{"id":"https://openalex.org/W6930354615","doi":"https://doi.org/10.5281/zenodo.14445642","title":"Online Appendix of the paper \"Locating Requirements in Backlog Items: Content Analysis and Experiments with Large Language Models\"","display_name":"Online Appendix of the paper \"Locating Requirements in Backlog Items: Content Analysis and Experiments with Large Language Models\"","publication_year":2024,"publication_date":"2024-12-17","ids":{"openalex":"https://openalex.org/W6930354615","doi":"https://doi.org/10.5281/zenodo.14445642"},"language":"en","primary_location":{"id":"doi:10.5281/zenodo.14445642","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14445642","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"type":"dataset","indexed_in":["datacite"],"open_access":{"is_oa":true,"oa_status":"green","oa_url":"https://doi.org/10.5281/zenodo.14445642","any_repository_has_fulltext":true},"authorships":[{"author_position":"first","author":{"id":null,"display_name":"van Can, Ashley","orcid":"https://orcid.org/0009-0001-1190-8327"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":true,"raw_author_name":"van Can, Ashley","raw_affiliation_strings":["Utrecht University"],"raw_orcid":"https://orcid.org/0009-0001-1190-8327","affiliations":[{"raw_affiliation_string":"Utrecht University","institution_ids":["https://openalex.org/I193662353"]}]},{"author_position":"last","author":{"id":null,"display_name":"Dalpiaz, Fabiano","orcid":"https://orcid.org/0000-0003-4480-3887"},"institutions":[{"id":"https://openalex.org/I193662353","display_name":"Utrecht University","ror":"https://ror.org/04pp8hn57","country_code":"NL","type":"education","lineage":["https://openalex.org/I193662353"]}],"countries":["NL"],"is_corresponding":false,"raw_author_name":"Dalpiaz, Fabiano","raw_affiliation_strings":["Utrecht University"],"raw_orcid":"https://orcid.org/0000-0003-4480-3887","affiliations":[{"raw_affiliation_string":"Utrecht University","institution_ids":["https://openalex.org/I193662353"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":2,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I193662353"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":null,"issue":null,"first_page":null,"last_page":null},"is_retracted":false,"is_paratext":false,"is_xpac":true,"primary_topic":{"id":"https://openalex.org/T12713","display_name":"Forest Ecology and Biodiversity Studies","score":0.3864000141620636,"subfield":{"id":"https://openalex.org/subfields/1109","display_name":"Insect Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},"topics":[{"id":"https://openalex.org/T12713","display_name":"Forest Ecology and Biodiversity Studies","score":0.3864000141620636,"subfield":{"id":"https://openalex.org/subfields/1109","display_name":"Insect Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T10004","display_name":"Soil Carbon and Nitrogen Dynamics","score":0.10610000044107437,"subfield":{"id":"https://openalex.org/subfields/1111","display_name":"Soil Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}},{"id":"https://openalex.org/T12618","display_name":"Botany and Plant Ecology Studies","score":0.06530000269412994,"subfield":{"id":"https://openalex.org/subfields/1110","display_name":"Plant Science"},"field":{"id":"https://openalex.org/fields/11","display_name":"Agricultural and Biological Sciences"},"domain":{"id":"https://openalex.org/domains/1","display_name":"Life Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/table","display_name":"Table (database)","score":0.8709999918937683},{"id":"https://openalex.org/keywords/raw-data","display_name":"Raw data","score":0.5217000246047974},{"id":"https://openalex.org/keywords/table-of-contents","display_name":"Table of contents","score":0.4832000136375427},{"id":"https://openalex.org/keywords/file-format","display_name":"File format","score":0.46149998903274536},{"id":"https://openalex.org/keywords/data-file","display_name":"Data file","score":0.4408000111579895},{"id":"https://openalex.org/keywords/flat-file-database","display_name":"Flat file database","score":0.4253000020980835},{"id":"https://openalex.org/keywords/scripting-language","display_name":"Scripting language","score":0.4099999964237213}],"concepts":[{"id":"https://openalex.org/C45235069","wikidata":"https://www.wikidata.org/wiki/Q278425","display_name":"Table (database)","level":2,"score":0.8709999918937683},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.8073999881744385},{"id":"https://openalex.org/C77088390","wikidata":"https://www.wikidata.org/wiki/Q8513","display_name":"Database","level":1,"score":0.522599995136261},{"id":"https://openalex.org/C132964779","wikidata":"https://www.wikidata.org/wiki/Q2110223","display_name":"Raw data","level":2,"score":0.5217000246047974},{"id":"https://openalex.org/C23123220","wikidata":"https://www.wikidata.org/wiki/Q816826","display_name":"Information retrieval","level":1,"score":0.4927000105381012},{"id":"https://openalex.org/C68476402","wikidata":"https://www.wikidata.org/wiki/Q1456936","display_name":"Table of contents","level":2,"score":0.4832000136375427},{"id":"https://openalex.org/C97250363","wikidata":"https://www.wikidata.org/wiki/Q235557","display_name":"File format","level":2,"score":0.46149998903274536},{"id":"https://openalex.org/C171730128","wikidata":"https://www.wikidata.org/wiki/Q5227290","display_name":"Data file","level":2,"score":0.4408000111579895},{"id":"https://openalex.org/C201743585","wikidata":"https://www.wikidata.org/wiki/Q1373925","display_name":"Flat file database","level":5,"score":0.4253000020980835},{"id":"https://openalex.org/C61423126","wikidata":"https://www.wikidata.org/wiki/Q187432","display_name":"Scripting language","level":2,"score":0.4099999964237213},{"id":"https://openalex.org/C77618280","wikidata":"https://www.wikidata.org/wiki/Q1155772","display_name":"Scheme (mathematics)","level":2,"score":0.3361000120639801},{"id":"https://openalex.org/C136764020","wikidata":"https://www.wikidata.org/wiki/Q466","display_name":"World Wide Web","level":1,"score":0.3262999951839447},{"id":"https://openalex.org/C124101348","wikidata":"https://www.wikidata.org/wiki/Q172491","display_name":"Data mining","level":1,"score":0.3237000107765198},{"id":"https://openalex.org/C2780940931","wikidata":"https://www.wikidata.org/wiki/Q174989","display_name":"File system","level":2,"score":0.3095000088214874},{"id":"https://openalex.org/C2775936607","wikidata":"https://www.wikidata.org/wiki/Q466845","display_name":"Tracking (education)","level":2,"score":0.3019999861717224},{"id":"https://openalex.org/C95637964","wikidata":"https://www.wikidata.org/wiki/Q82753","display_name":"Computer file","level":2,"score":0.301800012588501},{"id":"https://openalex.org/C104352257","wikidata":"https://www.wikidata.org/wiki/Q1238961","display_name":"Web log analysis software","level":5,"score":0.2906000018119812},{"id":"https://openalex.org/C199360897","wikidata":"https://www.wikidata.org/wiki/Q9143","display_name":"Programming language","level":1,"score":0.27709999680519104},{"id":"https://openalex.org/C205208641","wikidata":"https://www.wikidata.org/wiki/Q273404","display_name":"Pie chart","level":2,"score":0.265500009059906},{"id":"https://openalex.org/C2777904410","wikidata":"https://www.wikidata.org/wiki/Q7397","display_name":"Software","level":2,"score":0.26499998569488525},{"id":"https://openalex.org/C154586513","wikidata":"https://www.wikidata.org/wiki/Q4420972","display_name":"Tracking system","level":3,"score":0.25369998812675476}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.5281/zenodo.14445642","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14445642","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":null,"raw_source_name":null,"raw_type":"dataset"}],"best_oa_location":{"id":"doi:10.5281/zenodo.14445642","is_oa":true,"landing_page_url":"https://doi.org/10.5281/zenodo.14445642","pdf_url":null,"source":{"id":"https://openalex.org/S4306400562","display_name":"Zenodo (CERN European Organization for Nuclear Research)","issn_l":null,"issn":null,"is_oa":true,"is_in_doaj":false,"is_core":false,"host_organization":"https://openalex.org/I67311998","host_organization_name":"European Organization for Nuclear Research","host_organization_lineage":["https://openalex.org/I67311998"],"host_organization_lineage_names":[],"type":"repository"},"license":"cc-by","license_id":"https://openalex.org/licenses/cc-by","version":null,"is_accepted":false,"is_published":false,"raw_source_name":null,"raw_type":"dataset"},"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"pdf":false,"grobid_xml":false},"content_urls":null,"referenced_works_count":0,"referenced_works":[],"related_works":[],"abstract_inverted_index":{"Online":[0],"Appendix":[1],"of":[2,100,107,114,121,129,143,153,237,265,320,337,351,361,396,676,693,710,727,742,895,912,929,946,973,979,1004,1012],"the":[3,19,70,74,78,81,88,97,105,112,119,126,135,144,151,172,179,188,192,217,238,250,266,271,295,298,311,321,327,334,338,348,352,380,398,407,419,423,460,470,488,494,500,522,553,557,564,577,581,632,642,652,661,666,674,691,708,725,743,773,777,784,800,851,861,871,880,885,893,910,927,944,980,1013],"paper":[4],"\u201cLocating":[5],"Requirements":[6,1032],"in":[7,27,30,80,191,297,431,435,499,1033],"Backlog":[8,1034],"Items:":[9,1035],"Content":[10,1036],"Analysis":[11,1037],"and":[12,34,40,198,280,330,379,415,421,497,503,509,513,533,548,559,562,624,636,646,656,753,768,779,782,843,855,865,875,1038,1045],"Experiments":[13,1039],"with":[14,157,249,310,442,1040],"Large":[15,1041],"Language":[16,1042],"Models\u201d":[17],"In":[18,977,1010],"paper,":[20],"we":[21,175,241,269,292,302,345],"examine":[22],"how":[23,397],"requirements":[24,42],"are":[25,315],"documented":[26],"backlogs":[28],"stored":[29],"issue":[31,169,278,970],"tracking":[32,971],"systems":[33],"explore":[35],"automated":[36],"techniques":[37],"to":[38,52,64,140,222,364,426,464,477,525,664,746,883,957],"identify":[39],"classify":[41],"backlog":[43],"items.The":[44],"appendix":[45],"contains":[46,61,104,111,118,150,333,368,376,447,487,521,529,540,631,673,690,707,724,749,760,850,892,909,926,943],"two":[47,158,505,530,750],"main":[48,374,501],"folders,":[49],"each":[50,236,254,264,287,319,331,427,437],"related":[51,63,363,524,745],"one":[53,142],"research":[54],"question.":[55],"Folder:":[56,355],"Part":[57,356],"1":[58,258,411],"This":[59,85,132,358,366,429,485,491,519,587,739,806],"folder":[60,359,367,375,539,630,672,689,706,723,756,759,891,908,925,942],"material":[62,362,523],"RQ1.":[65],"The":[66,147,166,184,213,373,403,456,537,628,638,648,757,847,857,867],"notebook":[67,86,133],"get_results.ipynb":[68],"presents":[69,96],"results":[71,430,566,786],"based":[72],"on":[73,277,984,1017],"datasets":[75,507],"produced":[76],"by":[77,220,695,712,729,914,931,948],"files":[79,190,317,495,633,659,852,878],"subfolder":[82,193,486,520,588,740,807],"tagged":[83,156,251,293,312,335,349],"data.":[84,282],"generates":[87],"following":[89],"files:RQ1.1.xlsx,":[90],"RQ1.2a.xlsx,":[91],"RQ1.2b.xlsx,":[92],"RQ1.2c.xlsx,":[93],"RQ1.3.xlsx.":[94],"RQ1.1.xlsx":[95],"raw":[98,127,413,424,591,599,607,810,818,826],"data":[99,106,113,120,128,276,408,555,775,958],"table":[101,108,115,122,130,565,785],"3":[102],"RQ1.2a.xlsx":[103],"4":[109],"RQ1.2b.xlsx":[110],"5":[116],"RQ1.2c.xlsx":[117],"6":[123],"RQ1.3.xlsx":[124],"reports":[125],"7":[131],"utilizes":[134],"file":[136,149,167,202,218,246,307,325,332,387,404,433,457,480,489,492,550,639,649,662,770,858,868,881],"two_codes_per_req":[137],"-":[138,383,390,543,763],"OSS.xlsx":[139],"produce":[141],"result":[145],"tables.":[146],"Excel":[148,201,245,479],"number":[152],"text":[154,336,350],"segments":[155,418],"different":[159],"codes/categories":[160],"(per":[161],"project).":[162],"Subfolder":[163,181,483,517,626,669,686,703,720,888,905,922,939],"\u201cCoding":[164],"guidelines\u201d.":[165],"scheme":[168],"requirements.pdf":[170],"defines":[171],"tagging":[173],"guidelines":[174],"used":[176,616,621,835,840],"for":[177,253,326,469,511,569,617,622,644,654,789,836,841,863,873],"annotating":[178],"datasets.":[180],"\u201cTagged":[182,194],"data\u201d.":[183],"script":[185,214],"merge_nvivo_datasets.py":[186,221],"combines":[187],"Nvivo":[189,248,309],"data/Category":[195],"per":[196,208,224,454,594,596,602,604,610,612,678,813,815,821,823,829,831,897],"item\u201d":[197],"creates":[199,504],"an":[200,243,304,394,478],"that":[203],"indicates":[204],"which":[205,436],"categories":[206,252],"occur":[207],"item":[209,225,255],"(0":[210],"or":[211,259,452],"1).":[212],"link_codes_to_df.py":[215],"uses":[216,406,493],"exported":[219,244,305],"indicate":[223],"whether":[226,445],"a":[227,324,432,440,448,465],"category":[228],"occurs":[229],"more":[230],"than":[231],"once.":[232],"Subsubfolder":[233,261,283,585,804,845],"\u201cNvivo_extracted_v2\u201d.":[234],"For":[235,263,286,342],"OSS":[239,267],"projects,":[240,268],"include":[242],"from":[247,308,409,556,776],"(indicates":[256],"only":[257],"0).":[260],"\u201coriginal_samples\u201d.":[262],"add":[270],"original":[272,416],"sample":[273],"items,":[274],"including":[275],"type":[279],"creation":[281],"\u201craw":[284],"tags\u201d.":[285],"combination":[288],"(type":[289],"x":[290],"granularity)":[291],"(see":[294],"schema":[296,300],"coding":[299],"folder),":[301],"attach":[303],"txt":[306],"text.":[313],"There":[314],"10":[316],"(for":[318],"combinations":[322],"+":[323],"motivation":[328],"tags),":[329],"open":[339,1006],"source":[340,1007],"projects.":[341,354,1009],"confidentiality":[343],"reasons,":[344],"cannot":[346],"share":[347],"proprietary":[353],"2":[357],"consists":[360,741],"RQ2.":[365],"three":[369],"subfolders.":[370],"Main":[371,535,755],"folder.":[372],"convert_items_type.ipynb,":[377],"label_data.py":[378,405],"Figure":[381,388,541,761],"A":[382,389,1001],"example":[384,391,395],"segmentation.pdf.The":[385],"pdf":[386],"segmentation.pdf":[392],"provides":[393],"segmentation":[399],"process":[400],"is":[401],"performed.":[402],"part":[410],"(the":[412],"tags":[414,425],"samples),":[417],"items":[420],"links":[422],"segment.":[428],"segments_final.xlsx,":[434],"row":[438],"represents":[439],"segment":[441],"columns":[443,463],"indicating":[444],"it":[446,476,574,794],"particular":[449],"tag":[450,462,467],"(1":[451],"0":[453],"category).":[455],"convert_items_type.ipynb":[458],"converts":[459],"multiple":[461],"single":[466],"column":[468],"classification":[471],"task.":[472],"It":[473,528,748],"can":[474],"export":[475],"named:":[481],"segments_types_final.xlsx.":[482],"\u201cbalance_data\u201d":[484],"sample_data.ipynb.":[490],"segments_final.xlsx":[496],"segments_types_final.xlsx":[498],"directory":[502,849],"balanced":[506],"segments_balanced.xlsx":[508],"segments_types_balanced.xlsx":[510],"identifying":[512],"classifying":[514],"requirements,":[515],"respectively.":[516],"\u201cTask1\u201d":[518],"Task":[526],"1.":[527],"subfolders":[531,561,751],"decoder_models":[532,558,752,778],"encoder_models.":[534,754],"Folder":[536],"root":[538,629,758,848],"B":[542],"heatmap.pdf,":[544,764],"RQ2-1-precision-recall.pdf":[545],"(Figure":[546,766],"5)":[547,767],"get_req_results.ipynb.The":[549],"get_req_results.ipynb":[551],"extracts":[552,772],"performance":[554,675,692,709,726,774,894,911,928,945],"encoder_models":[560,780],"produces":[563,783],"plus":[567,787],"figures":[568,788],"Task1.":[570],"To":[571,791],"accomplish":[572,792],"this,":[573,793],"also":[575,795],"performs":[576,651,796,860,870],"hypothesis":[578,797],"tests":[579],"using":[580,799],"Python":[582,801],"package":[583,802],"SciPy.":[584,803],"\u201cdecoder_models\u201d":[586,805],"contains:":[589,808],"gpt_f1.xlxs:":[590],"F1":[592,811],"score":[593,601,609,812,820,828],"model":[595,603,611,814,822,830],"project":[597,605,613,816,824,832],"gpt_precision.xlsx:":[598],"precision":[600,819],"gpt_recall.xlsx:":[606],"recall":[608,827],"prompt_chatgpt.txt:":[614],"prompt":[615,620,834,839],"ChatGPT":[618,837],"prompt.txt:":[619],"Mistral":[623,842],"Llama":[625,844],"\u201cencoder_models\u201d":[627,846],"train_bert.py,":[634],"train_roberta.py":[635,650],"utils.py.":[637],"train_bert.py":[640],"executes":[641],"training":[643,653,667,862,872,886],"BERT":[645,677,864,896],"BERT_2.":[647,866],"RoBERTa":[655,711,874,930],"RoBERTa_2.":[657,876],"Both":[658,877],"use":[660,665,879,884],"utils.py":[663],"functions.":[668,887],"BERT:":[670,889],"this":[671,688,705,722,890,907,924,941],"project:":[679,696,713,730,898,915,932,949],"Accuracy,":[680,697,714,731,899,916,933,950],"Precision,":[681,698,715,732,900,917,934,951],"Recall,":[682,699,716,733,901,918,935,952],"TP,":[683,700,717,734,902,919,936,953],"FP,":[684,701,718,735,903,920,937,954],"FN":[685,702,719,736,904,921,938,955],"BERT_2:":[687,906],"BERT_2":[694,913],"Roberta:":[704,923],"Roberta_2:":[721,940],"RoBERTa_2":[728,947],"subfolder:":[737],"Task2":[738],"materials":[744],"Task2.":[747,790],"C":[762],"RQ2-2-precision-recall.pdf":[765],"get_req_results_type.ipynb.The":[769],"get_req_results_type.ipynb":[771],"subfolders,":[781],"testing":[798],"gpt_f1_types.xlxs:":[809],"gpt_precision_types.xlsx:":[817],"gpt_recall_types.xlsx:":[825],"prompt_type_chatgpt.txt:":[833],"prompt_type.txt:":[838],"train_bert_type.py,":[853],"train_roberta_type.py":[854,869],"utils_type.py.":[856],"train_bert_type.py":[859],"utils_type.py":[882],"Reference":[956,1023],"L.":[959],"Montgomery,":[960],"C.":[961],"L\u00fcders,":[962],"&":[963,996,1027],"W.":[964],"Maalej":[965],"(2022,":[966,999],"May).":[967,1000],"An":[968],"alternative":[969],"dataset":[972,1003],"public":[974],"jira":[975],"repositories.":[976],"Proceedings":[978,1011],"19th":[981,1014],"International":[982,1015],"Conference":[983,1016],"Mining":[985,1018],"Software":[986,1019,1046],"Repositories":[987,1020],"(pp.":[988,1021],"73-77).":[989],"V.":[990],"Tawosi,":[991],"A.":[992],"Al-Subaihin,":[993],"R.":[994],"Moussa,":[995],"F.":[997,1028],"Sarro":[998],"versatile":[1002],"agile":[1005],"software":[1008],"707-711).":[1022],"A.T.":[1024],"van":[1025],"Can":[1026],"Dalpiaz":[1029],"(2024).":[1030],"Locating":[1031],"Models.":[1043],"Information":[1044],"Technology":[1047]},"counts_by_year":[],"updated_date":"2025-11-06T06:51:31.235846","created_date":"2025-10-10T00:00:00"}