{"id":"https://openalex.org/W4296782405","doi":"https://doi.org/10.1142/s0218194022500589","title":"Exploring the Impact of Balanced and Imbalanced Learning in Source Code Suggestion","display_name":"Exploring the Impact of Balanced and Imbalanced Learning in Source Code Suggestion","publication_year":2022,"publication_date":"2022-09-20","ids":{"openalex":"https://openalex.org/W4296782405","doi":"https://doi.org/10.1142/s0218194022500589"},"language":"en","primary_location":{"id":"doi:10.1142/s0218194022500589","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218194022500589","pdf_url":null,"source":{"id":"https://openalex.org/S131442419","display_name":"International Journal of Software Engineering and Knowledge Engineering","issn_l":"0218-1940","issn":["0218-1940","1793-6403"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Software Engineering and Knowledge Engineering","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/A5079604389","display_name":"Yasir Hussain","orcid":"https://orcid.org/0000-0001-7318-8137"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yasir Hussain","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics (NUAA), Nanjing, Jiangsu 211106, P.\u00a0R.\u00a0China"],"raw_orcid":"https://orcid.org/0000-0001-7318-8137","affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics (NUAA), Nanjing, Jiangsu 211106, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5025184050","display_name":"Zhiqiu Huang","orcid":"https://orcid.org/0000-0001-6843-1892"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Zhiqiu Huang","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics (NUAA), Nanjing, Jiangsu 211106, P.\u00a0R.\u00a0China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics (NUAA), Nanjing, Jiangsu 211106, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"middle","author":{"id":"https://openalex.org/A5038150414","display_name":"Yu Zhou","orcid":"https://orcid.org/0000-0002-3723-7584"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Yu Zhou","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics (NUAA), Nanjing, Jiangsu 211106, P.\u00a0R.\u00a0China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics (NUAA), Nanjing, Jiangsu 211106, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I9842412"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5037432123","display_name":"Izhar Ahmed Khan","orcid":"https://orcid.org/0000-0001-7180-8179"},"institutions":[{"id":"https://openalex.org/I9842412","display_name":"Nanjing University of Aeronautics and Astronautics","ror":"https://ror.org/01scyh794","country_code":"CN","type":"education","lineage":["https://openalex.org/I9842412"]}],"countries":["CN"],"is_corresponding":false,"raw_author_name":"Izhar Ahmed Khan","raw_affiliation_strings":["College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics (NUAA), Nanjing, Jiangsu 211106, P.\u00a0R.\u00a0China"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics (NUAA), Nanjing, Jiangsu 211106, P.\u00a0R.\u00a0China","institution_ids":["https://openalex.org/I9842412"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I9842412"],"apc_list":null,"apc_paid":null,"fwci":0.0,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":{"value":0.18609858,"is_in_top_1_percent":false,"is_in_top_10_percent":false},"cited_by_percentile_year":null,"biblio":{"volume":"32","issue":"10","first_page":"1499","last_page":"1526"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10260","display_name":"Software Engineering Research","score":0.9994000196456909,"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":0.9994000196456909,"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/T11652","display_name":"Imbalanced Data Classification Techniques","score":0.9983000159263611,"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/T12423","display_name":"Software Reliability and Analysis Research","score":0.9861000180244446,"subfield":{"id":"https://openalex.org/subfields/1712","display_name":"Software"},"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":0.7667008638381958},{"id":"https://openalex.org/keywords/machine-learning","display_name":"Machine learning","score":0.7258126139640808},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.6854355931282043},{"id":"https://openalex.org/keywords/vocabulary","display_name":"Vocabulary","score":0.5596456527709961},{"id":"https://openalex.org/keywords/source-code","display_name":"Source code","score":0.5334558486938477},{"id":"https://openalex.org/keywords/task","display_name":"Task (project management)","score":0.4430527687072754},{"id":"https://openalex.org/keywords/natural-language-processing","display_name":"Natural language processing","score":0.321206271648407}],"concepts":[{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7667008638381958},{"id":"https://openalex.org/C119857082","wikidata":"https://www.wikidata.org/wiki/Q2539","display_name":"Machine learning","level":1,"score":0.7258126139640808},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.6854355931282043},{"id":"https://openalex.org/C2777601683","wikidata":"https://www.wikidata.org/wiki/Q6499736","display_name":"Vocabulary","level":2,"score":0.5596456527709961},{"id":"https://openalex.org/C43126263","wikidata":"https://www.wikidata.org/wiki/Q128751","display_name":"Source code","level":2,"score":0.5334558486938477},{"id":"https://openalex.org/C2780451532","wikidata":"https://www.wikidata.org/wiki/Q759676","display_name":"Task (project management)","level":2,"score":0.4430527687072754},{"id":"https://openalex.org/C204321447","wikidata":"https://www.wikidata.org/wiki/Q30642","display_name":"Natural language processing","level":1,"score":0.321206271648407},{"id":"https://openalex.org/C111919701","wikidata":"https://www.wikidata.org/wiki/Q9135","display_name":"Operating system","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/C138885662","wikidata":"https://www.wikidata.org/wiki/Q5891","display_name":"Philosophy","level":0,"score":0.0},{"id":"https://openalex.org/C41895202","wikidata":"https://www.wikidata.org/wiki/Q8162","display_name":"Linguistics","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:10.1142/s0218194022500589","is_oa":false,"landing_page_url":"https://doi.org/10.1142/s0218194022500589","pdf_url":null,"source":{"id":"https://openalex.org/S131442419","display_name":"International Journal of Software Engineering and Knowledge Engineering","issn_l":"0218-1940","issn":["0218-1940","1793-6403"],"is_oa":false,"is_in_doaj":false,"is_core":true,"host_organization":"https://openalex.org/P4310319815","host_organization_name":"World Scientific","host_organization_lineage":["https://openalex.org/P4310319815"],"host_organization_lineage_names":["World Scientific"],"type":"journal"},"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"International Journal of Software Engineering and Knowledge Engineering","raw_type":"journal-article"}],"best_oa_location":null,"sustainable_development_goals":[{"score":0.41999998688697815,"id":"https://metadata.un.org/sdg/4","display_name":"Quality Education"}],"awards":[{"id":"https://openalex.org/G368996807","display_name":null,"funder_award_id":"62150410441","funder_id":"https://openalex.org/F4320333688","funder_display_name":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China"}],"funders":[{"id":"https://openalex.org/F4320333688","display_name":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China","ror":null}],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":29,"referenced_works":["https://openalex.org/W1523518292","https://openalex.org/W1941659294","https://openalex.org/W2001487611","https://openalex.org/W2023639956","https://openalex.org/W2029602137","https://openalex.org/W2040010062","https://openalex.org/W2058580716","https://openalex.org/W2064675550","https://openalex.org/W2070808135","https://openalex.org/W2118978333","https://openalex.org/W2143612262","https://openalex.org/W2148143831","https://openalex.org/W2516621648","https://openalex.org/W2604272474","https://openalex.org/W2830760308","https://openalex.org/W2897250207","https://openalex.org/W2949297108","https://openalex.org/W2962807382","https://openalex.org/W2963895135","https://openalex.org/W2969674096","https://openalex.org/W2980260348","https://openalex.org/W2980786449","https://openalex.org/W3005373223","https://openalex.org/W3005855585","https://openalex.org/W3018933895","https://openalex.org/W3102782538","https://openalex.org/W3146720657","https://openalex.org/W4210890186","https://openalex.org/W4245415816"],"related_works":["https://openalex.org/W2349784553","https://openalex.org/W3022596247","https://openalex.org/W2601444686","https://openalex.org/W4292238148","https://openalex.org/W4323660495","https://openalex.org/W2385319785","https://openalex.org/W766546768","https://openalex.org/W2900827440","https://openalex.org/W3167549738","https://openalex.org/W2381983017"],"abstract_inverted_index":{"Studies":[0],"have":[1],"confirmed":[2],"the":[3,32,43,58,85,96,100,112,120,132,148,155,171,183,233,246,255,285],"robust":[4],"performance":[5,172,209,248,287],"of":[6,23,34,49,60,79,87,102,114,268,279],"machine":[7,18],"learning":[8,19,64,167,175],"classifiers":[9],"for":[10],"various":[11],"source":[12,66,103],"code":[13,67,73,104],"modeling":[14,91,133,156,247,286],"tasks.":[15],"In":[16,51,190],"general,":[17],"approaches":[20,39],"are":[21,29,291],"incapable":[22],"handling":[24],"imbalanced":[25,63,80,115,166],"datasets,":[26],"since":[27],"they":[28],"sensitive":[30],"to":[31,98,130,146,186,231],"choice":[33],"diverse":[35,139],"classes.":[36,81,116],"Therefore,":[37],"these":[38,161,204,239],"may":[40],"lean":[41],"towards":[42],"classes":[44],"with":[45,163,173,206],"a":[46,76,107,128,164,276],"large":[47,77,277],"percentage":[48],"observations.":[50],"this":[52,272],"work,":[53],"we":[54,94,118,136,159,178,192,226],"investigate":[55,111],"and":[56,62,110,144,150,169,201,220,236,262],"explore":[57,84],"impact":[59,86,153],"balanced":[61,174,251],"on":[65,90,154,196],"suggestion":[68,105],"task":[69,109],"otherwise":[70],"known":[71],"as":[72,106,127,212],"completion,":[74],"covering":[75],"number":[78],"We":[82],"further":[83],"vocabulary":[88,184,280],"size":[89,185,278],"performance.":[92,134,157],"First,":[93],"provide":[95],"essentials":[97],"formulate":[99],"problem":[101],"classification":[108],"level":[113],"Second,":[117],"train":[119,179],"four":[121],"most":[122],"adapted":[123],"neural":[124],"language":[125],"models":[126,162,180,195,205],"baseline":[129],"assess":[131],"Third,":[135],"impose":[137],"two":[138],"class":[140],"balancing":[141],"techniques,":[142],"TomekLinks":[143],"AllKNN,":[145],"balance":[147],"datasets":[149],"evaluate":[151],"their":[152,188],"Finally,":[158],"trained":[160,193],"weighted":[165,256],"approach":[168],"compared":[170],"approaches.":[176,240],"Additionally,":[177,225,271],"by":[181],"varying":[182],"study":[187,232,242,273],"impact.":[189],"total,":[191],"230":[194],"10":[197],"real-world":[198],"software":[199],"projects":[200],"extensively":[202],"evaluated":[203],"widely":[207],"used":[208],"metrics":[210],"such":[211],"Precision,":[213],"Recall,":[214],"FScore,":[215],"mean":[216],"reciprocal":[217],"rank":[218],"(MRR),":[219],"Receiver":[221],"operating":[222],"characteristics":[223],"(ROC).":[224],"employed":[227],"ANOVA":[228],"statistical":[229,234],"analysis":[230],"significance":[235],"differences":[237],"between":[238],"This":[241],"has":[243],"demonstrated":[244],"that":[245,275],"decreases":[249],"during":[250],"model":[252],"training,":[253],"whereas":[254],"imbalance":[257],"training":[258],"produces":[259],"comparable":[260],"results":[261],"is":[263],"more":[264],"efficient":[265],"in":[266],"terms":[267],"time":[269],"cost.":[270],"exhibits":[274],"does":[281],"not":[282],"necessarily":[283],"improve":[284],"when":[288],"out-of-vocabulary":[289],"predictions":[290],"disregarded.":[292]},"counts_by_year":[],"updated_date":"2026-05-21T06:26:12.895304","created_date":"2025-10-10T00:00:00"}
