{"id":"https://openalex.org/W1977453598","doi":"https://doi.org/10.1145/2556195.2556197","title":"Exploration and mining of web repositories","display_name":"Exploration and mining of web repositories","publication_year":2014,"publication_date":"2014-02-18","ids":{"openalex":"https://openalex.org/W1977453598","doi":"https://doi.org/10.1145/2556195.2556197","mag":"1977453598"},"language":"en","primary_location":{"id":"doi:10.1145/2556195.2556197","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2556195.2556197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM international conference on Web search and data mining","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/A5100641132","display_name":"Nan Zhang","orcid":"https://orcid.org/0000-0001-9620-5665"},"institutions":[{"id":"https://openalex.org/I193531525","display_name":"George Washington University","ror":"https://ror.org/00y4zzh67","country_code":"US","type":"education","lineage":["https://openalex.org/I193531525"]}],"countries":["US"],"is_corresponding":true,"raw_author_name":"Nan Zhang","raw_affiliation_strings":["The George Washington University, Washington, DC, USA","[The George Washington University, Washington DC, USA]"],"affiliations":[{"raw_affiliation_string":"The George Washington University, Washington, DC, USA","institution_ids":["https://openalex.org/I193531525"]},{"raw_affiliation_string":"[The George Washington University, Washington DC, USA]","institution_ids":["https://openalex.org/I193531525"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5002203026","display_name":"Gautam Das","orcid":"https://orcid.org/0000-0002-4627-9065"},"institutions":[{"id":"https://openalex.org/I189196454","display_name":"The University of Texas at Arlington","ror":"https://ror.org/019kgqr73","country_code":"US","type":"education","lineage":["https://openalex.org/I189196454"]}],"countries":["US"],"is_corresponding":false,"raw_author_name":"Gautam Das","raw_affiliation_strings":["The University of Texas at Arlington, Arlington, TX, USA"],"affiliations":[{"raw_affiliation_string":"The University of Texas at Arlington, Arlington, TX, USA","institution_ids":["https://openalex.org/I189196454"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5100641132"],"corresponding_institution_ids":["https://openalex.org/I193531525"],"apc_list":null,"apc_paid":null,"fwci":2.3667,"has_fulltext":false,"cited_by_count":3,"citation_normalized_percentile":{"value":0.90291218,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"675","last_page":"676"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9900000095367432,"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":0.9900000095367432,"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/T10317","display_name":"Advanced Database Systems and Queries","score":0.9865999817848206,"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"}},{"id":"https://openalex.org/T10215","display_name":"Semantic Web and Ontologies","score":0.9847999811172485,"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":0.7576804161071777},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.6733676791191101},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.4936262369155884},{"id":"https://openalex.org/keywords/web-mining","display_name":"Web mining","score":0.491115540266037},{"id":"https://openalex.org/keywords/deep-web","display_name":"Deep Web","score":0.4858098030090332},{"id":"https://openalex.org/keywords/keyword-search","display_name":"Keyword search","score":0.42157089710235596},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.38456472754478455},{"id":"https://openalex.org/keywords/the-internet","display_name":"The Internet","score":0.36945417523384094},{"id":"https://openalex.org/keywords/data-science","display_name":"Data science","score":0.33212360739707947}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7576804161071777},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.6733676791191101},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4936262369155884},{"id":"https://openalex.org/C197046077","wikidata":"https://www.wikidata.org/wiki/Q785337","display_name":"Web mining","level":3,"score":0.491115540266037},{"id":"https://openalex.org/C46721378","wikidata":"https://www.wikidata.org/wiki/Q221989","display_name":"Deep Web","level":3,"score":0.4858098030090332},{"id":"https://openalex.org/C2988412617","wikidata":"https://www.wikidata.org/wiki/Q7441656","display_name":"Keyword search","level":2,"score":0.42157089710235596},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.38456472754478455},{"id":"https://openalex.org/C110875604","wikidata":"https://www.wikidata.org/wiki/Q75","display_name":"The Internet","level":2,"score":0.36945417523384094},{"id":"https://openalex.org/C2522767166","wikidata":"https://www.wikidata.org/wiki/Q2374463","display_name":"Data science","level":1,"score":0.33212360739707947}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2556195.2556197","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2556195.2556197","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th ACM international conference on Web search and data mining","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W2037906003","https://openalex.org/W4378699829","https://openalex.org/W2953265498","https://openalex.org/W2533455610","https://openalex.org/W2083329789","https://openalex.org/W1892772476","https://openalex.org/W2376574812","https://openalex.org/W2074888472","https://openalex.org/W2160189941","https://openalex.org/W2182622516"],"abstract_inverted_index":{"With":[0],"the":[1],"proliferation":[2],"of":[3,27,36],"very":[4],"large":[5],"data":[6,34],"repositories":[7],"hidden":[8],"behind":[9],"web":[10,33],"interfaces,":[11],"e.g.,":[12],"keyword":[13],"search,":[14],"form-like":[15],"search":[16],"and":[17],"hierarchical/graph-based":[18],"browsing":[19],"interfaces":[20],"for":[21],"Amazon.com,":[22],"eBay.com,":[23],"etc.,":[24],"efficient":[25],"ways":[26],"searching,":[28],"exploring":[29],"and/or":[30],"mining":[31],"such":[32],"are":[35],"increasing":[37],"importance.":[38]},"counts_by_year":[{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
