{"id":"https://openalex.org/W2070158055","doi":"https://doi.org/10.1145/2806416.2806613","title":"The Influence of Pre-processing on the Estimation of Readability of Web Documents","display_name":"The Influence of Pre-processing on the Estimation of Readability of Web Documents","publication_year":2015,"publication_date":"2015-10-17","ids":{"openalex":"https://openalex.org/W2070158055","doi":"https://doi.org/10.1145/2806416.2806613","mag":"2070158055"},"language":"en","primary_location":{"id":"doi:10.1145/2806416.2806613","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2806416.2806613","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM International on Conference on Information and Knowledge Management","raw_type":"proceedings-article"},"type":"article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://eprints.qut.edu.au/91421/23/cikm2015_readability.pdf","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5022129033","display_name":"Jo\u00e3o Palotti","orcid":"https://orcid.org/0000-0002-7099-9716"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":true,"raw_author_name":"Jo\u00e3o Rafael de Moura Palotti","raw_affiliation_strings":["Vienna University of Technology, Vienna, Austria","Vienna University of technology, Vienna, Austria"],"affiliations":[{"raw_affiliation_string":"Vienna University of Technology, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]},{"raw_affiliation_string":"Vienna University of technology, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5076031002","display_name":"Guido Zuccon","orcid":"https://orcid.org/0000-0003-0271-5563"},"institutions":[{"id":"https://openalex.org/I160993911","display_name":"Queensland University of Technology","ror":"https://ror.org/03pnv4752","country_code":"AU","type":"education","lineage":["https://openalex.org/I160993911"]}],"countries":["AU"],"is_corresponding":false,"raw_author_name":"Guido Zuccon","raw_affiliation_strings":["Queensland University of Technology, Brisbane, Australia"],"affiliations":[{"raw_affiliation_string":"Queensland University of Technology, Brisbane, Australia","institution_ids":["https://openalex.org/I160993911"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5020665735","display_name":"Allan Hanbury","orcid":"https://orcid.org/0000-0002-7149-5843"},"institutions":[{"id":"https://openalex.org/I145847075","display_name":"TU Wien","ror":"https://ror.org/04d836q62","country_code":"AT","type":"education","lineage":["https://openalex.org/I145847075"]}],"countries":["AT"],"is_corresponding":false,"raw_author_name":"Allan Hanbury","raw_affiliation_strings":["Vienna University of Technology, Vienna, Austria","Vienna University of technology, Vienna, Austria"],"affiliations":[{"raw_affiliation_string":"Vienna University of Technology, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]},{"raw_affiliation_string":"Vienna University of technology, Vienna, Austria","institution_ids":["https://openalex.org/I145847075"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5022129033"],"corresponding_institution_ids":["https://openalex.org/I145847075"],"apc_list":null,"apc_paid":null,"fwci":5.7865,"has_fulltext":true,"cited_by_count":22,"citation_normalized_percentile":{"value":0.96130285,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":89,"max":99},"biblio":{"volume":null,"issue":null,"first_page":"1763","last_page":"1766"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.9998999834060669,"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"}},"topics":[{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.9998999834060669,"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/T10260","display_name":"Software Engineering Research","score":0.9225999712944031,"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/T10028","display_name":"Topic Modeling","score":0.9043999910354614,"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/readability","display_name":"Readability","score":0.9884527325630188},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.8225922584533691},{"id":"https://openalex.org/keywords/personalization","display_name":"Personalization","score":0.8040779829025269},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.6531480550765991},{"id":"https://openalex.org/keywords/reading","display_name":"Reading (process)","score":0.5724160671234131},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.5705615282058716},{"id":"https://openalex.org/keywords/reading-level","display_name":"Reading level","score":0.5447895526885986},{"id":"https://openalex.org/keywords/web-page","display_name":"Web page","score":0.4899977743625641},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.33117425441741943},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.10190224647521973}],"concepts":[{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.9884527325630188},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8225922584533691},{"id":"https://openalex.org/C183003079","wikidata":"https://www.wikidata.org/wiki/Q1000371","display_name":"Personalization","level":2,"score":0.8040779829025269},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.6531480550765991},{"id":"https://openalex.org/C554936623","wikidata":"https://www.wikidata.org/wiki/Q199657","display_name":"Reading (process)","level":2,"score":0.5724160671234131},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.5705615282058716},{"id":"https://openalex.org/C3018944925","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Reading level","level":3,"score":0.5447895526885986},{"id":"https://openalex.org/C21959979","wikidata":"https://www.wikidata.org/wiki/Q36774","display_name":"Web page","level":2,"score":0.4899977743625641},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.33117425441741943},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.10190224647521973},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.0},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0}],"mesh":[],"locations_count":3,"locations":[{"id":"doi:10.1145/2806416.2806613","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2806416.2806613","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 24th ACM International on Conference on Information and Knowledge Management","raw_type":"proceedings-article"},{"id":"pmh:oai:eprints.qut.edu.au:91421","is_oa":true,"landing_page_url":"http://dl.acm.org/citation.cfm?id=2806613","pdf_url":"https://eprints.qut.edu.au/91421/23/cikm2015_readability.pdf","source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 24th ACM International on Conference on Information and Knowledge Management","raw_type":"Chapter in Book, Report or Conference volume"},{"id":"pmh:oai:espace.library.uq.edu.au:UQ:83f4cbe","is_oa":false,"landing_page_url":null,"pdf_url":null,"source":{"id":"https://openalex.org/S4306402388","display_name":"Queensland's institutional digital repository (The University of Queensland)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I165143802","host_organization_name":"The University of Queensland","host_organization_lineage":["https://openalex.org/I165143802"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"Conference Paper"}],"best_oa_location":{"id":"pmh:oai:eprints.qut.edu.au:91421","is_oa":true,"landing_page_url":"http://dl.acm.org/citation.cfm?id=2806613","pdf_url":"https://eprints.qut.edu.au/91421/23/cikm2015_readability.pdf","source":{"id":"https://openalex.org/S4306402607","display_name":"QUT ePrints (Queensland University of Technology)","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I160993911","host_organization_name":"Queensland University of Technology","host_organization_lineage":["https://openalex.org/I160993911"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"Proceedings of the 24th ACM International on Conference on Information and Knowledge Management","raw_type":"Chapter in Book, Report or Conference volume"},"sustainable_development_goals":[{"display_name":"Quality Education","score":0.8899999856948853,"id":"https://metadata.un.org/sdg/4"}],"awards":[{"id":"https://openalex.org/G1176565477","display_name":null,"funder_award_id":"H2020-ICT-2014-1","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G1535130713","display_name":null,"funder_award_id":"H2020-ICT","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G177484282","display_name":null,"funder_award_id":"FP7/2007-2013","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G2153309609","display_name":null,"funder_award_id":"ICT-2014-1","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G2270015793","display_name":null,"funder_award_id":"644753","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"},{"id":"https://openalex.org/G2445369504","display_name":null,"funder_award_id":"H2020-ICT-2014","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G2447788411","display_name":null,"funder_award_id":"unknown","funder_id":"https://openalex.org/F4320321181","funder_display_name":"Austrian Science Fund"},{"id":"https://openalex.org/G3050553092","display_name":null,"funder_award_id":"644753","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3605322341","display_name":null,"funder_award_id":"257528","funder_id":"https://openalex.org/F4320334960","funder_display_name":"Seventh Framework Programme"},{"id":"https://openalex.org/G3829048491","display_name":null,"funder_award_id":"FP7/2007-2013","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G3981126665","display_name":null,"funder_award_id":"Seventh Framework Programme","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G4597347822","display_name":null,"funder_award_id":"644753","funder_id":"https://openalex.org/F4320332999","funder_display_name":"Horizon 2020 Framework Programme"},{"id":"https://openalex.org/G4937468798","display_name":null,"funder_award_id":"H2020","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5593277320","display_name":null,"funder_award_id":"2007-2013","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G5702163051","display_name":null,"funder_award_id":"FP7/2007","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7650496259","display_name":null,"funder_award_id":"257528","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G7847148445","display_name":null,"funder_award_id":"H2020-ICT-2014-1","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"},{"id":"https://openalex.org/G8318064016","display_name":null,"funder_award_id":"Horizon","funder_id":"https://openalex.org/F4320320300","funder_display_name":"European Commission"}],"funders":[{"id":"https://openalex.org/F4320320300","display_name":"European Commission","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320321181","display_name":"Austrian Science Fund","ror":"https://ror.org/013tf3c58"},{"id":"https://openalex.org/F4320332999","display_name":"Horizon 2020 Framework Programme","ror":"https://ror.org/00k4n6c32"},{"id":"https://openalex.org/F4320334960","display_name":"Seventh Framework Programme","ror":"https://ror.org/00k4n6c32"}],"has_content":{"pdf":true,"grobid_xml":false},"content_urls":{"pdf":"https://content.openalex.org/works/W2070158055.pdf"},"referenced_works_count":23,"referenced_works":["https://openalex.org/W15548","https://openalex.org/W133394232","https://openalex.org/W147182747","https://openalex.org/W175030052","https://openalex.org/W1481128830","https://openalex.org/W1602368597","https://openalex.org/W1968135851","https://openalex.org/W1969992055","https://openalex.org/W1974595223","https://openalex.org/W1991336188","https://openalex.org/W2048587526","https://openalex.org/W2106695994","https://openalex.org/W2112890532","https://openalex.org/W2120101509","https://openalex.org/W2125682643","https://openalex.org/W2145871697","https://openalex.org/W2578576916","https://openalex.org/W2910001684","https://openalex.org/W6600000387","https://openalex.org/W6605422000","https://openalex.org/W6607045664","https://openalex.org/W6628960004","https://openalex.org/W6636400605"],"related_works":["https://openalex.org/W2411333709","https://openalex.org/W2066223161","https://openalex.org/W4386022860","https://openalex.org/W1964305103","https://openalex.org/W2064134349","https://openalex.org/W2966024918","https://openalex.org/W4322768588","https://openalex.org/W2122066041","https://openalex.org/W2335619536","https://openalex.org/W279706530"],"abstract_inverted_index":{"This":[0,75],"paper":[1],"investigates":[2],"the":[3,11,14,51],"effect":[4],"that":[5,59,88],"text":[6,39,64,97],"pre-processing":[7],"approaches":[8],"have":[9],"on":[10,43],"estimation":[12],"of":[13,16,27,47,53,73],"readability":[15,40,98],"web":[17,28,66],"pages.":[18],"Readability":[19],"has":[20,76],"been":[21],"highlighted":[22],"as":[23,50],"an":[24,77],"important":[25,78],"aspect":[26],"search":[29,81,84],"result":[30,85],"personalisation":[31,86],"in":[32],"previous":[33],"work.":[34],"The":[35],"most":[36],"widely":[37],"used":[38],"measures":[41],"rely":[42],"surface":[44],"level":[45],"characteristics":[46],"text,":[48],"such":[49],"length":[52],"words":[54],"and":[55],"sentences.":[56],"We":[57],"demonstrate":[58],"different":[60,71],"tools":[61],"for":[62,80],"extracting":[63],"from":[65],"pages":[67],"lead":[68],"to":[69],"very":[70],"estimations":[72,99],"readability.":[74],"implication":[79],"engines":[82],"because":[83],"strategies":[87],"consider":[89],"users":[90],"reading":[91],"ability":[92],"may":[93],"fail":[94],"if":[95],"incorrect":[96],"are":[100],"computed.":[101]},"counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2021,"cited_by_count":1},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":6},{"year":2018,"cited_by_count":6},{"year":2017,"cited_by_count":4},{"year":2016,"cited_by_count":2},{"year":2015,"cited_by_count":1}],"updated_date":"2026-04-13T07:58:08.660418","created_date":"2025-10-10T00:00:00"}
