{"id":"https://openalex.org/W2032706581","doi":"https://doi.org/10.1145/2537734.2537746","title":"Malformed UTF-8 and spam","display_name":"Malformed UTF-8 and spam","publication_year":2013,"publication_date":"2013-12-05","ids":{"openalex":"https://openalex.org/W2032706581","doi":"https://doi.org/10.1145/2537734.2537746","mag":"2032706581"},"language":"en","primary_location":{"id":"doi:10.1145/2537734.2537746","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2537734.2537746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th 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":false,"raw_author_name":"Matt Crane","raw_affiliation_strings":["University of Otago, Dunedin, New Zealand","University of Otago, Dunedin, New Zealand "],"raw_orcid":null,"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":["https://openalex.org/I80281795"]}]},{"author_position":"middle","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 "],"raw_orcid":null,"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":["https://openalex.org/I80281795"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5108505151","display_name":"Richard O\u2019Keefe","orcid":null},"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":"Richard O'Keefe","raw_affiliation_strings":["University of Otago, Dunedin, New Zealand","University of Otago, Dunedin, New Zealand "],"raw_orcid":null,"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":["https://openalex.org/I80281795"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I80281795"],"apc_list":null,"apc_paid":null,"fwci":0.829,"has_fulltext":false,"cited_by_count":1,"citation_normalized_percentile":{"value":0.82622861,"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":"101","last_page":"104"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T12016","display_name":"Web Data Mining and Analysis","score":0.9965000152587891,"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":0.9965000152587891,"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":0.9957000017166138,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9934999942779541,"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":0.7905268669128418},{"id":"https://openalex.org/keywords/search-engine-indexing","display_name":"Search engine indexing","score":0.7769078612327576},{"id":"https://openalex.org/keywords/search-engine","display_name":"Search engine","score":0.7573972940444946},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6903201937675476},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.6080732345581055},{"id":"https://openalex.org/keywords/spamdexing","display_name":"Spamdexing","score":0.5903410315513611},{"id":"https://openalex.org/keywords/web-search-engine","display_name":"Web search engine","score":0.4633392095565796},{"id":"https://openalex.org/keywords/quality","display_name":"Quality (philosophy)","score":0.4350244700908661},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.39180538058280945},{"id":"https://openalex.org/keywords/data-mining","display_name":"Data mining","score":0.321233332157135},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.2687404751777649},{"id":"https://openalex.org/keywords/web-search-query","display_name":"Web search query","score":0.15857133269309998}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7905268669128418},{"id":"https://openalex.org/C75165309","wikidata":"https://www.wikidata.org/wiki/Q2258979","display_name":"Search engine indexing","level":2,"score":0.7769078612327576},{"id":"https://openalex.org/C97854310","wikidata":"https://www.wikidata.org/wiki/Q19541","display_name":"Search engine","level":2,"score":0.7573972940444946},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6903201937675476},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.6080732345581055},{"id":"https://openalex.org/C13565553","wikidata":"https://www.wikidata.org/wiki/Q804206","display_name":"Spamdexing","level":5,"score":0.5903410315513611},{"id":"https://openalex.org/C521815418","wikidata":"https://www.wikidata.org/wiki/Q4182287","display_name":"Web search engine","level":4,"score":0.4633392095565796},{"id":"https://openalex.org/C2779530757","wikidata":"https://www.wikidata.org/wiki/Q1207505","display_name":"Quality (philosophy)","level":2,"score":0.4350244700908661},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.39180538058280945},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.321233332157135},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.2687404751777649},{"id":"https://openalex.org/C164120249","wikidata":"https://www.wikidata.org/wiki/Q995982","display_name":"Web search query","level":3,"score":0.15857133269309998},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C111472728","wikidata":"https://www.wikidata.org/wiki/Q9471","display_name":"Epistemology","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1145/2537734.2537746","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2537734.2537746","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 18th Australasian Document Computing Symposium","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.590.267","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.590.267","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"http://www.cs.otago.ac.nz/homepages/andrew/papers/2013-8.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":7,"referenced_works":["https://openalex.org/W1685426458","https://openalex.org/W1797354850","https://openalex.org/W2082868123","https://openalex.org/W2188152546","https://openalex.org/W2465088004","https://openalex.org/W6638304679","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":{"In":[0,32],"this":[1,33],"paper":[2,34],"we":[3,35],"discuss":[4],"some":[5],"of":[6,66],"the":[7,27,37,64,67],"document":[8],"encoding":[9,38],"errors":[10],"that":[11],"were":[12],"found":[13],"when":[14],"scaling":[15],"our":[16,54],"indexer":[17,55],"and":[18,47,56,59],"search":[19,57],"engine":[20,58],"up":[21],"to":[22,63],"large":[23],"collections":[24],"crawled":[25],"from":[26],"web,":[28],"such":[29],"as":[30],"ClueWeb09.":[31],"describe":[36],"errors,":[39],"what":[40],"effect":[41],"they":[42,50,61],"could":[43],"have":[44],"on":[45],"indexing":[46],"searching,":[48],"how":[49,60],"are":[51],"processed":[52],"within":[53],"relate":[62],"quality":[65],"page":[68],"measured":[69],"by":[70],"another":[71],"method.":[72]},"counts_by_year":[{"year":2016,"cited_by_count":1}],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
