{"id":"https://openalex.org/W2082868123","doi":"https://doi.org/10.1145/2407085.2407086","title":"Effects of spam removal on search engine efficiency and effectiveness","display_name":"Effects of spam removal on search engine efficiency and effectiveness","publication_year":2012,"publication_date":"2012-12-05","ids":{"openalex":"https://openalex.org/W2082868123","doi":"https://doi.org/10.1145/2407085.2407086","mag":"2082868123"},"language":"en","primary_location":{"id":"doi:10.1145/2407085.2407086","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2407085.2407086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventeenth Australasian Document Computing Symposium","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/A5008800181","display_name":"Matt Crane","orcid":"https://orcid.org/0000-0002-7677-3398"},"institutions":[{"id":"https://openalex.org/I80281795","display_name":"University of Otago","ror":"https://ror.org/01jmxt844","country_code":"NZ","type":"education","lineage":["https://openalex.org/I80281795"]}],"countries":["NZ"],"is_corresponding":true,"raw_author_name":"Matt Crane","raw_affiliation_strings":["University of Otago, Dunedin, New Zealand","University of Otago, Dunedin, New Zealand "],"affiliations":[{"raw_affiliation_string":"University of Otago, Dunedin, New Zealand","institution_ids":["https://openalex.org/I80281795"]},{"raw_affiliation_string":"University of Otago, Dunedin, New Zealand ","institution_ids":[]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5050903724","display_name":"Andrew Trotman","orcid":"https://orcid.org/0000-0003-1253-7123"},"institutions":[{"id":"https://openalex.org/I80281795","display_name":"University of Otago","ror":"https://ror.org/01jmxt844","country_code":"NZ","type":"education","lineage":["https://openalex.org/I80281795"]}],"countries":["NZ"],"is_corresponding":false,"raw_author_name":"Andrew Trotman","raw_affiliation_strings":["University of Otago, Dunedin, New Zealand","University of Otago, Dunedin, New Zealand "],"affiliations":[{"raw_affiliation_string":"University of Otago, Dunedin, New Zealand","institution_ids":["https://openalex.org/I80281795"]},{"raw_affiliation_string":"University of Otago, Dunedin, New Zealand ","institution_ids":[]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5008800181"],"corresponding_institution_ids":["https://openalex.org/I80281795"],"apc_list":null,"apc_paid":null,"fwci":3.5527,"has_fulltext":false,"cited_by_count":8,"citation_normalized_percentile":{"value":0.93544111,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":96},"biblio":{"volume":null,"issue":null,"first_page":"1","last_page":"8"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11644","display_name":"Spam and Phishing Detection","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/T11644","display_name":"Spam and Phishing Detection","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/T12016","display_name":"Web Data Mining and Analysis","score":0.9991999864578247,"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/T10286","display_name":"Information Retrieval and Search Behavior","score":0.9990000128746033,"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/search-engine-indexing","display_name":"Search engine indexing","score":0.9188525676727295},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.8112239837646484},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.709377646446228},{"id":"https://openalex.org/keywords/process","display_name":"Process (computing)","score":0.618389368057251},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.5743222832679749},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5020554065704346},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.4987151622772217},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.3691602945327759},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.3563125729560852},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.31788039207458496},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.2715751528739929}],"concepts":[{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.9188525676727295},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.8112239837646484},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.709377646446228},{"id":"https://openalex.org/C98045186","wikidata":"https://www.wikidata.org/wiki/Q205663","display_name":"Process (computing)","level":2,"score":0.618389368057251},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.5743222832679749},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5020554065704346},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.4987151622772217},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3691602945327759},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.3563125729560852},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.31788039207458496},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.2715751528739929},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2407085.2407086","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2407085.2407086","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the Seventeenth Australasian Document Computing Symposium","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":21,"referenced_works":["https://openalex.org/W7157229","https://openalex.org/W94637519","https://openalex.org/W224439989","https://openalex.org/W1532423646","https://openalex.org/W1685426458","https://openalex.org/W1878118535","https://openalex.org/W1972594981","https://openalex.org/W2096913158","https://openalex.org/W2113640060","https://openalex.org/W2124564482","https://openalex.org/W2132314908","https://openalex.org/W2187262079","https://openalex.org/W2187652355","https://openalex.org/W2188152546","https://openalex.org/W2294145134","https://openalex.org/W2406556078","https://openalex.org/W3013019162","https://openalex.org/W6603899496","https://openalex.org/W6631770111","https://openalex.org/W6674723495","https://openalex.org/W6687557373"],"related_works":["https://openalex.org/W4282568653","https://openalex.org/W2419328283","https://openalex.org/W2082868123","https://openalex.org/W2296228743","https://openalex.org/W3139249295","https://openalex.org/W2124561181","https://openalex.org/W2354327071","https://openalex.org/W1968898749","https://openalex.org/W2147086435","https://openalex.org/W2119380317"],"abstract_inverted_index":{"Spam":[0],"has":[1,53],"long":[2],"been":[3],"identified":[4,50],"as":[5,51],"a":[6],"problem":[7],"that":[8,27,47,80],"web":[9],"search":[10,67,105],"engines":[11],"are":[12,20,76,88,101],"required":[13,57],"to":[14,34,58,90,103],"deal":[15],"with.":[16],"Large":[17],"collection":[18],"sizes":[19],"also":[21,63],"an":[22],"increasing":[23],"issue":[24],"for":[25,107],"institutions":[26],"do":[28],"not":[29],"have":[30],"the":[31,45,55,65,92,97],"necessary":[32],"resources":[33,56],"process":[35,59],"them":[36],"in":[37],"their":[38],"entirety.":[39],"In":[40],"this":[41],"paper":[42],"we":[43,87],"investigate":[44,64],"effect":[46],"withholding":[48],"documents":[49],"spam":[52,75,83],"on":[54],"large":[60],"collections.":[61],"We":[62,78],"resulting":[66],"effectiveness":[68],"and":[69,100],"efficiency":[70],"when":[71],"different":[72],"amounts":[73],"of":[74],"withheld.":[77],"find":[79],"by":[81],"removing":[82],"at":[84],"indexing":[85,98],"time":[86],"able":[89,102],"decrease":[91],"index":[93],"size":[94],"without":[95],"affecting":[96],"throughput,":[99],"improve":[104],"precision":[106],"some":[108],"thresholds.":[109]},"counts_by_year":[{"year":2018,"cited_by_count":2},{"year":2016,"cited_by_count":1},{"year":2015,"cited_by_count":2},{"year":2013,"cited_by_count":2},{"year":2012,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}