{"id":"https://openalex.org/W1619012836","doi":"https://doi.org/10.1016/j.procs.2015.08.484","title":"Language Independent Tokenization vs. Stemming in Automated Detection of Health Websites\u2019 HONcode Conformity: An Evaluation","display_name":"Language Independent Tokenization vs. Stemming in Automated Detection of Health Websites\u2019 HONcode Conformity: An Evaluation","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W1619012836","doi":"https://doi.org/10.1016/j.procs.2015.08.484","mag":"1619012836"},"language":"en","primary_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2015.08.484","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"type":"article","type_crossref":"journal-article","indexed_in":["crossref"],"open_access":{"is_oa":true,"oa_status":"gold","oa_url":"https://doi.org/10.1016/j.procs.2015.08.484","any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5062298135","display_name":"C\u00e9lia Boyer","orcid":null},"institutions":[{"id":"https://openalex.org/I1282688002","display_name":"Health On The Net Foundation","ror":"https://ror.org/01j4wpj84","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I1282688002"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"C\u00e9lia Boyer","raw_affiliation_strings":["Health On The Net Foundation, Geneva, Switzerland."],"affiliations":[{"raw_affiliation_string":"Health On The Net Foundation, Geneva, Switzerland.","institution_ids":["https://openalex.org/I1282688002"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5063528547","display_name":"Ljiljana Dolamic","orcid":"https://orcid.org/0000-0002-0656-5315"},"institutions":[{"id":"https://openalex.org/I1282688002","display_name":"Health On The Net Foundation","ror":"https://ror.org/01j4wpj84","country_code":"CH","type":"nonprofit","lineage":["https://openalex.org/I1282688002"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Ljiljana Dolamic","raw_affiliation_strings":["Health On The Net Foundation, Geneva, Switzerland."],"affiliations":[{"raw_affiliation_string":"Health On The Net Foundation, Geneva, Switzerland.","institution_ids":["https://openalex.org/I1282688002"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5073534376","display_name":"Gilles Falquet","orcid":"https://orcid.org/0000-0002-1401-5110"},"institutions":[{"id":"https://openalex.org/I114457229","display_name":"University of Geneva","ror":"https://ror.org/01swzsf04","country_code":"CH","type":"education","lineage":["https://openalex.org/I114457229"]}],"countries":["CH"],"is_corresponding":false,"raw_author_name":"Gilles Falquet","raw_affiliation_strings":["University of Geneva Geneva, Switzerland"],"affiliations":[{"raw_affiliation_string":"University of Geneva Geneva, Switzerland","institution_ids":["https://openalex.org/I114457229"]}]}],"institution_assertions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":[],"apc_list":null,"apc_paid":null,"fwci":0.605,"has_fulltext":true,"fulltext_origin":"ngrams","cited_by_count":2,"citation_normalized_percentile":{"value":0.751751,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":73,"max":76},"biblio":{"volume":"64","issue":null,"first_page":"224","last_page":"231"},"is_retracted":false,"is_paratext":false,"primary_topic":{"id":"https://openalex.org/T10737","display_name":"Health Literacy and Information Accessibility","score":0.9945,"subfield":{"id":"https://openalex.org/subfields/3600","display_name":"General Health Professions"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},"topics":[{"id":"https://openalex.org/T10737","display_name":"Health Literacy and Information Accessibility","score":0.9945,"subfield":{"id":"https://openalex.org/subfields/3600","display_name":"General Health Professions"},"field":{"id":"https://openalex.org/fields/36","display_name":"Health Professions"},"domain":{"id":"https://openalex.org/domains/4","display_name":"Health Sciences"}},{"id":"https://openalex.org/T13629","display_name":"Text Readability and Simplification","score":0.988,"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/T12016","display_name":"Web Data Mining and Analysis","score":0.9844,"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/lexical-analysis","display_name":"Lexical analysis","score":0.8798628},{"id":"https://openalex.org/keywords/conformity","display_name":"Conformity","score":0.80269724}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.9169919},{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.8798628},{"id":"https://openalex.org/C142172996","wikidata":"https://www.wikidata.org/wiki/Q221284","display_name":"Conformity","level":2,"score":0.80269724},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.53056073},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.4527233},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4445549},{"id":"https://openalex.org/C199539241","wikidata":"https://www.wikidata.org/wiki/Q7748","display_name":"Law","level":1,"score":0.0},{"id":"https://openalex.org/C17744445","wikidata":"https://www.wikidata.org/wiki/Q36442","display_name":"Political science","level":0,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2015.08.484","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true}],"best_oa_location":{"is_oa":true,"landing_page_url":"https://doi.org/10.1016/j.procs.2015.08.484","pdf_url":null,"source":{"id":"https://openalex.org/S120348307","display_name":"Procedia Computer Science","issn_l":"1877-0509","issn":["1877-0509"],"is_oa":true,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310320990","host_organization_name":"Elsevier BV","host_organization_lineage":["https://openalex.org/P4310320990"],"host_organization_lineage_names":["Elsevier BV"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true},"sustainable_development_goals":[],"grants":[],"datasets":[],"versions":[],"referenced_works_count":18,"referenced_works":["https://openalex.org/W1482754067","https://openalex.org/W1521082019","https://openalex.org/W1532325895","https://openalex.org/W1660390307","https://openalex.org/W1722724786","https://openalex.org/W1872909666","https://openalex.org/W1956351727","https://openalex.org/W1998824124","https://openalex.org/W2017687165","https://openalex.org/W2029097226","https://openalex.org/W2061474427","https://openalex.org/W2069489145","https://openalex.org/W2077046902","https://openalex.org/W2080251601","https://openalex.org/W2093625697","https://openalex.org/W2099342305","https://openalex.org/W2118020653","https://openalex.org/W4213009331"],"related_works":["https://openalex.org/W4376107815","https://openalex.org/W4319309671","https://openalex.org/W4319309603","https://openalex.org/W4300598845","https://openalex.org/W3093361777","https://openalex.org/W2601638452","https://openalex.org/W2285263069","https://openalex.org/W2011517474","https://openalex.org/W1748623649","https://openalex.org/W1599985958"],"abstract_inverted_index":{"Abstract":[0],"Authors":[3],"evaluated":[4],"supervised":[5],"automatic":[6],"classification":[7,79,87],"algorithms":[8],"for":[9,64,151,164,169],"determination":[10],"of":[11,20,45,81,89],"health":[12],"related":[13],"web-page":[14],"compliance":[15,67,154],"with":[16],"individual":[17,65],"HONcode":[18,57,66,153],"criteria":[19,166],"conduct":[21],"(":[22],"www.hon.ch/Conduct.html":[23],").":[24],"The":[25,49,75,108],"current":[26],"study":[27,109,172],"used":[28],"varying":[29],"length":[30],"character":[31],"n-gram":[32,82,176],"vectors":[33],"to":[34,84,111,137,183],"represent":[35],"healthcare":[36],"web":[37,53],"page":[38,54],"documents":[39],"\u2013":[40],"not":[41],"the":[42,62,69,85,114,132,144,156],"traditional":[43],"approach":[44,117,146],"using":[46,96],"word":[47,185],"vectors.":[48],"training/testing":[50],"collection":[51],"comprised":[52],"fragments":[55],"that":[56,175],"experts":[58],"had":[59],"cited":[60],"as":[61,126],"basis":[63],"during":[68],"manual":[70],"certification":[71],"process":[72],"(described":[73],"below).":[74],"authors":[76,129],"compared":[77,131],"automated":[78,86],"performance":[80,88,158],"tokenization":[83,177],"document":[90,94,127,184],"words":[91,95],"and":[92,101,139,167],"Porter-stemmed":[93],"a":[97,179],"Naive":[98],"Bayes":[99],"classifier":[100],"DF":[102,134],"(document":[103],"frequency)":[104],"dimensionality":[105,141],"reduction":[106,135],"metrics.":[107],"attempted":[110],"determine":[112],"whether":[113],"automated,":[115],"language-independent":[116],"might":[118],"safely":[119],"replace":[120],"single":[121],"word-based":[122],"classification.":[123],"Using":[124],"5-grams":[125],"features,":[128],"also":[130],"baseline":[133],"function":[136],"Chi-square":[138,157],"Z-score":[140,145],"reductions.":[142],"While":[143],"statistically":[147],"significantly":[148],"improved":[149],"precision":[150],"some":[152,165],"components,":[155],"was":[159],"unreliable,":[160],"performing":[161],"very":[162],"well":[163],"poorly":[168],"others.":[170],"Overall":[171],"results":[173],"indicate":[174],"provide":[178],"potentially":[180],"viable":[181],"alternative":[182],"stemming.":[186]},"cited_by_api_url":"https://api.openalex.org/works?filter=cites:W1619012836","counts_by_year":[{"year":2023,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2025-01-16T08:06:47.429688","created_date":"2016-06-24"}