{"id":"https://openalex.org/W2007256221","doi":"https://doi.org/10.1145/2023607.2023677","title":"The impact of text pre-processing to determine the similarity in students assignments","display_name":"The impact of text pre-processing to determine the similarity in students assignments","publication_year":2011,"publication_date":"2011-01-01","ids":{"openalex":"https://openalex.org/W2007256221","doi":"https://doi.org/10.1145/2023607.2023677","mag":"2007256221"},"language":"en","primary_location":{"id":"doi:10.1145/2023607.2023677","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2023607.2023677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Computer Systems and Technologies - CompSysTech '11","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/A5046586772","display_name":"Daniela Chud\u00e1","orcid":"https://orcid.org/0000-0002-3873-9308"},"institutions":[{"id":"https://openalex.org/I110757952","display_name":"Slovak University of Technology in Bratislava","ror":"https://ror.org/0561ghm58","country_code":"SK","type":"education","lineage":["https://openalex.org/I110757952"]}],"countries":["SK"],"is_corresponding":true,"raw_author_name":"Daniela Chud\u00e1","raw_affiliation_strings":["Slovak University of Technology in Bratislava, Slovak Republic","Slovak University of Technology in Bratislava,Slovak Republic"],"affiliations":[{"raw_affiliation_string":"Slovak University of Technology in Bratislava, Slovak Republic","institution_ids":["https://openalex.org/I110757952"]},{"raw_affiliation_string":"Slovak University of Technology in Bratislava,Slovak Republic","institution_ids":["https://openalex.org/I110757952"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5053518384","display_name":"J\u00e1n Chlpek","orcid":null},"institutions":[{"id":"https://openalex.org/I110757952","display_name":"Slovak University of Technology in Bratislava","ror":"https://ror.org/0561ghm58","country_code":"SK","type":"education","lineage":["https://openalex.org/I110757952"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"J\u00e1n Chlpek","raw_affiliation_strings":["Slovak University of Technology in Bratislava, Slovak Republic","Slovak University of Technology in Bratislava,Slovak Republic"],"affiliations":[{"raw_affiliation_string":"Slovak University of Technology in Bratislava, Slovak Republic","institution_ids":["https://openalex.org/I110757952"]},{"raw_affiliation_string":"Slovak University of Technology in Bratislava,Slovak Republic","institution_ids":["https://openalex.org/I110757952"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5091622732","display_name":"Andrej Kumor","orcid":null},"institutions":[{"id":"https://openalex.org/I110757952","display_name":"Slovak University of Technology in Bratislava","ror":"https://ror.org/0561ghm58","country_code":"SK","type":"education","lineage":["https://openalex.org/I110757952"]}],"countries":["SK"],"is_corresponding":false,"raw_author_name":"Andrej Kumor","raw_affiliation_strings":["Slovak University of Technology in Bratislava, Slovak Republic","Slovak University of Technology in Bratislava,Slovak Republic"],"affiliations":[{"raw_affiliation_string":"Slovak University of Technology in Bratislava, Slovak Republic","institution_ids":["https://openalex.org/I110757952"]},{"raw_affiliation_string":"Slovak University of Technology in Bratislava,Slovak Republic","institution_ids":["https://openalex.org/I110757952"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5046586772"],"corresponding_institution_ids":["https://openalex.org/I110757952"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.22976012,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":"417","last_page":"417"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}},"topics":[{"id":"https://openalex.org/T11492","display_name":"Academic integrity and plagiarism","score":0.9958999752998352,"subfield":{"id":"https://openalex.org/subfields/3311","display_name":"Safety Research"},"field":{"id":"https://openalex.org/fields/33","display_name":"Social Sciences"},"domain":{"id":"https://openalex.org/domains/2","display_name":"Social Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/readability","display_name":"Readability","score":0.9241595268249512},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.7488503456115723},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7458536624908447},{"id":"https://openalex.org/keywords/plagiarism-detection","display_name":"Plagiarism detection","score":0.7396044731140137},{"id":"https://openalex.org/keywords/focus","display_name":"Focus (optics)","score":0.5658969283103943},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.48552751541137695},{"id":"https://openalex.org/keywords/index","display_name":"Index (typography)","score":0.4671710431575775},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.419768750667572},{"id":"https://openalex.org/keywords/text-processing","display_name":"Text processing","score":0.4147800803184509},{"id":"https://openalex.org/keywords/information-retrieval","display_name":"Information retrieval","score":0.3996365964412689},{"id":"https://openalex.org/keywords/world-wide-web","display_name":"World Wide Web","score":0.16677290201187134},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08309075236320496}],"concepts":[{"id":"https://openalex.org/C2778143727","wikidata":"https://www.wikidata.org/wiki/Q1820650","display_name":"Readability","level":2,"score":0.9241595268249512},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.7488503456115723},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7458536624908447},{"id":"https://openalex.org/C2780907237","wikidata":"https://www.wikidata.org/wiki/Q2986238","display_name":"Plagiarism detection","level":2,"score":0.7396044731140137},{"id":"https://openalex.org/C192209626","wikidata":"https://www.wikidata.org/wiki/Q190909","display_name":"Focus (optics)","level":2,"score":0.5658969283103943},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.48552751541137695},{"id":"https://openalex.org/C2777382242","wikidata":"https://www.wikidata.org/wiki/Q6017816","display_name":"Index (typography)","level":2,"score":0.4671710431575775},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.419768750667572},{"id":"https://openalex.org/C2779500292","wikidata":"https://www.wikidata.org/wiki/Q14802672","display_name":"Text processing","level":2,"score":0.4147800803184509},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.3996365964412689},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.16677290201187134},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08309075236320496},{"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/C121332964","wikidata":"https://www.wikidata.org/wiki/Q413","display_name":"Physics","level":0,"score":0.0},{"id":"https://openalex.org/C120665830","wikidata":"https://www.wikidata.org/wiki/Q14620","display_name":"Optics","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1145/2023607.2023677","is_oa":false,"landing_page_url":"https://doi.org/10.1145/2023607.2023677","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Proceedings of the 12th International Conference on Computer Systems and Technologies - CompSysTech '11","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[{"id":"https://metadata.un.org/sdg/4","score":0.8999999761581421,"display_name":"Quality Education"}],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":5,"referenced_works":["https://openalex.org/W1967390364","https://openalex.org/W1971226872","https://openalex.org/W1989682595","https://openalex.org/W2015043351","https://openalex.org/W2042054636"],"related_works":["https://openalex.org/W1964661231","https://openalex.org/W4254960163","https://openalex.org/W3110264473","https://openalex.org/W2370831213","https://openalex.org/W4315704968","https://openalex.org/W4285478380","https://openalex.org/W2100255360","https://openalex.org/W1971922616","https://openalex.org/W3145472249","https://openalex.org/W2798173746"],"abstract_inverted_index":{"The":[0,37],"aim":[1],"of":[2,8,11,21,34,40,55,67,74,83,111,114],"this":[3,41],"paper":[4,42],"is":[5,43],"to":[6,93,104],"appraise":[7],"the":[9,65,81,87,107],"problems":[10],"plagiarism":[12,54],"in":[13,109],"students":[14,84],"assignments.":[15],"We":[16],"focus":[17],"on":[18,60,64],"pre-processing":[19,75],"techniques":[20,76,103],"Slovak":[22],"texts":[23],"assignments":[24,85],"such":[25],"as":[26,96,98],"removing":[27],"stop":[28],"words,":[29],"replacing":[30],"synonyms,":[31],"lemmatization,":[32],"using":[33],"readability":[35],"index.":[36],"main":[38],"goal":[39],"find":[44,71,105],"out":[45,106],"if":[46,90],"we":[47,70,91],"can":[48],"identify":[49],"original":[50,56],"student":[51,57],"assignment":[52,58],"and":[53,77,100],"based":[59],"their":[61],"readability.":[62],"Based":[63],"result":[66],"further":[68],"experimentation,":[69],"which":[72],"combinations":[73],"methods":[78],"for":[79,101],"determining":[80],"similarity":[82,95],"are":[86],"most":[88],"suitable,":[89],"want":[92],"detect":[94],"exactly":[97],"possible":[99],"particular":[102],"extent":[108],"detection":[110],"categorised":[112],"types":[113],"plagiarism.":[115]},"counts_by_year":[],"updated_date":"2025-11-06T03:46:38.306776","created_date":"2025-10-10T00:00:00"}
