{"id":"https://openalex.org/W2394613339","doi":"https://doi.org/10.3233/978-1-61499-564-7-1064","title":"Automated Detection of Health Websites' HONcode Conformity: Can N-gram Tokenization Replace Stemming?","display_name":"Automated Detection of Health Websites' HONcode Conformity: Can N-gram Tokenization Replace Stemming?","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2394613339","doi":"https://doi.org/10.3233/978-1-61499-564-7-1064","mag":"2394613339","pmid":"https://pubmed.ncbi.nlm.nih.gov/26262363"},"language":"en","primary_location":{"id":"doi:10.3233/978-1-61499-564-7-1064","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-564-7-1064","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},"type":"article","indexed_in":["crossref","pubmed"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"Boyer Célia","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":true,"raw_author_name":"Boyer Célia","raw_affiliation_strings":["Health on The Net Foundation, Geneva, Switzerland"],"raw_orcid":null,"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":"Dolamic Ljiljana","raw_affiliation_strings":["Health on The Net Foundation, Geneva, Switzerland"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Health on The Net Foundation, Geneva, Switzerland","institution_ids":["https://openalex.org/I1282688002"]}]},{"author_position":"last","author":{"id":null,"display_name":"Grabar Natalia","orcid":null},"institutions":[{"id":"https://openalex.org/I2279609970","display_name":"Universit\u00e9 de Lille","ror":"https://ror.org/02kzqn938","country_code":"FR","type":"education","lineage":["https://openalex.org/I2279609970"]}],"countries":["FR"],"is_corresponding":false,"raw_author_name":"Grabar Natalia","raw_affiliation_strings":["Universit\u00e9 Lille 3, France"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Universit\u00e9 Lille 3, France","institution_ids":["https://openalex.org/I2279609970"]}]}],"institutions":[],"countries_distinct_count":2,"institutions_distinct_count":3,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I1282688002"],"apc_list":null,"apc_paid":null,"fwci":2.5635,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.88705466,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":{"min":89,"max":95},"biblio":{"volume":"216","issue":null,"first_page":"1064","last_page":"1064"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10737","display_name":"Health Literacy and Information Accessibility","score":0.9138000011444092,"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":0.9138000011444092,"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"}}],"keywords":[{"id":"https://openalex.org/keywords/lexical-analysis","display_name":"Lexical analysis","score":0.8175173997879028},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7527270317077637},{"id":"https://openalex.org/keywords/naive-bayes-classifier","display_name":"Naive Bayes classifier","score":0.6808589100837708},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6155774593353271},{"id":"https://openalex.org/keywords/n-gram","display_name":"n-gram","score":0.6039861440658569},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5392239689826965},{"id":"https://openalex.org/keywords/dimensionality-reduction","display_name":"Dimensionality reduction","score":0.46845006942749023},{"id":"https://openalex.org/keywords/document-classification","display_name":"Document classification","score":0.45312264561653137},{"id":"https://openalex.org/keywords/stop-words","display_name":"Stop words","score":0.43783313035964966},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.39207106828689575},{"id":"https://openalex.org/keywords/support-vector-machine","display_name":"Support vector machine","score":0.35609060525894165},{"id":"https://openalex.org/keywords/preprocessor","display_name":"Preprocessor","score":0.15919694304466248},{"id":"https://openalex.org/keywords/language-model","display_name":"Language model","score":0.10474973917007446}],"concepts":[{"id":"https://openalex.org/C176982825","wikidata":"https://www.wikidata.org/wiki/Q835922","display_name":"Lexical analysis","level":2,"score":0.8175173997879028},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7527270317077637},{"id":"https://openalex.org/C52001869","wikidata":"https://www.wikidata.org/wiki/Q812530","display_name":"Naive Bayes classifier","level":3,"score":0.6808589100837708},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6155774593353271},{"id":"https://openalex.org/C117884012","wikidata":"https://www.wikidata.org/wiki/Q94489","display_name":"n-gram","level":3,"score":0.6039861440658569},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5392239689826965},{"id":"https://openalex.org/C70518039","wikidata":"https://www.wikidata.org/wiki/Q16000077","display_name":"Dimensionality reduction","level":2,"score":0.46845006942749023},{"id":"https://openalex.org/C2780479914","wikidata":"https://www.wikidata.org/wiki/Q302088","display_name":"Document classification","level":2,"score":0.45312264561653137},{"id":"https://openalex.org/C188338183","wikidata":"https://www.wikidata.org/wiki/Q80735","display_name":"Stop words","level":3,"score":0.43783313035964966},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.39207106828689575},{"id":"https://openalex.org/C12267149","wikidata":"https://www.wikidata.org/wiki/Q282453","display_name":"Support vector machine","level":2,"score":0.35609060525894165},{"id":"https://openalex.org/C34736171","wikidata":"https://www.wikidata.org/wiki/Q918333","display_name":"Preprocessor","level":2,"score":0.15919694304466248},{"id":"https://openalex.org/C137293760","wikidata":"https://www.wikidata.org/wiki/Q3621696","display_name":"Language model","level":2,"score":0.10474973917007446}],"mesh":[{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D000069553","descriptor_name":"Supervised Machine Learning","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D005240","descriptor_name":"Feasibility Studies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005240","descriptor_name":"Feasibility Studies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D005240","descriptor_name":"Feasibility Studies","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D009323","descriptor_name":"Natural Language Processing","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D010363","descriptor_name":"Pattern Recognition, Automated","qualifier_ui":"Q000379","qualifier_name":"methods","is_major_topic":false},{"descriptor_ui":"D017410","descriptor_name":"Practice Guidelines as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017410","descriptor_name":"Practice Guidelines as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D017410","descriptor_name":"Practice Guidelines as Topic","qualifier_ui":null,"qualifier_name":null,"is_major_topic":true},{"descriptor_ui":"D019983","descriptor_name":"Guideline Adherence","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D019983","descriptor_name":"Guideline Adherence","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D019983","descriptor_name":"Guideline Adherence","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D019983","descriptor_name":"Guideline Adherence","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D019983","descriptor_name":"Guideline Adherence","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D019983","descriptor_name":"Guideline Adherence","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D020407","descriptor_name":"Internet","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D038622","descriptor_name":"Internationality","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D038622","descriptor_name":"Internationality","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D038622","descriptor_name":"Internationality","qualifier_ui":null,"qualifier_name":null,"is_major_topic":false},{"descriptor_ui":"D054626","descriptor_name":"Consumer Health Information","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D054626","descriptor_name":"Consumer Health Information","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D054626","descriptor_name":"Consumer Health Information","qualifier_ui":"Q000592","qualifier_name":"standards","is_major_topic":false},{"descriptor_ui":"D054626","descriptor_name":"Consumer Health Information","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D054626","descriptor_name":"Consumer Health Information","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false},{"descriptor_ui":"D054626","descriptor_name":"Consumer Health Information","qualifier_ui":"Q000706","qualifier_name":"statistics & numerical data","is_major_topic":false}],"locations_count":2,"locations":[{"id":"doi:10.3233/978-1-61499-564-7-1064","is_oa":false,"landing_page_url":"https://doi.org/10.3233/978-1-61499-564-7-1064","pdf_url":null,"source":{"id":"https://openalex.org/S4210179765","display_name":"Studies in health technology and informatics","issn_l":"0926-9630","issn":["0926-9630","1879-8365"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310318577","host_organization_name":"IOS Press","host_organization_lineage":["https://openalex.org/P4310318577"],"host_organization_lineage_names":["IOS Press"],"type":"book series"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in Health Technology and Informatics","raw_type":"book-chapter"},{"id":"pmid:26262363","is_oa":false,"landing_page_url":"https://pubmed.ncbi.nlm.nih.gov/26262363","pdf_url":null,"source":{"id":"https://openalex.org/S4306525036","display_name":"PubMed","issn_l":null,"issn":null,"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I1299303238","host_organization_name":"National Institutes of Health","host_organization_lineage":["https://openalex.org/I1299303238"],"host_organization_lineage_names":[],"type":"repository"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Studies in health technology and informatics","raw_type":null}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":["https://openalex.org/W3110233274","https://openalex.org/W914025585","https://openalex.org/W1824099197","https://openalex.org/W4386005680","https://openalex.org/W3157673128","https://openalex.org/W4386023432","https://openalex.org/W4405333889","https://openalex.org/W4389581355","https://openalex.org/W2900572605","https://openalex.org/W2394613339"],"abstract_inverted_index":{"Authors":[0],"evaluated":[1],"supervised":[2],"automatic":[3],"classification":[4,51,59],"algorithms":[5],"for":[6],"determination":[7],"of":[8,17,53,61],"health":[9],"related":[10],"web-page":[11],"compliance":[12],"with":[13],"individual":[14],"HONcode":[15,40],"criteria":[16],"conduct":[18],"using":[19,68],"varying":[20],"length":[21],"character":[22],"n-gram":[23,54,119],"vectors":[24],"to":[25,56,83,108,126],"represent":[26],"healthcare":[27],"web":[28,35],"page":[29,36],"documents.":[30],"The":[31,47,80],"training/testing":[32],"collection":[33],"comprised":[34],"fragments":[37],"extracted":[38],"by":[39],"experts":[41],"during":[42],"the":[43,57,86,103],"manual":[44],"certification":[45],"process.":[46],"authors":[48,100],"compared":[49,102],"automated":[50,58],"performance":[52,60],"tokenization":[55,120],"document":[62,66,98,127],"words":[63,67],"and":[64,73,110],"Porter-stemmed":[65],"a":[69,122],"Naive":[70],"Bayes":[71],"classifier":[72],"DF":[74,105],"(document":[75],"frequency)":[76],"dimensionality":[77,112],"reduction":[78,106],"metrics.":[79],"study":[81,115],"attempted":[82],"determine":[84],"whether":[85],"automated,":[87],"language-independent":[88],"approach":[89],"might":[90],"safely":[91],"replace":[92],"word-based":[93],"classification.":[94],"Using":[95],"5-grams":[96],"as":[97],"features,":[99],"also":[101],"baseline":[104],"function":[107],"Chi-square":[109],"Z-score":[111],"reductions.":[113],"Overall":[114],"results":[116],"indicate":[117],"that":[118],"provided":[121],"potentially":[123],"viable":[124],"alternative":[125],"word":[128],"stemming.":[129]},"counts_by_year":[{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":1},{"year":2018,"cited_by_count":1}],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}