{"id":"https://openalex.org/W2296515788","doi":"https://doi.org/10.5220/0005619105770584","title":"Performance Evaluation of Similarity Measures on Similar and Dissimilar Text Retrieval","display_name":"Performance Evaluation of Similarity Measures on Similar and Dissimilar Text Retrieval","publication_year":2015,"publication_date":"2015-01-01","ids":{"openalex":"https://openalex.org/W2296515788","doi":"https://doi.org/10.5220/0005619105770584","mag":"2296515788"},"language":"en","primary_location":{"id":"doi:10.5220/0005619105770584","is_oa":false,"landing_page_url":"https://doi.org/10.5220/0005619105770584","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","raw_type":"proceedings-article"},"type":"conference-paper","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/A5084943017","display_name":"Victor U. Thompson","orcid":null},"institutions":[{"id":"https://openalex.org/I5728261","display_name":"University of Sunderland","ror":"https://ror.org/04p55hr04","country_code":"GB","type":"education","lineage":["https://openalex.org/I5728261"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Victor U. Thompson","raw_affiliation_strings":["University of Sunderland, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sunderland, United Kingdom","institution_ids":["https://openalex.org/I5728261"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5026282516","display_name":"Christo Panchev","orcid":"https://orcid.org/0000-0002-0243-6006"},"institutions":[{"id":"https://openalex.org/I5728261","display_name":"University of Sunderland","ror":"https://ror.org/04p55hr04","country_code":"GB","type":"education","lineage":["https://openalex.org/I5728261"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Christo Panchev","raw_affiliation_strings":["University of Sunderland, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sunderland, United Kingdom","institution_ids":["https://openalex.org/I5728261"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5049405285","display_name":"Michael Oakes","orcid":"https://orcid.org/0000-0003-2793-8245"},"institutions":[{"id":"https://openalex.org/I5728261","display_name":"University of Sunderland","ror":"https://ror.org/04p55hr04","country_code":"GB","type":"education","lineage":["https://openalex.org/I5728261"]}],"countries":["GB"],"is_corresponding":false,"raw_author_name":"Michael Michael Oakes","raw_affiliation_strings":["University of Sunderland, United Kingdom"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"University of Sunderland, United Kingdom","institution_ids":["https://openalex.org/I5728261"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I5728261"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":24,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"577","last_page":"584"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10028","display_name":"Topic Modeling","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/T10028","display_name":"Topic Modeling","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/T10181","display_name":"Natural Language Processing Techniques","score":0.9988999962806702,"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/T11550","display_name":"Text and Document Classification Technologies","score":0.9980999827384949,"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/similarity","display_name":"Similarity (geometry)","score":0.8150578737258911},{"id":"https://openalex.org/keywords/pearson-product-moment-correlation-coefficient","display_name":"Pearson product-moment correlation coefficient","score":0.695021390914917},{"id":"https://openalex.org/keywords/cosine-similarity","display_name":"Cosine similarity","score":0.6849161982536316},{"id":"https://openalex.org/keywords/context","display_name":"Context (archaeology)","score":0.5947555899620056},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.5634143352508545},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.5360230803489685},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.5346381664276123},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.5107710361480713},{"id":"https://openalex.org/keywords/divergence","display_name":"Divergence (linguistics)","score":0.4772762656211853},{"id":"https://openalex.org/keywords/euclidean-distance","display_name":"Euclidean distance","score":0.45500633120536804},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.3630102276802063},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.32966500520706177},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.3181801438331604},{"id":"https://openalex.org/keywords/statistics","display_name":"Statistics","score":0.24441462755203247},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.12412920594215393}],"concepts":[{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.8150578737258911},{"id":"https://openalex.org/C55078378","wikidata":"https://www.wikidata.org/wiki/Q1136628","display_name":"Pearson product-moment correlation coefficient","level":2,"score":0.695021390914917},{"id":"https://openalex.org/C2780762811","wikidata":"https://www.wikidata.org/wiki/Q1784941","display_name":"Cosine similarity","level":3,"score":0.6849161982536316},{"id":"https://openalex.org/C2779343474","wikidata":"https://www.wikidata.org/wiki/Q3109175","display_name":"Context (archaeology)","level":2,"score":0.5947555899620056},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.5634143352508545},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.5360230803489685},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.5346381664276123},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.5107710361480713},{"id":"https://openalex.org/C207390915","wikidata":"https://www.wikidata.org/wiki/Q1230525","display_name":"Divergence (linguistics)","level":2,"score":0.4772762656211853},{"id":"https://openalex.org/C120174047","wikidata":"https://www.wikidata.org/wiki/Q847073","display_name":"Euclidean distance","level":2,"score":0.45500633120536804},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.3630102276802063},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.32966500520706177},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.3181801438331604},{"id":"https://openalex.org/C105795698","wikidata":"https://www.wikidata.org/wiki/Q12483","display_name":"Statistics","level":1,"score":0.24441462755203247},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.12412920594215393},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C86803240","wikidata":"https://www.wikidata.org/wiki/Q420","display_name":"Biology","level":0,"score":0.0},{"id":"https://openalex.org/C151730666","wikidata":"https://www.wikidata.org/wiki/Q7205","display_name":"Paleontology","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5220/0005619105770584","is_oa":false,"landing_page_url":"https://doi.org/10.5220/0005619105770584","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 7th International Joint Conference on Knowledge Discovery, Knowledge Engineering and Knowledge Management","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/1","display_name":"No poverty","score":0.5400000214576721}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":25,"referenced_works":["https://openalex.org/W75235505","https://openalex.org/W195533127","https://openalex.org/W1522930108","https://openalex.org/W1536949787","https://openalex.org/W1566018662","https://openalex.org/W1567365482","https://openalex.org/W1660390307","https://openalex.org/W1662133657","https://openalex.org/W1924059391","https://openalex.org/W1967925097","https://openalex.org/W1978394996","https://openalex.org/W1979663447","https://openalex.org/W1988711048","https://openalex.org/W1992371859","https://openalex.org/W2000569744","https://openalex.org/W2012833704","https://openalex.org/W2024932032","https://openalex.org/W2048045485","https://openalex.org/W2093390569","https://openalex.org/W2114097960","https://openalex.org/W2122577179","https://openalex.org/W2144211451","https://openalex.org/W2147152072","https://openalex.org/W2164634022","https://openalex.org/W2165612380"],"related_works":["https://openalex.org/W2236358107","https://openalex.org/W4294567033","https://openalex.org/W2135511601","https://openalex.org/W2612969269","https://openalex.org/W2010199950","https://openalex.org/W2789574762","https://openalex.org/W2020422879","https://openalex.org/W1990140521","https://openalex.org/W2909244363","https://openalex.org/W3095261004"],"abstract_inverted_index":{"Many":[0],"Information":[1],"Retrieval":[2],"(IR)":[3],"and":[4,18,96,135,144,153,160,165,186],"Natural":[5],"language":[6],"processing":[7],"(NLP)":[8],"systems":[9],"require":[10],"textual":[11,67,106],"similarity":[12,25,60,68,100,107,143,159,199],"measurement":[13],"in":[14,80,92],"order":[15],"to":[16],"function,":[17],"do":[19,40,43],"so":[20,44],"with":[21,129],"the":[22,55,81,97,116,121,130,172,193,198],"help":[23],"of":[24,57,66,72,83,94,105,118,120,132,195,197,205],"measures.":[26],"Similarity":[27],"measures":[28,32,61,122,200],"function":[29],"differently,":[30],"some":[31],"which":[33,138],"work":[34],"better":[35],"on":[36,46,62,125,149,154,175,201],"highly":[37,47,126,176],"similar":[38,127],"texts":[39],"not":[41],"always":[42],"well":[45],"dissimilar":[48,177],"texts.":[49,74,178],"In":[50],"this":[51],"paper,":[52],"we":[53],"evaluated":[54],"performances":[56,117],"eight":[58],"popular":[59],"four":[63],"levels":[64],"(degree)":[65],"using":[69],"a":[70,202],"corpus":[71],"plagiarised":[73],"The":[75,179],"evaluation":[76],"was":[77,90,108],"carried":[78],"out":[79],"context":[82],"candidate":[84],"selection":[85],"for":[86,102],"plagiarism":[87],"detection.":[88],"Performance":[89],"measured":[91],"terms":[93],"recall,":[95],"best":[98,148,164,167,173,191],"performed":[99,147,163],"measure(s)":[101],"each":[103,196],"degree":[104],"identified.":[109],"Results":[110],"from":[111],"our":[112],"Experiments":[113],"show":[114,182],"that":[115,190],"most":[119],"were":[123],"equal":[124],"texts,":[128,157],"exception":[131],"Euclidean":[133],"distance":[134],"Jensen-Shannon":[136],"divergence":[137],"had":[139,171],"poorer":[140],"performances.":[141],"Cosine":[142,158],"Bhattacharryan":[145],"coefficient":[146],"lightly":[150],"reviewed":[151,156],"text,":[152],"heavily":[155],"Pearson":[161,169],"Correlation":[162,170],"next":[166],"respectively.":[168],"performance":[174,194],"results":[180],"also":[181],"term":[183],"weighing":[184],"methods":[185],"n-gram":[187],"document":[188],"representations":[189],"optimises":[192],"particular":[203],"level":[204],"intertextual":[206],"similarity.":[207]},"counts_by_year":[{"year":2025,"cited_by_count":4},{"year":2024,"cited_by_count":2},{"year":2023,"cited_by_count":1},{"year":2022,"cited_by_count":4},{"year":2021,"cited_by_count":6},{"year":2020,"cited_by_count":1},{"year":2019,"cited_by_count":3},{"year":2018,"cited_by_count":1},{"year":2017,"cited_by_count":1},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}