corresponding_author_ids":["https://openalex.org/A5003547538"],"corresponding_institution_ids":["https://openalex.org/I5124864"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.13097547,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"301","last_page":"302"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9993000030517578,"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":0.9993000030517578,"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":0.9908999800682068,"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/T10538","display_name":"Data Mining Algorithms and Applications","score":0.9779000282287598,"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/computer-science","display_name":"Computer science","score":0.80836021900177},{"id":"https://openalex.org/keywords/web-crawler","display_name":"Web crawler","score":0.7840750217437744},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.7249919772148132},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.563823401927948},{"id":"https://openalex.org/keywords/data-web","display_name":"Data Web","score":0.5270987749099731},{"id":"https://openalex.org/keywords/web-content","display_name":"Web content","score":0.4927733242511749},{"id":"https://openalex.org/keywords/web-modeling","display_name":"Web modeling","score":0.4905316233634949},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.47729456424713135},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.4112507998943329},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.400519460439682}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.80836021900177},{"id":"https://openalex.org/C13743948","wikidata":"https://www.wikidata.org/wiki/Q45842","display_name":"Web crawler","level":2,"score":0.7840750217437744},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.7249919772148132},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.563823401927948},{"id":"https://openalex.org/C162005631","wikidata":"https://www.wikidata.org/wiki/Q54837","display_name":"Data Web","level":3,"score":0.5270987749099731},{"id":"https://openalex.org/C2776324614","wikidata":"https://www.wikidata.org/wiki/Q3948731","display_name":"Web content","level":3,"score":0.4927733242511749},{"id":"https://openalex.org/C130436687","wikidata":"https://www.wikidata.org/wiki/Q7978591","display_name":"Web modeling","level":3,"score":0.4905316233634949},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.47729456424713135},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.4112507998943329},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.400519460439682}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/1810617.1810685","is_oa":false,"landing_page_url":"https://doi.org/10.1145/1810617.1810685","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 21st ACM conference on Hypertext and hypermedia","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":2,"referenced_works":["https://openalex.org/W2155163093","https://openalex.org/W2166325326"],"related_works":["https://openalex.org/W132269582","https://openalex.org/W2945931694","https://openalex.org/W2622968908","https://openalex.org/W2511337351","https://openalex.org/W3174726539","https://openalex.org/W2187012497","https://openalex.org/W2182629206","https://openalex.org/W2134078223","https://openalex.org/W2384444869","https://openalex.org/W2744329849"],"abstract_inverted_index":{"In":[0],"this":[1],"paper":[2],"we":[3],"present":[4],"a":[5,70],"web":[6,20,29,35,38,42,67,76],"mining":[7,30,40],"tool":[8,71],"which":[9],"automatically":[10,73],"extracts":[11],"the":[12,26,52,64],"structure,":[13,53],"content":[14,39,54],"and":[15,41,55,98,102],"usage":[16,43,56],"data":[17,57,78],"statistics":[18,97],"of":[19,32,47,85,107],"sites.":[21],"This":[22],"work":[23],"inspired":[24],"by":[25],"fact":[27],"that":[28,79],"consists":[31],"three":[33,87],"axes:":[34],"structure":[36],"mining,":[37],"mining.":[44],"Each":[45],"one":[46,84],"those":[48,86],"axes":[49,88],"is":[50,61,110],"using":[51],"respectively.":[58],"The":[59],"scope":[60],"to":[62,72,92],"use":[63],"developed":[65],"multi-thread":[66],"crawler":[68],"as":[69,112,114],"extract":[74],"from":[75],"pages":[77],"are":[80],"associated":[81],"with":[82],"each":[83],"in":[89],"order":[90],"afterwards":[91],"compute":[93],"several":[94],"useful":[95],"descriptive":[96],"apply":[99],"advanced":[100],"mathematical":[101],"statistical":[103],"methods.":[104],"A":[105],"description":[106],"our":[108],"system":[109],"provided":[111],"well":[113],"some":[115],"experimentation":[116],"results.":[117]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
