{"id":"https://openalex.org/W1888132250","doi":"https://doi.org/10.1109/cec.2004.1330955","title":"Evolving document features for Web document clustering: a feasibility study","display_name":"Evolving document features for Web document clustering: a feasibility study","publication_year":2004,"publication_date":"2004-09-28","ids":{"openalex":"https://openalex.org/W1888132250","doi":"https://doi.org/10.1109/cec.2004.1330955","mag":"1888132250"},"language":"en","primary_location":{"id":"doi:10.1109/cec.2004.1330955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec.2004.1330955","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753)","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/A5004851702","display_name":"Mark P. Sinka","orcid":null},"institutions":[{"id":"https://openalex.org/I71052956","display_name":"University of Reading","ror":"https://ror.org/05v62cm79","country_code":"GB","type":"education","lineage":["https://openalex.org/I71052956"]}],"countries":["GB"],"is_corresponding":true,"raw_author_name":"M.P. Sinka","raw_affiliation_strings":["Dept. of Computer Science Whiteknights, University of Reading, Reading, UK","Dept. of Comput. Sci., Reading Univ., , UK"],"affiliations":[{"raw_affiliation_string":"Dept. of Computer Science Whiteknights, University of Reading, Reading, UK","institution_ids":["https://openalex.org/I71052956"]},{"raw_affiliation_string":"Dept. of Comput. Sci., Reading Univ., , UK","institution_ids":["https://openalex.org/I71052956"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5061783148","display_name":"David Corne","orcid":"https://orcid.org/0000-0003-4369-3807"},"institutions":[],"countries":[],"is_corresponding":false,"raw_author_name":"D.W. Corne","raw_affiliation_strings":[],"affiliations":[]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":["https://openalex.org/A5004851702"],"corresponding_institution_ids":["https://openalex.org/I71052956"],"apc_list":null,"apc_paid":null,"fwci":2.3127,"has_fulltext":false,"cited_by_count":5,"citation_normalized_percentile":{"value":0.89150562,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"891","last_page":"897"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9950000047683716,"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/T13083","display_name":"Advanced Text Analysis Techniques","score":0.9950000047683716,"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":0.9948999881744385,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9914000034332275,"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":0.7567307949066162},{"id":"https://openalex.org/keywords/cluster-analysis","display_name":"Cluster analysis","score":0.6268550157546997},{"id":"https://openalex.org/keywords/salient","display_name":"Salient","score":0.6120128035545349},{"id":"https://openalex.org/keywords/document-clustering","display_name":"Document clustering","score":0.576575756072998},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.5487332344055176},{"id":"https://openalex.org/keywords/encode","display_name":"ENCODE","score":0.5370044112205505},{"id":"https://openalex.org/keywords/encoding","display_name":"Encoding (memory)","score":0.5184666514396667},{"id":"https://openalex.org/keywords/key","display_name":"Key (lock)","score":0.4768194556236267},{"id":"https://openalex.org/keywords/variety","display_name":"Variety (cybernetics)","score":0.4752359390258789},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4483000934123993},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.4211319088935852},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.3708537817001343},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.11619514226913452}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7567307949066162},{"id":"https://openalex.org/C73555534","wikidata":"https://www.wikidata.org/wiki/Q622825","display_name":"Cluster analysis","level":2,"score":0.6268550157546997},{"id":"https://openalex.org/C2780719617","wikidata":"https://www.wikidata.org/wiki/Q1030752","display_name":"Salient","level":2,"score":0.6120128035545349},{"id":"https://openalex.org/C177937566","wikidata":"https://www.wikidata.org/wiki/Q4223102","display_name":"Document clustering","level":3,"score":0.576575756072998},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.5487332344055176},{"id":"https://openalex.org/C66746571","wikidata":"https://www.wikidata.org/wiki/Q1134833","display_name":"ENCODE","level":3,"score":0.5370044112205505},{"id":"https://openalex.org/C125411270","wikidata":"https://www.wikidata.org/wiki/Q18653","display_name":"Encoding (memory)","level":2,"score":0.5184666514396667},{"id":"https://openalex.org/C26517878","wikidata":"https://www.wikidata.org/wiki/Q228039","display_name":"Key (lock)","level":2,"score":0.4768194556236267},{"id":"https://openalex.org/C136197465","wikidata":"https://www.wikidata.org/wiki/Q1729295","display_name":"Variety (cybernetics)","level":2,"score":0.4752359390258789},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4483000934123993},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.4211319088935852},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.3708537817001343},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.11619514226913452},{"id":"https://openalex.org/C104317684","wikidata":"https://www.wikidata.org/wiki/Q7187","display_name":"Gene","level":2,"score":0.0},{"id":"https://openalex.org/C55493867","wikidata":"https://www.wikidata.org/wiki/Q7094","display_name":"Biochemistry","level":1,"score":0.0},{"id":"https://openalex.org/C38652104","wikidata":"https://www.wikidata.org/wiki/Q3510521","display_name":"Computer security","level":1,"score":0.0},{"id":"https://openalex.org/C185592680","wikidata":"https://www.wikidata.org/wiki/Q2329","display_name":"Chemistry","level":0,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0},{"id":"https://openalex.org/C162324750","wikidata":"https://www.wikidata.org/wiki/Q8134","display_name":"Economics","level":0,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":2,"locations":[{"id":"doi:10.1109/cec.2004.1330955","is_oa":false,"landing_page_url":"https://doi.org/10.1109/cec.2004.1330955","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 2004 Congress on Evolutionary Computation (IEEE Cat. No.04TH8753)","raw_type":"proceedings-article"},{"id":"pmh:oai:CiteSeerX.psu:10.1.1.343.1619","is_oa":false,"landing_page_url":"http://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.343.1619","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"submittedVersion","is_accepted":false,"is_published":false,"raw_source_name":"","raw_type":"text"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[{"id":"https://openalex.org/F4320334627","display_name":"Engineering and Physical Sciences Research Council","ror":"https://ror.org/0439y7842"}],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":11,"referenced_works":["https://openalex.org/W33488452","https://openalex.org/W1497256448","https://openalex.org/W1578372979","https://openalex.org/W1600983471","https://openalex.org/W1833785989","https://openalex.org/W1978394996","https://openalex.org/W2083215836","https://openalex.org/W2087499664","https://openalex.org/W3149025087","https://openalex.org/W6601349271","https://openalex.org/W6636088954"],"related_works":["https://openalex.org/W2372020181","https://openalex.org/W2156531654","https://openalex.org/W2149051193","https://openalex.org/W1581723585","https://openalex.org/W4378714697","https://openalex.org/W2294330161","https://openalex.org/W2910600015","https://openalex.org/W2940472653","https://openalex.org/W2253069048","https://openalex.org/W2804553224"],"abstract_inverted_index":{"Document":[0],"analysis":[1],"and":[2,9,50,76,118],"its":[3],"associated":[4],"research":[5,28],"underpins":[6],"Web":[7],"intelligence":[8],"the":[10,45,77,80,89,112],"envisaged":[11],"'semantic":[12],"Web'.":[13],"A":[14],"key":[15],"issue":[16],"is":[17,115],"how":[18],"to":[19,94],"encode":[20],"a":[21,64,74],"document":[22,130],"without":[23],"losing":[24],"salient":[25],"information.":[26],"Current":[27],"almost":[29],"always":[30],"uses":[31],"fixed-length":[32],"vectors":[33],"based":[34],"on":[35,88],"word":[36],"(term)":[37],"frequency":[38],"(TF)":[39],"and/or":[40],"variants":[41],"thereof.":[42],"We":[43],"explore":[44],"question":[46],"of":[47,66,82,85,129],"alternative":[48],"encodings,":[49],"we":[51,119],"search":[52],"for":[53,126],"such":[54],"encodings":[55,96],"using":[56,101],"an":[57],"evolutionary":[58],"algorithm":[59],"(EA).":[60],"These":[61],"alternatives":[62],"consider":[63],"variety":[65],"other":[67],"features":[68,123],"that":[69,111],"can":[70,120],"be":[71],"extracted":[72],"from":[73],"document,":[75],"EA":[78],"explores":[79],"space":[81],"weighted":[83],"combinations":[84],"these.":[86],"Tests":[87],"BankSearch":[90],"dataset":[91],"were":[92],"able":[93],"find":[95],"which":[97],"outperformed":[98],"previous":[99],"results":[100],"TF-based":[102],"encodings.":[103],"Among":[104],"several":[105],"tentative":[106],"findings":[107],"it":[108],"seems":[109],"clear":[110],"ideal":[113],"encoding":[114],"highly":[116],"task-dependent,":[117],"recommend":[121],"certain":[122],"as":[124],"useful":[125],"specific":[127],"types":[128],"clustering":[131],"tasks.":[132]},"counts_by_year":[],"updated_date":"2026-04-05T17:49:38.594831","created_date":"2025-10-10T00:00:00"}