{"id":"https://openalex.org/W2590657376","doi":"https://doi.org/10.1134/s0361768817010066","title":"Measuring similarity between Karel programs using character and word n-grams","display_name":"Measuring similarity between Karel programs using character and word n-grams","publication_year":2017,"publication_date":"2017-01-01","ids":{"openalex":"https://openalex.org/W2590657376","doi":"https://doi.org/10.1134/s0361768817010066","mag":"2590657376"},"language":"en","primary_location":{"id":"doi:10.1134/s0361768817010066","is_oa":false,"landing_page_url":"https://doi.org/10.1134/s0361768817010066","pdf_url":null,"source":{"id":"https://openalex.org/S150218641","display_name":"Programming and Computer Software","issn_l":"0361-7688","issn":["0361-7688","1608-3261","3034-5847"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320267","host_organization_name":"Pleiades Publishing","host_organization_lineage":["https://openalex.org/P4310320267","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Pleiades Publishing","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Programming and Computer Software","raw_type":"journal-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/A5008287867","display_name":"Grigori Sidorov","orcid":"https://orcid.org/0000-0003-3901-3522"},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"G. Sidorov","raw_affiliation_strings":["Instituto Polit\u00e9cnico Nacional (IPN), Center for Computing Research (CIC), Mexico City, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto Polit\u00e9cnico Nacional (IPN), Center for Computing Research (CIC), Mexico City, Mexico","institution_ids":["https://openalex.org/I59361560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5109524223","display_name":"Manuel Romero","orcid":null},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":false,"raw_author_name":"M. Ibarra Romero","raw_affiliation_strings":["Instituto Polit\u00e9cnico Nacional (IPN), Center for Computing Research (CIC), Mexico City, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto Polit\u00e9cnico Nacional (IPN), Center for Computing Research (CIC), Mexico City, Mexico","institution_ids":["https://openalex.org/I59361560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5051243807","display_name":"Ilia Markov","orcid":"https://orcid.org/0000-0001-9533-748X"},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"I. Markov","raw_affiliation_strings":["Instituto Polit\u00e9cnico Nacional (IPN), Center for Computing Research (CIC), Mexico City, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto Polit\u00e9cnico Nacional (IPN), Center for Computing Research (CIC), Mexico City, Mexico","institution_ids":["https://openalex.org/I59361560"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5030185432","display_name":"Rafael Guzm\u00e1n-Cabrera","orcid":"https://orcid.org/0000-0002-9320-7021"},"institutions":[{"id":"https://openalex.org/I129858807","display_name":"Universidad de Guanajuato","ror":"https://ror.org/058cjye32","country_code":"MX","type":"education","lineage":["https://openalex.org/I129858807"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"R. Guzman-Cabrera","raw_affiliation_strings":["Engineering Division, University of Guanajuato, Campus Irapuato-Salamanca, Guanajuato, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Engineering Division, University of Guanajuato, Campus Irapuato-Salamanca, Guanajuato, Mexico","institution_ids":["https://openalex.org/I129858807"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5087217360","display_name":"Liliana Chanona-Hern\u00e1ndez","orcid":"https://orcid.org/0000-0001-7468-9603"},"institutions":[{"id":"https://openalex.org/I59361560","display_name":"Instituto Polit\u00e9cnico Nacional","ror":"https://ror.org/059sp8j34","country_code":"MX","type":"education","lineage":["https://openalex.org/I59361560"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"L. Chanona-Hern\u00e1ndez","raw_affiliation_strings":["Instituto Polit\u00e9cnico Nacional, School of Mechanical and Electrical Engineering (ESIME), Mexico City, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Instituto Polit\u00e9cnico Nacional, School of Mechanical and Electrical Engineering (ESIME), Mexico City, Mexico","institution_ids":["https://openalex.org/I59361560"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5013144372","display_name":"Francisco Vel\u00e1squez","orcid":"https://orcid.org/0000-0001-9672-7500"},"institutions":[{"id":"https://openalex.org/I4210156031","display_name":"Polytechnic University of Queretaro","ror":"https://ror.org/0580rm578","country_code":"MX","type":"education","lineage":["https://openalex.org/I4210156031"]}],"countries":["MX"],"is_corresponding":true,"raw_author_name":"F. Vel\u00e1squez","raw_affiliation_strings":["Polytechnic University of Queretaro, Queretaro, Mexico"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Polytechnic University of Queretaro, Queretaro, Mexico","institution_ids":["https://openalex.org/I4210156031"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":3,"corresponding_author_ids":["https://openalex.org/A5008287867","https://openalex.org/A5013144372","https://openalex.org/A5030185432","https://openalex.org/A5051243807","https://openalex.org/A5087217360"],"corresponding_institution_ids":["https://openalex.org/I129858807","https://openalex.org/I4210156031","https://openalex.org/I59361560"],"apc_list":null,"apc_paid":null,"fwci":3.7875,"has_fulltext":false,"cited_by_count":10,"citation_normalized_percentile":{"value":0.94111191,"is_in_top_1_percent":false,"is_in_top_10_percent":true},"cited_by_percentile_year":{"min":90,"max":96},"biblio":{"volume":"43","issue":"1","first_page":"47","last_page":"50"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9980999827384949,"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"}},"topics":[{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9980999827384949,"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/T10181","display_name":"Natural Language Processing Techniques","score":0.9973000288009644,"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/T12254","display_name":"Machine Learning in Bioinformatics","score":0.9945999979972839,"subfield":{"id":"https://openalex.org/subfields/1312","display_name":"Molecular Biology"},"field":{"id":"https://openalex.org/fields/13","display_name":"Biochemistry, Genetics and Molecular Biology"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7776597142219543},{"id":"https://openalex.org/keywords/latent-semantic-analysis","display_name":"Latent semantic analysis","score":0.7682129144668579},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6768654584884644},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.6396054625511169},{"id":"https://openalex.org/keywords/character","display_name":"Character (mathematics)","score":0.5741592645645142},{"id":"https://openalex.org/keywords/karel","display_name":"Karel","score":0.552276074886322},{"id":"https://openalex.org/keywords/similarity","display_name":"Similarity (geometry)","score":0.5480445027351379},{"id":"https://openalex.org/keywords/word","display_name":"Word (group theory)","score":0.5396021008491516},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.5056648254394531},{"id":"https://openalex.org/keywords/semantic-similarity","display_name":"Semantic similarity","score":0.46689948439598083},{"id":"https://openalex.org/keywords/trigram","display_name":"Trigram","score":0.46537965536117554},{"id":"https://openalex.org/keywords/classifier","display_name":"Classifier (UML)","score":0.4571537673473358},{"id":"https://openalex.org/keywords/linguistics","display_name":"Linguistics","score":0.11111322045326233},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.09686389565467834},{"id":"https://openalex.org/keywords/programming-language","display_name":"Programming language","score":0.08978188037872314}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7776597142219543},{"id":"https://openalex.org/C170133592","wikidata":"https://www.wikidata.org/wiki/Q1806883","display_name":"Latent semantic analysis","level":2,"score":0.7682129144668579},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6768654584884644},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.6396054625511169},{"id":"https://openalex.org/C2780861071","wikidata":"https://www.wikidata.org/wiki/Q1062934","display_name":"Character (mathematics)","level":2,"score":0.5741592645645142},{"id":"https://openalex.org/C2780043134","wikidata":"https://www.wikidata.org/wiki/Q204693","display_name":"Karel","level":2,"score":0.552276074886322},{"id":"https://openalex.org/C103278499","wikidata":"https://www.wikidata.org/wiki/Q254465","display_name":"Similarity (geometry)","level":3,"score":0.5480445027351379},{"id":"https://openalex.org/C90805587","wikidata":"https://www.wikidata.org/wiki/Q10944557","display_name":"Word (group theory)","level":2,"score":0.5396021008491516},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.5056648254394531},{"id":"https://openalex.org/C130318100","wikidata":"https://www.wikidata.org/wiki/Q2268914","display_name":"Semantic similarity","level":2,"score":0.46689948439598083},{"id":"https://openalex.org/C137546455","wikidata":"https://www.wikidata.org/wiki/Q3213474","display_name":"Trigram","level":2,"score":0.46537965536117554},{"id":"https://openalex.org/C95623464","wikidata":"https://www.wikidata.org/wiki/Q1096149","display_name":"Classifier (UML)","level":2,"score":0.4571537673473358},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","level":1,"score":0.11111322045326233},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.09686389565467834},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.08978188037872314},{"id":"https://openalex.org/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"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/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0},{"id":"https://openalex.org/C187736073","wikidata":"https://www.wikidata.org/wiki/Q2920921","display_name":"Management","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1134/s0361768817010066","is_oa":false,"landing_page_url":"https://doi.org/10.1134/s0361768817010066","pdf_url":null,"source":{"id":"https://openalex.org/S150218641","display_name":"Programming and Computer Software","issn_l":"0361-7688","issn":["0361-7688","1608-3261","3034-5847"],"is_oa":false,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/P4310320267","host_organization_name":"Pleiades Publishing","host_organization_lineage":["https://openalex.org/P4310320267","https://openalex.org/P4310319965"],"host_organization_lineage_names":["Pleiades Publishing","Springer Nature"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"Programming and Computer Software","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":18,"referenced_works":["https://openalex.org/W76990466","https://openalex.org/W1505648523","https://openalex.org/W1616853180","https://openalex.org/W1964962870","https://openalex.org/W2024635814","https://openalex.org/W2073265902","https://openalex.org/W2085698608","https://openalex.org/W2111295912","https://openalex.org/W2121412398","https://openalex.org/W2133990480","https://openalex.org/W2147152072","https://openalex.org/W2165005075","https://openalex.org/W2612383341","https://openalex.org/W3007592595","https://openalex.org/W3138587813","https://openalex.org/W4252211664","https://openalex.org/W4285719527","https://openalex.org/W4301404790"],"related_works":["https://openalex.org/W2011383762","https://openalex.org/W2760819588","https://openalex.org/W3152143533","https://openalex.org/W3016822073","https://openalex.org/W2626769217","https://openalex.org/W2311893701","https://openalex.org/W4385572821","https://openalex.org/W2907506409","https://openalex.org/W2367617289","https://openalex.org/W2321844481"],"abstract_inverted_index":{"We":[0,10,46],"present":[1],"a":[2,48],"method":[3],"for":[4],"measuring":[5],"similarity":[6],"between":[7],"source":[8,63],"codes.":[9],"approach":[11],"this":[12,44],"task":[13],"from":[14],"the":[15,36,39,54,67,80,93],"machine":[16,30],"learning":[17,31],"perspective":[18],"using":[19,87],"character":[20],"and":[21,27,97],"word":[22],"n":[23],"-grams":[24],"as":[25,99],"features":[26,100],"examining":[28],"different":[29,74],"algorithms.":[32],"Furthermore,":[33],"we":[34],"explore":[35],"contribution":[37],"of":[38,60,102],"latent":[40,94],"semantic":[41,95],"analysis":[42],"in":[43,50,66],"task.":[45],"developed":[47],"corpus":[49,58],"order":[51],"to":[52,71],"evaluate":[53],"proposed":[55],"approach.":[56],"The":[57,76],"consists":[59],"around":[61],"10,000":[62],"codes":[64],"written":[65],"Karel":[68],"programming":[69],"language":[70],"solve":[72],"100":[73],"tasks.":[75],"results":[77],"show":[78],"that":[79],"highest":[81],"classification":[82],"accuracy":[83],"is":[84],"achieved":[85],"when":[86],"Support":[88],"Vector":[89],"Machines":[90],"classifier,":[91],"applying":[92],"analysis,":[96],"selecting":[98],"trigrams":[101],"words.":[103]},"counts_by_year":[{"year":2025,"cited_by_count":1},{"year":2021,"cited_by_count":2},{"year":2020,"cited_by_count":2},{"year":2019,"cited_by_count":2},{"year":2017,"cited_by_count":2},{"year":2016,"cited_by_count":1}],"updated_date":"2026-07-31T08:31:51.225901","created_date":"2025-10-10T00:00:00"}
