Exploring ChatGPT's Potential in Java API Method Recommendation: An Empirical Study

ABSTRACT As software development grows increasingly complex, application programming interface (API) plays a significant role in enhancing development efficiency and code quality. However, the explosive growth in the number of APIs makes it impossible for developers to become familiar with all of th...

Celý popis

Uložené v:
Podrobná bibliografia
Vydané v:Journal of software : evolution and process Ročník 37; číslo 1
Hlavní autori: Wang, Ye, Xue, Weihao, Huang, Qiao, Jiang, Bo, Zhang, Hua
Médium: Journal Article
Jazyk:English
Vydavateľské údaje: Chichester Wiley Subscription Services, Inc 01.01.2025
Predmet:
ISSN:2047-7473, 2047-7481
On-line prístup:Získať plný text
Tagy: Pridať tag
Žiadne tagy, Buďte prvý, kto otaguje tento záznam!
Abstract ABSTRACT As software development grows increasingly complex, application programming interface (API) plays a significant role in enhancing development efficiency and code quality. However, the explosive growth in the number of APIs makes it impossible for developers to become familiar with all of them. In actual development scenarios, developers may spend a significant amount of time searching for suitable APIs, which could severely impact the development process. Recently, the OpenAI's large language model (LLM) based application—ChatGPT has shown exceptional performance across various software development tasks, responding swiftly to instructions and generating high‐quality textual responses, suggesting its potential in API recommendation tasks. Thus, this paper presents an empirical study to investigate the performance of ChatGPT in query‐based API recommendation tasks. Specifically, we utilized the existing benchmark APIBENCH‐Q and the newly constructed dataset as evaluation datasets, selecting the state‐of‐the‐art models BIKER and MULAREC for comparison with ChatGPT. Our research findings demonstrate that ChatGPT outperforms existing approaches in terms of success rate, mean reciprocal rank (MRR), and mean average precision (MAP). Through a manual examination of samples in which ChatGPT exceeds baseline performance and those where it provides incorrect answers, we further substantiate ChatGPT's advantages over the baselines and identify several issues contributing to its suboptimal performance. To address these issues and enhance ChatGPT's recommendation capabilities, we employed two strategies: (1) utilizing a more advanced LLM (GPT‐4) and (2) exploring a new approach—MACAR, which is based on the Chain of Thought methodology. The results indicate that both strategies are effective. This paper presents an empirical study to investigate the performance of ChatGPT in query‐based API recommendation tasks. Our research findings demonstrate that ChatGPT with specific prompt outperforms existing approaches in terms of success rate, mean reciprocal rank (MRR), and mean average precision (MAP). To further improve the performance of ChatGPT, we propose a new approach called MACAR, which utilize multi‐agent collaboration and chain of thought.
AbstractList ABSTRACT As software development grows increasingly complex, application programming interface (API) plays a significant role in enhancing development efficiency and code quality. However, the explosive growth in the number of APIs makes it impossible for developers to become familiar with all of them. In actual development scenarios, developers may spend a significant amount of time searching for suitable APIs, which could severely impact the development process. Recently, the OpenAI's large language model (LLM) based application—ChatGPT has shown exceptional performance across various software development tasks, responding swiftly to instructions and generating high‐quality textual responses, suggesting its potential in API recommendation tasks. Thus, this paper presents an empirical study to investigate the performance of ChatGPT in query‐based API recommendation tasks. Specifically, we utilized the existing benchmark APIBENCH‐Q and the newly constructed dataset as evaluation datasets, selecting the state‐of‐the‐art models BIKER and MULAREC for comparison with ChatGPT. Our research findings demonstrate that ChatGPT outperforms existing approaches in terms of success rate, mean reciprocal rank (MRR), and mean average precision (MAP). Through a manual examination of samples in which ChatGPT exceeds baseline performance and those where it provides incorrect answers, we further substantiate ChatGPT's advantages over the baselines and identify several issues contributing to its suboptimal performance. To address these issues and enhance ChatGPT's recommendation capabilities, we employed two strategies: (1) utilizing a more advanced LLM (GPT‐4) and (2) exploring a new approach—MACAR, which is based on the Chain of Thought methodology. The results indicate that both strategies are effective. This paper presents an empirical study to investigate the performance of ChatGPT in query‐based API recommendation tasks. Our research findings demonstrate that ChatGPT with specific prompt outperforms existing approaches in terms of success rate, mean reciprocal rank (MRR), and mean average precision (MAP). To further improve the performance of ChatGPT, we propose a new approach called MACAR, which utilize multi‐agent collaboration and chain of thought.
As software development grows increasingly complex, application programming interface (API) plays a significant role in enhancing development efficiency and code quality. However, the explosive growth in the number of APIs makes it impossible for developers to become familiar with all of them. In actual development scenarios, developers may spend a significant amount of time searching for suitable APIs, which could severely impact the development process. Recently, the OpenAI's large language model (LLM) based application—ChatGPT has shown exceptional performance across various software development tasks, responding swiftly to instructions and generating high‐quality textual responses, suggesting its potential in API recommendation tasks. Thus, this paper presents an empirical study to investigate the performance of ChatGPT in query‐based API recommendation tasks. Specifically, we utilized the existing benchmark APIBENCH‐Q and the newly constructed dataset as evaluation datasets, selecting the state‐of‐the‐art models BIKER and MULAREC for comparison with ChatGPT. Our research findings demonstrate that ChatGPT outperforms existing approaches in terms of success rate, mean reciprocal rank (MRR), and mean average precision (MAP). Through a manual examination of samples in which ChatGPT exceeds baseline performance and those where it provides incorrect answers, we further substantiate ChatGPT's advantages over the baselines and identify several issues contributing to its suboptimal performance. To address these issues and enhance ChatGPT's recommendation capabilities, we employed two strategies: (1) utilizing a more advanced LLM (GPT‐4) and (2) exploring a new approach—MACAR, which is based on the Chain of Thought methodology. The results indicate that both strategies are effective.
Author Xue, Weihao
Jiang, Bo
Zhang, Hua
Wang, Ye
Huang, Qiao
Author_xml – sequence: 1
  givenname: Ye
  surname: Wang
  fullname: Wang, Ye
  organization: Zhejiang Key Laboratory of Big Data and Future E‐Commerce Technology
– sequence: 2
  givenname: Weihao
  surname: Xue
  fullname: Xue, Weihao
  organization: Zhejiang Key Laboratory of Big Data and Future E‐Commerce Technology
– sequence: 3
  givenname: Qiao
  orcidid: 0000-0002-7869-1310
  surname: Huang
  fullname: Huang, Qiao
  email: qiaohuang@zjgsu.edu.cn
  organization: Zhejiang Key Laboratory of Big Data and Future E‐Commerce Technology
– sequence: 4
  givenname: Bo
  surname: Jiang
  fullname: Jiang, Bo
  organization: Zhejiang Key Laboratory of Big Data and Future E‐Commerce Technology
– sequence: 5
  givenname: Hua
  surname: Zhang
  fullname: Zhang, Hua
  organization: Zhejiang Key Laboratory of Big Data and Future E‐Commerce Technology
BookMark eNp1kFFLwzAUhYMoOOfAnxDwQV86kzRNqm9jzDnZcGzzOWRp6jLapCadun9v5sQ3L1zO4fJxD5wLcGqd1QBcYdTHCJG7UPs-4Sw7AR2CKE84zfHpn-fpOeiFsEVxGEEZzTpgOfpqKueNfYPDjWzH89VNgHPXatsaWUFj4bP8kHAwn8CZbjeugAutXF1rW8jWOPsABxaO6sZ4oyK_bHfF_hKclbIKuverXfD6OFoNn5Lpy3gyHEwTRWJ2QlNE0lxhxHFa0CwnmpU5zdYUYariWZVrWRKqGC8UYzItsIy6VgXNeVkynHbB9fFv4937TodWbN3O2xgpUszQYe9ppG6PlPIuBK9L0XhTS78XGIlDayK2Jg6tRTQ5op-m0vt_ObGcLX74b_ltbak
Cites_doi 10.1109/ICSE.2015.336
10.1109/ICSE-SEIP52600.2021.00022
10.1109/TSE.2015.2500238
10.1162/neco.1997.9.8.1735
10.1109/ICSE48619.2023.00129
10.1145/3196398.3196450
10.1145/3238147.3238191
10.1007/978-0-387-85820-3_1
10.1145/3597503.3623306
10.18653/v1/2020.findings-emnlp.139
10.1016/S0169-7552(98)00110-X
10.1109/TSE.2023.3346954
10.1109/ASE56229.2023.00075
10.1109/SANER.2016.80
10.1109/SANER56733.2023.00034
10.1145/2594291.2594321
10.1038/323533a0
10.18653/v1/2023.emnlp-main.557
10.1109/ICSE43902.2021.00026
10.1016/j.future.2018.05.006
10.1145/3524459.3527351
10.1145/2393596.2393606
10.1109/TSE.2022.3197063
10.1145/1985793.1985809
10.1145/2884781.2884808
10.1145/2950290.2950334
10.1145/3338906.3338971
10.1109/TSE.2021.3053111
10.1145/3022671.2984041
10.1016/j.infsof.2023.107269
10.1145/3196321.3196334
10.1145/2884781.2884862
ContentType Journal Article
Copyright 2025 John Wiley & Sons Ltd.
2025 John Wiley & Sons, Ltd.
Copyright_xml – notice: 2025 John Wiley & Sons Ltd.
– notice: 2025 John Wiley & Sons, Ltd.
DBID AAYXX
CITATION
7SC
8FD
JQ2
L7M
L~C
L~D
DOI 10.1002/smr.2765
DatabaseName CrossRef
Computer and Information Systems Abstracts
Technology Research Database
ProQuest Computer Science Collection
Advanced Technologies Database with Aerospace
Computer and Information Systems Abstracts – Academic
Computer and Information Systems Abstracts Professional
DatabaseTitle CrossRef
Computer and Information Systems Abstracts
Technology Research Database
Computer and Information Systems Abstracts – Academic
Advanced Technologies Database with Aerospace
ProQuest Computer Science Collection
Computer and Information Systems Abstracts Professional
DatabaseTitleList
Computer and Information Systems Abstracts
CrossRef
DeliveryMethod fulltext_linktorsrc
Discipline Computer Science
EISSN 2047-7481
EndPage n/a
ExternalDocumentID 10_1002_smr_2765
SMR2765
Genre article
GrantInformation_xml – fundername: Natural Science Foundation of Zhejiang Province
  funderid: LY24F020003
– fundername: Zhejiang Province’s "Sharpshooter & Pioneer" Key Research and Breakthrough Program
  funderid: 2024C01070
– fundername: National Natural Science Foundation of China
  funderid: 62302447
GroupedDBID .3N
.4S
.GA
.Y3
05W
0R~
10A
1OB
1OC
31~
33P
3SF
50Z
52O
52U
8-0
8-1
8-3
8-4
8-5
930
A03
AAESR
AAEVG
AAHQN
AAMNL
AANHP
AANLZ
AAONW
AASGY
AAXRX
AAYCA
AAZKR
ABCUV
ABPVW
ACAHQ
ACBWZ
ACCZN
ACPOU
ACRPL
ACXBN
ACXQS
ACYXJ
ADBBV
ADEOM
ADIZJ
ADKYN
ADMGS
ADMLS
ADNMO
ADOZA
ADXAS
ADZMN
AEIGN
AEIMD
AEUYR
AEYWJ
AFBPY
AFFPM
AFGKR
AFWVQ
AFZJQ
AGHNM
AGQPQ
AGYGG
AHBTC
AITYG
AIURR
AJXKR
ALMA_UNASSIGNED_HOLDINGS
ALUQN
ALVPJ
AMBMR
AMYDB
ARCSS
ATUGU
AUFTA
AZBYB
AZFZN
BAFTC
BDRZF
BHBCM
BMNLL
BMXJE
BRXPI
BY8
D-E
D-F
DCZOG
DPXWK
DR2
DRFUL
DRSTM
EBS
EDO
EJD
F00
F01
F04
G-S
G.N
GODZA
HGLYW
HZ~
I-F
LATKE
LEEKS
LH4
LITHE
LOXES
LUTES
LW6
LYRES
MEWTI
MRFUL
MRSTM
MSFUL
MSSTM
MXFUL
MXSTM
N04
N05
O66
O9-
P2W
P2X
PQQKQ
Q.N
Q11
QB0
R.K
ROL
SUPJJ
TUS
W8V
W99
WBKPD
WIH
WIK
WOHZO
WXSBR
WYISQ
WZISG
~WT
AAYXX
CITATION
O8X
7SC
8FD
JQ2
L7M
L~C
L~D
ID FETCH-LOGICAL-c2545-430238c10713d4582e6f845b4014cc10cfbaf24c67dc66a3d1ac66bcd487ff613
IEDL.DBID DRFUL
ISICitedReferencesCount 0
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=001407016600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 2047-7473
IngestDate Wed Aug 13 10:43:44 EDT 2025
Sat Nov 29 03:00:26 EST 2025
Wed Aug 20 07:26:39 EDT 2025
IsPeerReviewed true
IsScholarly true
Issue 1
Language English
LinkModel DirectLink
MergedId FETCHMERGED-LOGICAL-c2545-430238c10713d4582e6f845b4014cc10cfbaf24c67dc66a3d1ac66bcd487ff613
Notes Funding
This work was supported by the Natural Science Foundation of China (grant number 62302447), the Zhejiang Province's “Sharpshooter & Pioneer” Key Research and Breakthrough Program (grant number 2024C01070), and the Natural Science Foundation of Zhejiang Province (grant number LY24F020003).
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ORCID 0000-0002-7869-1310
PQID 3160316094
PQPubID 2034650
PageCount 20
ParticipantIDs proquest_journals_3160316094
crossref_primary_10_1002_smr_2765
wiley_primary_10_1002_smr_2765_SMR2765
PublicationCentury 2000
PublicationDate January 2025
2025-01-00
20250101
PublicationDateYYYYMMDD 2025-01-01
PublicationDate_xml – month: 01
  year: 2025
  text: January 2025
PublicationDecade 2020
PublicationPlace Chichester
PublicationPlace_xml – name: Chichester
PublicationTitle Journal of software : evolution and process
PublicationYear 2025
Publisher Wiley Subscription Services, Inc
Publisher_xml – name: Wiley Subscription Services, Inc
References 2021; 48
2012
2011
2023; 162
2024; 50
2016; 51
2020; 33
2023; 2
2024
2018; 87
2022; 49
1997; 9
1986; 323
2013; 15
2023
2022
2021
2020
2015; 42
2022; 35
2019
2018
2017
2016
2015
2014
2020; 21
1998; 30
Ouyang L. (e_1_2_11_6_1) 2022; 35
Li J. (e_1_2_11_29_1) 2024
e_1_2_11_32_1
e_1_2_11_31_1
e_1_2_11_30_1
e_1_2_11_36_1
Vaswani A. (e_1_2_11_10_1) 2017
e_1_2_11_13_1
e_1_2_11_35_1
e_1_2_11_12_1
e_1_2_11_34_1
e_1_2_11_11_1
e_1_2_11_33_1
e_1_2_11_7_1
e_1_2_11_28_1
e_1_2_11_5_1
e_1_2_11_27_1
e_1_2_11_4_1
e_1_2_11_3_1
e_1_2_11_2_1
Singh R. (e_1_2_11_22_1) 2013
Stiennon N. (e_1_2_11_15_1) 2020; 33
Wei J. (e_1_2_11_25_1) 2022
Raffel C. (e_1_2_11_14_1) 2020; 21
e_1_2_11_21_1
e_1_2_11_44_1
e_1_2_11_20_1
e_1_2_11_45_1
e_1_2_11_46_1
e_1_2_11_40_1
e_1_2_11_24_1
e_1_2_11_41_1
e_1_2_11_9_1
e_1_2_11_23_1
e_1_2_11_42_1
e_1_2_11_8_1
e_1_2_11_43_1
e_1_2_11_18_1
e_1_2_11_17_1
e_1_2_11_16_1
e_1_2_11_37_1
e_1_2_11_38_1
e_1_2_11_39_1
e_1_2_11_19_1
Chen W. (e_1_2_11_26_1) 2023; 2
References_xml – start-page: 858
  year: 2015
  end-page: 868
– start-page: 69
  year: 2022
  end-page: 75
– year: 2024
  article-title: Structured Chain‐of‐Thought Prompting for Code Generation
  publication-title: ACM Transactions on Software Engineering and Methodology
– start-page: 471
  year: 2023
  end-page: 483
– volume: 21
  start-page: 1
  issue: 140
  year: 2020
  end-page: 67
  article-title: Exploring the Limits of Transfer Learning With a Unified Text‐to‐Text Transformer
  publication-title: Journal of Machine Learning Research
– volume: 48
  start-page: 2157
  issue: 6
  year: 2021
  end-page: 2172
  article-title: Boosting API Recommendation With Implicit Feedback
  publication-title: IEEE Transactions on Software Engineering
– volume: 51
  start-page: 731
  issue: 10
  year: 2016
  end-page: 747
  article-title: Probabilistic Model for Code With Decision Trees
  publication-title: ACM SIGPLAN Notices
– volume: 33
  start-page: 3008
  year: 2020
  end-page: 3021
  article-title: Learning to Summarize With Human Feedback
  publication-title: Advances in Neural Information Processing Systems
– year: 2021
– start-page: 404
  year: 2016
  end-page: 415
– volume: 162
  start-page: 107269
  year: 2023
  article-title: PAREI: A Progressive Approach for Web API Recommendation by Combining Explicit and Implicit Information
  publication-title: Information and Software Technology
– year: 2024
– start-page: 111
  year: 2011
  end-page: 120
– volume: 35
  start-page: 27730
  year: 2022
  end-page: 27744
  article-title: Training Language Models to Follow Instructions With Human Feedback
  publication-title: Advances in Neural Information Processing Systems
– volume: 35
  start-page: 24824
  year: 2022
  end-page: 24837
– start-page: 1482
  year: 2023
  end-page: 1494
– year: 2018
– start-page: 419
  year: 2014
  end-page: 428
– start-page: 272
  year: 2023
  end-page: 283
– volume: 15
  year: 2013
– start-page: 150
  year: 2021
  end-page: 162
– year: 2012
– volume: 42
  start-page: 530
  issue: 6
  year: 2015
  end-page: 543
  article-title: Automatically Recommending Peer Reviewers in Modern Code Review
  publication-title: IEEE Transactions on Software Engineering
– start-page: 1
  year: 2011
  end-page: 35
– volume: 49
  start-page: 1876
  issue: 4
  year: 2022
  end-page: 1897
  article-title: Revisiting, Benchmarking and Exploring API Recommendation: How Far Are We?
  publication-title: IEEE Transactions on Software Engineering
– volume: 2
  start-page: 6
  issue: 4
  year: 2023
  article-title: Agentverse: Facilitating Multi‐Agent Collaboration and Exploring Emergent Behaviors in Agents
  publication-title: arXiv preprint arXiv:2308.10848
– volume: 30
  start-page: 107
  issue: 1‐7
  year: 1998
  end-page: 117
  article-title: The Anatomy of a Large‐Scale Hypertextual Web Search Engine
  publication-title: Computer Networks and ISDN Systems
– volume: 50
  start-page: 280
  issue: 2
  year: 2024
  end-page: 295
  article-title: Answering Uncertain, Under‐Specified API Queries Assisted by Knowledge‐Aware Human‐AI Dialogue
  publication-title: IEEE Transactions on Software Engineering
– start-page: 200
  year: 2018
  end-page: 210
– volume: 9
  start-page: 1735
  issue: 8
  year: 1997
  end-page: 1780
  article-title: Long Short‐Term Memory
  publication-title: Neural Computation
– volume: 323
  start-page: 533
  issue: 6088
  year: 1986
  end-page: 536
  article-title: Learning Representations by Back‐Propagating Errors
  publication-title: Nature
– year: 2020
– year: 2023
– start-page: 357
  year: 2016
  end-page: 367
– start-page: 293
  year: 2018
  end-page: 304
– year: 2017
– start-page: 349
  year: 2016
  end-page: 359
– volume: 87
  start-page: 382
  year: 2018
  end-page: 391
  article-title: Automating Smart Recommendation From Natural Language API Descriptions via Representation Learning
  publication-title: Future Generation Computer Systems
– start-page: 1
  year: 2018
  end-page: 5
– start-page: 131
  year: 2021
  end-page: 139
– start-page: 120
  year: 2019
  end-page: 130
– year: 2019
– start-page: 631
  year: 2016
  end-page: 642
– volume: 35
  start-page: 27730
  year: 2022
  ident: e_1_2_11_6_1
  article-title: Training Language Models to Follow Instructions With Human Feedback
  publication-title: Advances in Neural Information Processing Systems
– ident: e_1_2_11_7_1
  doi: 10.1109/ICSE.2015.336
– ident: e_1_2_11_13_1
– ident: e_1_2_11_41_1
– volume: 33
  start-page: 3008
  year: 2020
  ident: e_1_2_11_15_1
  article-title: Learning to Summarize With Human Feedback
  publication-title: Advances in Neural Information Processing Systems
– ident: e_1_2_11_44_1
  doi: 10.1109/ICSE-SEIP52600.2021.00022
– ident: e_1_2_11_18_1
  doi: 10.1109/TSE.2015.2500238
– ident: e_1_2_11_11_1
  doi: 10.1162/neco.1997.9.8.1735
– volume: 21
  start-page: 1
  issue: 140
  year: 2020
  ident: e_1_2_11_14_1
  article-title: Exploring the Limits of Transfer Learning With a Unified Text‐to‐Text Transformer
  publication-title: Journal of Machine Learning Research
– ident: e_1_2_11_43_1
  doi: 10.1109/ICSE48619.2023.00129
– ident: e_1_2_11_23_1
  doi: 10.1145/3196398.3196450
– ident: e_1_2_11_5_1
  doi: 10.1145/3238147.3238191
– ident: e_1_2_11_8_1
  doi: 10.1007/978-0-387-85820-3_1
– ident: e_1_2_11_21_1
– ident: e_1_2_11_46_1
  doi: 10.1145/3597503.3623306
– ident: e_1_2_11_20_1
  doi: 10.18653/v1/2020.findings-emnlp.139
– volume: 2
  start-page: 6
  issue: 4
  year: 2023
  ident: e_1_2_11_26_1
  article-title: Agentverse: Facilitating Multi‐Agent Collaboration and Exploring Emergent Behaviors in Agents
  publication-title: arXiv preprint arXiv:2308.10848
– ident: e_1_2_11_32_1
  doi: 10.1016/S0169-7552(98)00110-X
– ident: e_1_2_11_37_1
  doi: 10.1109/TSE.2023.3346954
– start-page: 24824
  volume-title: Advances in Neural Information Processing Systems
  year: 2022
  ident: e_1_2_11_25_1
– ident: e_1_2_11_27_1
– ident: e_1_2_11_38_1
  doi: 10.1109/ASE56229.2023.00075
– ident: e_1_2_11_17_1
  doi: 10.1109/SANER.2016.80
– ident: e_1_2_11_19_1
  doi: 10.1109/SANER56733.2023.00034
– ident: e_1_2_11_39_1
  doi: 10.1145/2594291.2594321
– ident: e_1_2_11_12_1
  doi: 10.1038/323533a0
– ident: e_1_2_11_24_1
  doi: 10.18653/v1/2023.emnlp-main.557
– ident: e_1_2_11_40_1
  doi: 10.1109/ICSE43902.2021.00026
– volume-title: Advances in Neural Information Processing Systems
  year: 2017
  ident: e_1_2_11_10_1
– ident: e_1_2_11_36_1
  doi: 10.1016/j.future.2018.05.006
– ident: e_1_2_11_42_1
  doi: 10.1145/3524459.3527351
– year: 2024
  ident: e_1_2_11_29_1
  article-title: Structured Chain‐of‐Thought Prompting for Code Generation
  publication-title: ACM Transactions on Software Engineering and Methodology
– ident: e_1_2_11_33_1
  doi: 10.1145/2393596.2393606
– ident: e_1_2_11_2_1
  doi: 10.1109/TSE.2022.3197063
– ident: e_1_2_11_28_1
– ident: e_1_2_11_31_1
  doi: 10.1145/1985793.1985809
– ident: e_1_2_11_30_1
  doi: 10.1145/2884781.2884808
– ident: e_1_2_11_4_1
  doi: 10.1145/2950290.2950334
– ident: e_1_2_11_9_1
  doi: 10.1145/3338906.3338971
– ident: e_1_2_11_34_1
  doi: 10.1109/TSE.2021.3053111
– ident: e_1_2_11_3_1
  doi: 10.1145/3022671.2984041
– volume-title: Elements of Survey Sampling
  year: 2013
  ident: e_1_2_11_22_1
– ident: e_1_2_11_35_1
  doi: 10.1016/j.infsof.2023.107269
– ident: e_1_2_11_45_1
  doi: 10.1145/3196321.3196334
– ident: e_1_2_11_16_1
  doi: 10.1145/2884781.2884862
SSID ssj0000620545
Score 2.3082695
Snippet ABSTRACT As software development grows increasingly complex, application programming interface (API) plays a significant role in enhancing development...
As software development grows increasingly complex, application programming interface (API) plays a significant role in enhancing development efficiency and...
SourceID proquest
crossref
wiley
SourceType Aggregation Database
Index Database
Publisher
SubjectTerms API recommendation
Application programming interface
Artificial intelligence
BIKER
chain of thought
Chatbots
ChatGPT
Datasets
empirical study
Large language models
MULAREC
Software
Software development
Title Exploring ChatGPT's Potential in Java API Method Recommendation: An Empirical Study
URI https://onlinelibrary.wiley.com/doi/abs/10.1002%2Fsmr.2765
https://www.proquest.com/docview/3160316094
Volume 37
WOSCitedRecordID wos001407016600001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVWIB
  databaseName: Wiley Online Library Full Collection 2020
  customDbUrl:
  eissn: 2047-7481
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0000620545
  issn: 2047-7473
  databaseCode: DRFUL
  dateStart: 20120101
  isFulltext: true
  titleUrlDefault: https://onlinelibrary.wiley.com
  providerName: Wiley-Blackwell
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEB609eDF-sRqlRVET7HNJs3DW6nWB7aEPqC3sNlNsIekpYkF_72zm6TVgyB4WggZEiY7u_NNZr8P4FpRfuPKJ886IUCJTEdjiDM0KkLhujRybB4osQl7MHCmU9cruirlWZicH2JdcJORodZrGeAsSJsb0tA0Xt5R22pvQxWfY5gVqD4Me5O3dYWlZVHMR2QPI5V0BJg3GyX7bIs2S_Of-9Emyfyeqqq9plf7z1vuw16RYZJOPiUOYCtMDqFWqjeQIpiPYLRuvyPdd5Y9eePblHjzTLYPof0sIa9sxUjHeyF9JTNNJFSN47CQYbonnYQ8xouZIhkhsiHx8xgmvcdx91krJBY0jsiwrZlSM8jhusSqQv5CC63IMdsBoi6T42UeBSyiJrdswS2LGUJnOAZcIM6JIkwFTqCSzJPwFIhrR0zH-LcEhrgwEMoZItSlwm4YMD0w6nBVOtpf5Ewafs6ZTH30ki-9VIdG-QX8IpZS31BK2Bbi0DrcKF__au-P-kM5nv31xnPYpVLQV9VUGlDJlh_hBezwVTZLl5fFjPoCwMDMyA
linkProvider Wiley-Blackwell
linkToHtml http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LT8JAEJ4omOhFfEYUdU2Mnip0-0RPBEFQIA2PhFuz3W0jBwoBJPHfO7u0oAcTE0-bNJ1kM93ZnW86-30At4ryG3c-edcJAUpkuhpDnKFREYpymUauwwMlNuF0Ou5wWPa24Cm9C7Pih1gX3GRkqP1aBrgsSBc3rKHz8eyBOra1DVkTV5GVgexztz5orUssJZtiQiKbGKnkI8DE2UjpZ0u0mJr_PJA2Web3XFUdNvXcv6Z5APtJjkkqq0VxCFthfAS5VL-BJOF8DL11Ax6pvrPFi9e_nxNvspANRGg_iskrWzJS8ZqkrYSmiQSr43GYCDE9kkpMauPpSNGMENmS-HkCg3qtX21oiciCxhEbWpopVYNcrku0KuRPtNCOXNMKEHeZHB_zKGARNbntCG7bzBA6wzHgApFOFGEycAqZeBKHZ0DKTsR03AFsgUEuDARzhgh1qbEbBkwPjDzcpJ72pysuDX_Fmkx99JIvvZSHQvoJ_CSa5r6htLBtRKJ5uFPO_tXe77W7cjz_64vXsNvot1t-q9l5u4A9KuV9VYWlAJnF7CO8hB2-XIzms6tkeX0BEcPQuA
linkToPdf http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1LS8NAEB60injxLdbnCqKn2GaTbhI9lWp91RK0BW9hsw_soWlpq-C_d3abVD0IgqeFkIVlsjM732T2-wBOLOU3Rj5z1wkBivZDhyPOcKhUMoqoDgORWrGJoN0OX16ieA4ui7swU36IWcHNeIaN18bB1VDqyhdr6Lg_OqcBq83Dgl-LGHrlwtVTs9ualViqjGJCYpoYqeEjwMTZK-hnq7RSTP95IH1lmd9zVXvYNFf_tcw1WMlzTFKfbop1mFPZBqwW-g0kd-dNeJ414JHGK5_cxJ2zMYkHE9NAhPN7Gbnn75zU4zvyaIWmiQGr_b7KhZguSD0j1_1hz9KMENOS-LEF3eZ1p3Hr5CILjkBsWHN8oxoUCtegVWl-oimmQ7-WIu7yBT4WOuWa-oIFUjDGPelyHFMhEelojcnANpSyQaZ2gESB5i5GACbRyaWHYM6TyjUauyrlbuqV4biwdDKccmkkU9ZkmqCVEmOlMuwXnyDJvWmceFYLmyESLcOpNfav85Pnxycz7v71xSNYiq-aSeuu_bAHy9So-9oCyz6UJqM3dQCL4n3SG48O8931CeHJ0DM
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Exploring+ChatGPT%27s+Potential+in+Java+API+Method+Recommendation%3A+An+Empirical+Study&rft.jtitle=Journal+of+software+%3A+evolution+and+process&rft.au=Wang%2C+Ye&rft.au=Xue%2C+Weihao&rft.au=Huang%2C+Qiao&rft.au=Jiang%2C+Bo&rft.date=2025-01-01&rft.pub=Wiley+Subscription+Services%2C+Inc&rft.eissn=2047-7481&rft.volume=37&rft.issue=1&rft_id=info:doi/10.1002%2Fsmr.2765&rft.externalDBID=NO_FULL_TEXT
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=2047-7473&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=2047-7473&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=2047-7473&client=summon