{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T16:48:29Z","timestamp":1783097309427,"version":"3.54.6"},"reference-count":164,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T00:00:00Z","timestamp":1754006400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000038","name":"Software Analytics Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Empir Software Eng"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s10664-025-10705-2","type":"journal-article","created":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T13:00:49Z","timestamp":1754053249000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["An Empirical Investigation on the Challenges in Scientific Workflow Systems Development"],"prefix":"10.1007","volume":"30","author":[{"given":"Khairul","family":"Alam","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Banani","family":"Roy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chanchal K.","family":"Roy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kartik","family":"Mittal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,8,1]]},"reference":[{"key":"10705_CR1","doi-asserted-by":"crossref","unstructured":"Abdellatif A, Costa D, Badran K, Abdalkareem R, Shihab E (2020) Challenges in chatbot development: a study of stack overflow posts. In: MSR. pp 174\u2013185","DOI":"10.1145\/3379597.3387472"},{"issue":"4","key":"10705_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3325097","volume":"52","author":"M Adhikari","year":"2019","unstructured":"Adhikari M, Amgoth T, Srirama SN (2019) A survey on scheduling strategies for workflows in cloud environment and emerging trends. ACM Comput Surv (CSUR) 52(4):1\u201336","journal-title":"ACM Comput Surv (CSUR)"},{"key":"10705_CR3","doi-asserted-by":"publisher","first-page":"53491","DOI":"10.1109\/ACCESS.2021.3070785","volume":"9","author":"Z Ahmad","year":"2021","unstructured":"Ahmad Z, Jehangiri AI, Ala\u2019anzy MA, Othman M, Latip R, Zaman SKU, Umar AI (2021) Scientific workflows management and scheduling in cloud computing: taxonomy, prospects, and challenges. IEEE Access 9:53491\u201353508","journal-title":"IEEE Access"},{"key":"10705_CR4","doi-asserted-by":"crossref","unstructured":"Ahmed S, Bagherzadeh M (2018) What do concurrency developers ask about? a large-scale study using stack overflow. In: Proceedings of the 12th ACM\/IEEE international symposium on empirical software engineering and measurement. pp 1\u201310","DOI":"10.1145\/3239235.3239524"},{"key":"10705_CR5","doi-asserted-by":"crossref","unstructured":"Alam K, Roy B, Roy C, Mittal K (2025) Artifact of the paper \u201cAn Empirical Investigation on the Challenges in Scientific Workflow Systems Development.\u201d. https:\/\/zenodo.org\/records\/15454588. Accessed May 2025","DOI":"10.1007\/s10664-025-10705-2"},{"key":"10705_CR6","doi-asserted-by":"publisher","unstructured":"Alam K, Roy B, Serebrenik A (2023) Reusability challenges of scientific workflows: a case study for galaxy. In: 2023 30th Asia-Pacific Software Engineering Conference (APSEC). pp 289\u2013298. https:\/\/doi.org\/10.1109\/APSEC60848.2023.00039","DOI":"10.1109\/APSEC60848.2023.00039"},{"key":"10705_CR7","doi-asserted-by":"crossref","unstructured":"Allamanis M, Sutton C (2013) Why, when, and what: analyzing stack overflow questions by topic, type, and code. In: Mining Software Repositories (MSR). IEEE, pp 53\u201356","DOI":"10.1109\/MSR.2013.6624004"},{"key":"10705_CR8","doi-asserted-by":"crossref","unstructured":"Almeida JR, Ribeiro RF, Oliveira JL (2018) A modular workflow management framework. In: HEALTHINF. pp 414\u2013421","DOI":"10.5220\/0006583104140421"},{"key":"10705_CR9","doi-asserted-by":"crossref","unstructured":"Alshangiti M, Sapkota H, Murukannaiah PK, Liu X, Yu Q (2019) Why is developing machine learning applications challenging? a study on stack overflow posts. In: International symposium on (ESEM). IEEE, pp 1\u201311","DOI":"10.1109\/ESEM.2019.8870187"},{"key":"10705_CR10","unstructured":"Amstutz, P, Crusoe MR, Tijani\u0107, N, Chapman B, Chilton J, Heuer M, Kartashov A, Leehr D, M\u00e9nager H, Nedeljkovich M, et al (2016) Common workflow language, v1. 0"},{"key":"10705_CR11","doi-asserted-by":"crossref","unstructured":"Asuncion HU, Asuncion AU, Taylor RN (2010) Software traceability with topic modeling. In: Proceedings of the 32nd ACM\/IEEE international conference on software engineering-vol 1. pp 95\u2013104","DOI":"10.1145\/1806799.1806817"},{"key":"10705_CR12","doi-asserted-by":"crossref","unstructured":"Atkinson M, Gesing S, Montagnat J, Taylor I (2017) Scientific workflows: past, present and future. Elsevier","DOI":"10.1016\/j.future.2017.05.041"},{"issue":"13","key":"10705_CR13","doi-asserted-by":"publisher","first-page":"4925","DOI":"10.3390\/s22134925","volume":"22","author":"D Atzeni","year":"2022","unstructured":"Atzeni D, Bacciu D, Mazzei D, Prencipe G (2022) A systematic review of wi-fi and machine learning integration with topic modeling techniques. Sensors 22(13):4925","journal-title":"Sensors"},{"issue":"5","key":"10705_CR14","doi-asserted-by":"publisher","first-page":"621","DOI":"10.1177\/0165551514538744","volume":"40","author":"A Bagheri","year":"2014","unstructured":"Bagheri A, Saraee M, De Jong F (2014) ADM-LDA: an aspect detection model based on topic modelling using the structure of review sentences. J Inf Sci 40(5):621\u2013636","journal-title":"J Inf Sci"},{"key":"10705_CR15","doi-asserted-by":"crossref","unstructured":"Bagherzadeh M, Khatchadourian R (2019) Going big: a large-scale study on what big data developers ask. In: Proceedings of the 2019 27th ACM joint meeting on European software engineering conference and symposium on the foundations of software engineering. pp 432\u2013442","DOI":"10.1145\/3338906.3338939"},{"key":"10705_CR16","doi-asserted-by":"crossref","unstructured":"Bajaj K, Pattabiraman K, Mesbah A (2014) Mining questions asked by web developers. In: Proceedings of the 11th working conference on mining software repositories. pp 112\u2013121","DOI":"10.1145\/2597073.2597083"},{"key":"10705_CR17","doi-asserted-by":"crossref","unstructured":"Baldini I, Castro P, Chang K, Cheng P, Fink S, Ishakian V, Mitchell N, Muthusamy V, Rabbah R, Slominski A, et al (2017) Serverless computing: Current trends and open problems. Research advances in cloud computing, 1\u201320","DOI":"10.1007\/978-981-10-5026-8_1"},{"key":"10705_CR18","doi-asserted-by":"crossref","unstructured":"Barbosa LS (2020) Software engineering for \u2018quantum advantage\u2019. In: Proceedings of the IEEE\/ACM 42nd international conference on software engineering workshops. pp 427\u2013429","DOI":"10.1145\/3387940.3392184"},{"key":"10705_CR19","doi-asserted-by":"crossref","unstructured":"Barker A, Van\u00a0Hemert J (2007) Scientific workflow: a survey and research directions. In: PPAM. Springer, pp 746\u2013753","DOI":"10.1007\/978-3-540-68111-3_78"},{"key":"10705_CR20","doi-asserted-by":"publisher","first-page":"619","DOI":"10.1007\/s10664-012-9231-y","volume":"19","author":"A Barua","year":"2014","unstructured":"Barua A, Thomas SW, Hassan AE (2014) What are developers talking about? an analysis of topics and trends in stack overflow. Empir Softw Eng 19:619\u2013654","journal-title":"Empir Softw Eng"},{"issue":"2","key":"10705_CR21","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1177\/1094428106290193","volume":"10","author":"CJ Bean","year":"2007","unstructured":"Bean CJ (2007) Qualitative research design: an interactive approach. Organ Res Methods 10(2):393","journal-title":"Organ Res Methods"},{"issue":"7","key":"10705_CR22","doi-asserted-by":"publisher","first-page":"3965","DOI":"10.1007\/s00500-022-07534-6","volume":"27","author":"RC Belwal","year":"2023","unstructured":"Belwal RC, Rai S, Gupta A (2023) Extractive text summarization using clustering-based topic modeling. Soft Comput 27(7):3965\u20133982","journal-title":"Soft Comput"},{"key":"10705_CR23","unstructured":"Ben-Kiki O, Evans C, Ingerson B (2009) YAML ain\u2019t markup language (YAML\u2122) version 1.1. Working Draft 2008 5(11)"},{"issue":"1983","key":"10705_CR24","doi-asserted-by":"publisher","first-page":"20120066","DOI":"10.1098\/rsta.2012.0066","volume":"371","author":"GB Berriman","year":"2013","unstructured":"Berriman GB, Deelman E, Juve G, Rynge M, V\u00f6ckler J-S (2013) The application of cloud computing to scientific workflows: a study of cost and performance. Phil Trans R Soc A Math Phys Eng Sci 371(1983):20120066","journal-title":"Phil Trans R Soc A Math Phys Eng Sci"},{"issue":"1","key":"10705_CR25","doi-asserted-by":"publisher","first-page":"26","DOI":"10.1145\/1656274.1656280","volume":"11","author":"MR Berthold","year":"2009","unstructured":"Berthold MR, Cebron N, Dill F, Gabriel TR, K\u00f6tter T, Meinl T, Ohl P, Thiel K, Wiswedel B (2009) KNIME-the Konstanz information miner: version 2.0 and beyond. ACM SIGKDD Explor Newsl 11(1):26\u201331","journal-title":"ACM SIGKDD Explor Newsl"},{"key":"10705_CR26","doi-asserted-by":"crossref","unstructured":"Bird S (2006) NLTK: the natural language toolkit. In: Proceedings of the COLING\/ACL 2006 interactive presentation sessions. pp 69\u201372","DOI":"10.3115\/1225403.1225421"},{"issue":"5","key":"10705_CR27","doi-asserted-by":"publisher","first-page":"723","DOI":"10.1002\/(SICI)1097-0258(20000315)19:5<723::AID-SIM379>3.0.CO;2-A","volume":"19","author":"NJ-M Blackman","year":"2000","unstructured":"Blackman NJ-M, Koval JJ (2000) Interval estimation for Cohen\u2019s kappa as a measure of agreement. Stat Med 19(5):723\u2013741","journal-title":"Stat Med"},{"key":"10705_CR28","doi-asserted-by":"crossref","unstructured":"Blei DM, Lafferty JD (2006b) Dynamic topic models. In: Proceedings of the 23rd international conference on machine learning. pp 113\u2013120","DOI":"10.1145\/1143844.1143859"},{"key":"10705_CR29","first-page":"993","volume":"3","author":"DM Blei","year":"2003","unstructured":"Blei DM, Ng AY, Jordan MI (2003) Latent Dirichlet allocation. J Mach Learn Res 3:993\u20131022","journal-title":"J Mach Learn Res"},{"key":"10705_CR30","first-page":"147","volume":"18","author":"D Blei","year":"2006","unstructured":"Blei D, Lafferty J (2006) Correlated topic models. Adv Neural Inf Process Syst 18:147","journal-title":"Adv Neural Inf Process Syst"},{"issue":"1","key":"10705_CR31","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1145\/2723872.2723882","volume":"49","author":"C Boettiger","year":"2015","unstructured":"Boettiger C (2015) An introduction to docker for reproducible research. ACM SIGOPS Oper Syst Rev 49(1):71\u201379","journal-title":"ACM SIGOPS Oper Syst Rev"},{"key":"10705_CR32","first-page":"19","volume":"1","author":"S Bowers","year":"2012","unstructured":"Bowers S (2012) Scientific workflow, provenance, and data modeling challenges and approaches. JoDS 1:19\u201330","journal-title":"JoDS"},{"key":"10705_CR33","doi-asserted-by":"crossref","unstructured":"Campbell JC, Hindle A, Stroulia E (2015) Latent Dirichlet allocation: extracting topics from software engineering data. In: The Art and science of analyzing software data. Elsevier, pp 139\u2013159","DOI":"10.1016\/B978-0-12-411519-4.00006-9"},{"key":"10705_CR34","doi-asserted-by":"crossref","unstructured":"Carver JC, Kendall RP, Squires SE, Post DE (2007) Software development environments for scientific and engineering software: a series of case studies. In: 29th International Conference on Software Engineering (ICSE\u201907). IEEE, pp 550\u2013559","DOI":"10.1109\/ICSE.2007.77"},{"issue":"6","key":"10705_CR35","doi-asserted-by":"publisher","first-page":"864","DOI":"10.1109\/TSE.2009.42","volume":"35","author":"M Cataldo","year":"2009","unstructured":"Cataldo M, Mockus A, Roberts JA, Herbsleb JD (2009) Software dependencies, work dependencies, and their impact on failures. IEEE Trans Software Eng 35(6):864\u2013878","journal-title":"IEEE Trans Software Eng"},{"issue":"19","key":"10705_CR36","doi-asserted-by":"publisher","first-page":"3815","DOI":"10.1093\/bioinformatics\/btz133","volume":"35","author":"A Cervera","year":"2019","unstructured":"Cervera A, Rantanen V, Ovaska K, Laakso M, Nunez-Fontarnau J, Alkodsi A, Casado J, Facciotto C, H\u00e4kkinen A, Louhimo R et al (2019) Anduril 2: upgraded large-scale data integration framework. Bioinformatics 35(19):3815\u20133817","journal-title":"Bioinformatics"},{"key":"10705_CR37","doi-asserted-by":"crossref","unstructured":"Chen T-H, Thomas SW, Nagappan M, Hassan AE (2012) Explaining software defects using topic models. In: 2012 9th IEEE working conference on mining software repositories (MSR). IEEE, pp 189\u2013198","DOI":"10.1109\/MSR.2012.6224280"},{"key":"10705_CR38","doi-asserted-by":"publisher","first-page":"1843","DOI":"10.1007\/s10664-015-9402-8","volume":"21","author":"T-H Chen","year":"2016","unstructured":"Chen T-H, Thomas SW, Hassan AE (2016) A survey on the use of topic models when mining software repositories. Empir Softw Eng 21:1843\u20131919","journal-title":"Empir Softw Eng"},{"key":"10705_CR39","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1016\/j.jss.2019.07.033","volume":"156","author":"H Chen","year":"2019","unstructured":"Chen H, Coogle J, Damevski K (2019) Modeling stack overflow tags and topics as a hierarchy of concepts. J Syst Softw 156:283\u2013299","journal-title":"J Syst Softw"},{"issue":"2","key":"10705_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2846092","volume":"34","author":"Z Cheng","year":"2016","unstructured":"Cheng Z, Shen J (2016) On effective location-aware music recommendation. ACM Trans Inf Syst (TOIS) 34(2):1\u201332","journal-title":"ACM Trans Inf Syst (TOIS)"},{"key":"10705_CR41","doi-asserted-by":"crossref","unstructured":"Chirigati F, Rampin R, Shasha D, Freire J (2016) Reprozip: computational reproducibility with ease. In: Proceedings of the 2016 international conference on management of data. pp 2085\u20132088","DOI":"10.1145\/2882903.2899401"},{"issue":"1","key":"10705_CR42","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1093\/bioinformatics\/btu595","volume":"31","author":"P Cingolani","year":"2015","unstructured":"Cingolani P, Sladek R, Blanchette M (2015) Bigdatascript: a scripting language for data pipelines. Bioinformatics 31(1):10\u201316","journal-title":"Bioinformatics"},{"key":"10705_CR43","unstructured":"community (2024) Workflow systems. https:\/\/workflows.community\/systems. Accessed Jan 2024"},{"issue":"W1","key":"10705_CR44","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1093\/nar\/gkac247","volume":"50","author":"Galaxy Community","year":"2022","unstructured":"Community Galaxy (2022) The galaxy platform for accessible, reproducible and collaborative biomedical analyses: 2022 update. Nucleic Acids Res 50(W1):345\u2013351","journal-title":"Nucleic Acids Res"},{"key":"10705_CR45","unstructured":"cwl (2024) Existing workflow systems. https:\/\/github.com\/common-workflow-language\/common-workflow-language\/wiki\/Existing-Workflow-systems. Accessed Jan 2024"},{"key":"10705_CR46","doi-asserted-by":"crossref","unstructured":"Dabbish L, Stuart C, Tsay J, Herbsleb J (2012) Social coding in Github: transparency and collaboration in an open software repository. In: Proceedings of the ACM 2012 conference on computer supported cooperative work. pp 1277\u20131286","DOI":"10.1145\/2145204.2145396"},{"key":"10705_CR47","doi-asserted-by":"crossref","unstructured":"Davidson SB, Freire J (2008) Provenance and scientific workflows: challenges and opportunities. In: ACM SIGMOD. pp 1345\u20131350","DOI":"10.1145\/1376616.1376772"},{"key":"10705_CR48","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1016\/j.future.2014.10.008","volume":"46","author":"E Deelman","year":"2015","unstructured":"Deelman E, Vahi K, Juve G, Rynge M, Callaghan S, Maechling PJ, Mayani R, Chen W, Da Silva RF, Livny M et al (2015) Pegasus, a workflow management system for science automation. Futur Gener Comput Syst 46:17\u201335","journal-title":"Futur Gener Comput Syst"},{"issue":"6","key":"10705_CR49","doi-asserted-by":"publisher","first-page":"1128","DOI":"10.1177\/1094342019852127","volume":"33","author":"E Deelman","year":"2019","unstructured":"Deelman E, Mandal A, Jiang M, Sakellariou R (2019) The role of machine learning in scientific workflows. Int J High Perform Comput Appl 33(6):1128\u20131139","journal-title":"Int J High Perform Comput Appl"},{"key":"10705_CR50","doi-asserted-by":"crossref","unstructured":"Dhasade AB, Venigalla ASM, Chimalakonda S (2020) Towards prioritizing Github issues. In: Proceedings of the 13th innovations in software engineering conference on formerly known as India software engineering conference. pp 1\u20135","DOI":"10.1145\/3385032.3385052"},{"issue":"4","key":"10705_CR51","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1038\/nbt.3820","volume":"35","author":"P Di Tommaso","year":"2017","unstructured":"Di Tommaso P, Chatzou M, Floden EW, Barja PP, Palumbo E, Notredame C (2017) Nextflow enables reproducible computational workflows. Nat Biotechnol 35(4):316\u2013319","journal-title":"Nat Biotechnol"},{"key":"10705_CR52","doi-asserted-by":"crossref","unstructured":"Doi T, Isonuma M, Yanaka H (2024) Topic modeling for short texts with large language models. In: Proceedings of the 62nd annual meeting of the association for computational linguistics (vol 4: Student Research Workshop). pp 21\u201333","DOI":"10.18653\/v1\/2024.acl-srw.3"},{"key":"10705_CR53","doi-asserted-by":"crossref","unstructured":"Duboc L, Rosenblum D, Wicks T (2007) A framework for characterization and analysis of software system scalability. In: Proceedings of the the 6th Joint meeting of the European software engineering conference and the ACM SIGSOFT symposium on the foundations of software engineering. pp 375\u2013384","DOI":"10.1145\/1287624.1287679"},{"key":"10705_CR54","unstructured":"Eidelman V, Boyd-Graber J., Resnik P (2012) Topic models for dynamic translation model adaptation. In: Proceedings of the 50th annual meeting of the association for computational linguistics (vol 2: Short Papers). pp 115\u2013119"},{"key":"10705_CR55","doi-asserted-by":"crossref","unstructured":"Ewels P, Krueger F, K\u00e4ller M, Andrews S (2016) Cluster flow: a user-friendly bioinformatics workflow tool. F1000Research 5","DOI":"10.12688\/f1000research.10335.1"},{"key":"10705_CR56","unstructured":"Exchange S (2024) Stack exchange data explorer. https:\/\/data.stackexchange.com\/. Accessed 31 Jan 2024"},{"key":"10705_CR57","unstructured":"Face H (2024) Hugging face model Hub. https:\/\/huggingface.co\/docs\/hub\/en\/models-the-hub. Accessed Aug 2024"},{"issue":"2","key":"10705_CR58","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1109\/TSC.2013.27","volume":"9","author":"H Fern\u00e1ndez","year":"2013","unstructured":"Fern\u00e1ndez H, Tedeschi C, Priol T (2013) A chemistry-inspired workflow management system for decentralizing workflow execution. IEEE Trans Serv Comput 9(2):213\u2013226","journal-title":"IEEE Trans Serv Comput"},{"key":"10705_CR59","doi-asserted-by":"crossref","unstructured":"Fiscus JG, Doddington GR (2002) Topic detection and tracking evaluation overview. In: Topic detection and tracking: event-based information organization. Springer, pp 17\u201331","DOI":"10.1007\/978-1-4615-0933-2_2"},{"key":"10705_CR60","doi-asserted-by":"crossref","unstructured":"Foster I, Zhao Y, Raicu I, Lu S (2008) Cloud computing and grid computing 360-degree compared. In: 2008 Grid computing environments workshop. IEEE, pp 1\u201310","DOI":"10.1109\/GCE.2008.4738445"},{"key":"10705_CR61","doi-asserted-by":"publisher","first-page":"271","DOI":"10.1016\/j.future.2017.01.008","volume":"75","author":"D Garijo","year":"2017","unstructured":"Garijo D, Gil Y, Corcho O (2017) Abstract, link, publish, exploit: an end to end framework for workflow sharing. Futur Gener Comput Syst 75:271\u2013283","journal-title":"Futur Gener Comput Syst"},{"key":"10705_CR62","doi-asserted-by":"crossref","unstructured":"Gethers, M., Poshyvanyk, D (2010) Using relational topic models to capture coupling among classes in object-oriented software systems. In: 2010 IEEE international conference on software maintenance. IEEE, pp 1\u201310","DOI":"10.1109\/ICSM.2010.5609687"},{"issue":"10","key":"10705_CR63","doi-asserted-by":"publisher","first-page":"1451","DOI":"10.1101\/gr.4086505","volume":"15","author":"B Giardine","year":"2005","unstructured":"Giardine B, Riemer C, Hardison RC, Burhans R, Elnitski L, Shah P, Zhang Y, Blankenberg D, Albert I, Taylor J et al (2005) Galaxy: a platform for interactive large-scale genome analysis. Genome Res 15(10):1451\u20131455","journal-title":"Genome Res"},{"issue":"12","key":"10705_CR64","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1109\/MC.2007.421","volume":"40","author":"Y Gil","year":"2007","unstructured":"Gil Y, Deelman E, Ellisman M, Fahringer T, Fox G, Gannon D, Goble C, Livny M, Moreau L, Myers J (2007) Examining the challenges of scientific workflows. Computer 40(12):24\u201332","journal-title":"Computer"},{"key":"10705_CR65","unstructured":"github (2024) GitHub REST API. https:\/\/docs.github.com\/en\/rest?apiVersion=2022-11-28. Jan 2024"},{"key":"10705_CR66","doi-asserted-by":"publisher","unstructured":"Gokcimen T, Das B (2024) Topic modelling using BERTopic for robust spam detection. In: 2024 12th international symposium on digital forensics and security (ISDFS). pp 1\u20135. https:\/\/doi.org\/10.1109\/ISDFS60797.2024.10527342","DOI":"10.1109\/ISDFS60797.2024.10527342"},{"key":"10705_CR67","unstructured":"Grootendorst M (2022) BERTopic: neural topic modeling with a class-based TF-IDF procedure. arXiv:2203.05794"},{"key":"10705_CR68","doi-asserted-by":"crossref","unstructured":"Gu Y, Cao J, Guo Y, Qian S, Guan W (2023) Plan, generate and match: scientific workflow recommendation with large language models. In: International conference on service-oriented computing. Springer, pp 86\u2013102","DOI":"10.1007\/978-3-031-48421-6_7"},{"issue":"1","key":"10705_CR69","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1147\/sj.411.0004","volume":"41","author":"B Hailpern","year":"2002","unstructured":"Hailpern B, Santhanam P (2002) Software debugging, testing, and verification. IBM Syst J 41(1):4\u201312","journal-title":"IBM Syst J"},{"key":"10705_CR70","doi-asserted-by":"publisher","first-page":"2694","DOI":"10.1007\/s10664-020-09819-6","volume":"25","author":"J Han","year":"2020","unstructured":"Han J, Shihab E, Wan Z, Deng S, Xia X (2020) What do programmers discuss about deep learning frameworks. Empir Softw Eng 25:2694\u20132747","journal-title":"Empir Softw Eng"},{"key":"10705_CR71","doi-asserted-by":"crossref","unstructured":"Hendrix V, Fox J, Ghoshal D, Ramakrishnan L (2016) Tigres workflow library: supporting scientific pipelines on HPC systems. In: 2016 16th IEEE\/ACM international symposium on cluster, cloud and grid computing (CCGrid). IEEE, pp 146\u2013155","DOI":"10.1109\/CCGrid.2016.54"},{"key":"10705_CR72","unstructured":"Hochstein L, Moser R (2017) Ansible: up and running: automating configuration management and deployment the easy way. \u201c\u2019Reilly Media, Inc.\u201d"},{"key":"10705_CR73","first-page":"87","volume":"3","author":"E Jaeger","year":"2005","unstructured":"Jaeger E, Altintas I, Zhang J, Lud\u00e4scher B, Pennington D, Michener W (2005) A scientific workflow approach to distributed geospatial data processing using web services. SSDBM 3:87\u201390","journal-title":"SSDBM"},{"issue":"20","key":"10705_CR74","doi-asserted-by":"publisher","first-page":"2907","DOI":"10.1093\/bioinformatics\/btr478","volume":"27","author":"B Jagla","year":"2011","unstructured":"Jagla B, Wiswedel B, Copp\u00e9e J-Y (2011) Extending KNIME for next-generation sequencing data analysis. Bioinformatics 27(20):2907\u20132909","journal-title":"Bioinformatics"},{"issue":"17","key":"10705_CR75","doi-asserted-by":"publisher","first-page":"5037","DOI":"10.1002\/cpe.3505","volume":"27","author":"A Jain","year":"2015","unstructured":"Jain A, Ong SP, Chen W, Medasani B, Qu X, Kocher M, Brafman M, Petretto G, Rignanese G-M, Hautier G et al (2015) Fireworks: a dynamic workflow system designed for high-throughput applications. Concurr Comput Pract Experience 27(17):5037\u20135059","journal-title":"Concurr Comput Pract Experience"},{"key":"10705_CR76","doi-asserted-by":"publisher","first-page":"15169","DOI":"10.1007\/s11042-018-6894-4","volume":"78","author":"H Jelodar","year":"2019","unstructured":"Jelodar H, Wang Y, Yuan C, Feng X, Jiang X, Li Y, Zhao L (2019) Latent Dirichlet allocation (LDA) and topic modeling: models, applications, a survey. Multimed Tools Appl 78:15169\u201315211","journal-title":"Multimed Tools Appl"},{"key":"10705_CR77","doi-asserted-by":"crossref","unstructured":"Jimenez I, Sevilla M, Watkins N, Maltzahn C, Lofstead J, Mohror K, Arpaci-Dusseau A, Arpaci-Dusseau R (2017) The popper convention: making reproducible systems evaluation practical. In: 2017 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW). IEEE, pp 1561\u20131570","DOI":"10.1109\/IPDPSW.2017.157"},{"key":"10705_CR78","unstructured":"Jokhio M (2021) Mining Github issues for bugs, feature requests and questions.\u201d"},{"key":"10705_CR79","doi-asserted-by":"crossref","unstructured":"Jo Y, Oh AH (2011) Aspect and sentiment unification model for online review analysis. In: Proceedings of the Fourth ACM international conference on web search and data mining. pp 815\u2013824","DOI":"10.1145\/1935826.1935932"},{"issue":"3","key":"10705_CR80","first-page":"14","volume":"16","author":"G Juve","year":"2010","unstructured":"Juve G, Deelman E (2010) Scientific workflows and clouds. XRDS: crossroads. ACM Mag Stud 16(3):14\u201318","journal-title":"ACM Mag Stud"},{"key":"10705_CR81","doi-asserted-by":"publisher","unstructured":"Kang W, Kim Y, Kim H, Lee J (2023) An analysis of research trends on language model using BERTopic. In: 2023 congress in computer science, computer engineering, and applied computing (CSCE). pp 168\u2013172. https:\/\/doi.org\/10.1109\/CSCE60160.2023.00032","DOI":"10.1109\/CSCE60160.2023.00032"},{"key":"10705_CR82","doi-asserted-by":"publisher","first-page":"59","DOI":"10.1016\/j.is.2013.11.003","volume":"42","author":"Y Kim","year":"2014","unstructured":"Kim Y, Shim K (2014) TWILITE: a recommendation system for Twitter using a probabilistic model based on latent Dirichlet allocation. Inf Syst 42:59\u201377","journal-title":"Inf Syst"},{"key":"10705_CR83","first-page":"121","volume":"6","author":"AD Kiran","year":"2023","unstructured":"Kiran AD, Ay MC, Allmer J (2023) Criteria for the evaluation of workflow management systems for scientific data analysis. J Bioinform Syst Biol 6:121\u2013133","journal-title":"J Bioinform Syst Biol"},{"issue":"6","key":"10705_CR84","doi-asserted-by":"publisher","first-page":"068","DOI":"10.1093\/gigascience\/giaa068","volume":"9","author":"M Kluge","year":"2020","unstructured":"Kluge M, Friedl MS, Menzel AL, Friedel CC (2020) Watchdog 2.0: new developments for reusability, reproducibility, and workflow execution. GigaScience 9(6):068","journal-title":"GigaScience"},{"issue":"19","key":"10705_CR85","doi-asserted-by":"publisher","first-page":"2520","DOI":"10.1093\/bioinformatics\/bts480","volume":"28","author":"J K\u00f6ster","year":"2012","unstructured":"K\u00f6ster J, Rahmann S (2012) Snakemake-a scalable bioinformatics workflow engine. Bioinformatics 28(19):2520\u20132522","journal-title":"Bioinformatics"},{"issue":"7","key":"10705_CR86","doi-asserted-by":"publisher","first-page":"084","DOI":"10.1093\/gigascience\/giz084","volume":"8","author":"M Kotliar","year":"2019","unstructured":"Kotliar M, Kartashov AV, Barski A (2019) CWL-airflow: a lightweight pipeline manager supporting common workflow language. GigaScience 8(7):084","journal-title":"GigaScience"},{"issue":"5","key":"10705_CR87","doi-asserted-by":"publisher","first-page":"044","DOI":"10.1093\/gigascience\/giz044","volume":"8","author":"S Lampa","year":"2019","unstructured":"Lampa S, Dahl\u00f6 M, Alvarsson J, Spjuth O (2019) SciPipe: a workflow library for agile development of complex and dynamic bioinformatics pipelines. GigaScience 8(5):044","journal-title":"GigaScience"},{"issue":"2\u20133","key":"10705_CR88","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1080\/01638539809545028","volume":"25","author":"TK Landauer","year":"1998","unstructured":"Landauer TK, Foltz PW, Laham D (1998) An introduction to latent semantic analysis. Discourse Process 25(2\u20133):259\u2013284","journal-title":"Discourse Process"},{"key":"10705_CR89","unstructured":"Lee D, Seung HS (2000) Algorithms for non-negative matrix factorization. Advances in neural information processing systems, 13"},{"issue":"3","key":"10705_CR90","first-page":"0116781","volume":"10","author":"Z Li","year":"2015","unstructured":"Li Z, Yang C, Jin B, Yu M, Liu K, Sun M, Zhan M (2015) Enabling big geoscience data analytics with a cloud-based, MapReduce-enabled and service-oriented workflow framework. PLoS ONE 10(3):0116781","journal-title":"PLoS ONE"},{"issue":"4","key":"10705_CR91","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3012429","volume":"49","author":"CS Liew","year":"2016","unstructured":"Liew CS, Atkinson MP, Galea M, Ang TF, Martin P, Hemert JIV (2016) Scientific workflows: moving across paradigms. ACM Comput Surv (CSUR) 49(4):1\u201339","journal-title":"ACM Comput Surv (CSUR)"},{"key":"10705_CR92","doi-asserted-by":"crossref","unstructured":"Li H, Khomh F, Openja M, et al (2021) Understanding quantum software engineering challenges an empirical study on stack exchange forums and Github issues. In: ICSME. IEEE, pp 343\u2013354","DOI":"10.1109\/ICSME52107.2021.00037"},{"key":"10705_CR93","first-page":"79","volume":"2","author":"C Lin","year":"2009","unstructured":"Lin C, Lu S, Fei X, Chebotko A, Pai D, Lai Z, Fotouhi F, Hua J (2009) A reference architecture for scientific workflow management systems and the VIEW SOA solution. IEEE TSC 2:79\u201392","journal-title":"IEEE TSC"},{"key":"10705_CR94","doi-asserted-by":"crossref","unstructured":"Linstead E, Lopes C, Baldi P (2008) An application of latent Dirichlet allocation to analyzing software evolution. In: 2008 seventh international conference on machine learning and applications. IEEE, pp 813\u2013818","DOI":"10.1109\/ICMLA.2008.47"},{"key":"10705_CR95","doi-asserted-by":"crossref","unstructured":"Linstead E, Rigor P, Bajracharya S, Lopes C, Baldi P (2007) Mining concepts from code with probabilistic topic models. In: Proceedings of the 22nd IEEE\/ACM international conference on automated software engineering. pp 461\u2013464","DOI":"10.1145\/1321631.1321709"},{"key":"10705_CR96","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1007\/s10723-015-9329-8","volume":"13","author":"J Liu","year":"2015","unstructured":"Liu J, Pacitti E, Valduriez P, Mattoso M (2015) A survey of data-intensive scientific workflow management. J Grid Comput 13:457\u2013493","journal-title":"J Grid Comput"},{"issue":"3","key":"10705_CR97","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/MIS.2015.20","volume":"30","author":"H-M Lu","year":"2015","unstructured":"Lu H-M, Lee C-H (2015) A twitter hashtag recommendation model that accommodates for temporal clustering effects. IEEE Intell Syst 30(3):18\u201325","journal-title":"IEEE Intell Syst"},{"issue":"9","key":"10705_CR98","doi-asserted-by":"publisher","first-page":"972","DOI":"10.1016\/j.infsof.2010.04.002","volume":"52","author":"SK Lukins","year":"2010","unstructured":"Lukins SK, Kraft NA, Etzkorn LH (2010) Bug localization using latent Dirichlet allocation. Inf Softw Technol 52(9):972\u2013990","journal-title":"Inf Softw Technol"},{"key":"10705_CR99","unstructured":"Luostarinen T, Kohonen O (2013) Using topic models in content-based news recommender systems. In: Proceedings of the 19th Nordic conference of computational linguistics (NODALIDA 2013). pp 239\u2013251"},{"key":"10705_CR100","doi-asserted-by":"crossref","unstructured":"Mamykina L, Manoim B, Mittal M, Hripcsak G, Hartmann B (2011) Design lessons from the fastest Q &A site in the west. In: Proceedings of the SIGCHI conference on human factors in computing systems. pp 2857\u20132866","DOI":"10.1145\/1978942.1979366"},{"key":"10705_CR101","doi-asserted-by":"publisher","unstructured":"Mankolli E (2022) Reducing the complexity of candidate selection using natural language processing. In: 2022 29th international conference on systems, signals and image processing (IWSSIP), vol. CFP2255E-ART. pp 1\u20134. https:\/\/doi.org\/10.1109\/IWSSIP55020.2022.9854488","DOI":"10.1109\/IWSSIP55020.2022.9854488"},{"issue":"3","key":"10705_CR102","doi-asserted-by":"publisher","first-page":"480","DOI":"10.1109\/TSC.2016.2589243","volume":"11","author":"F Marozzo","year":"2016","unstructured":"Marozzo F, Talia D, Trunfio P (2016) A workflow management system for scalable data mining on clouds. IEEE Trans Serv Comput 11(3):480\u2013492","journal-title":"IEEE Trans Serv Comput"},{"issue":"3","key":"10705_CR103","doi-asserted-by":"publisher","first-page":"276","DOI":"10.11613\/BM.2012.031","volume":"22","author":"ML McHugh","year":"2012","unstructured":"McHugh ML (2012) Interrater reliability: the kappa statistic. Biochemia Medica 22(3):276\u2013282","journal-title":"Biochemia Medica"},{"issue":"11","key":"10705_CR104","doi-asserted-by":"publisher","first-page":"205","DOI":"10.21105\/joss.00205","volume":"2","author":"L McInnes","year":"2017","unstructured":"McInnes L, Healy J, Astels S et al (2017) HDBSCAN: hierarchical density based clustering. J Open Source Softw 2(11):205","journal-title":"J Open Source Softw"},{"key":"10705_CR105","doi-asserted-by":"crossref","unstructured":"McInnes L, Healy J, Melville J (2018) UMAP: uniform manifold approximation and projection for dimension reduction. arXiv:1802.03426","DOI":"10.21105\/joss.00861"},{"key":"10705_CR106","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1016\/j.future.2008.06.013","volume":"25","author":"T McPhillips","year":"2009","unstructured":"McPhillips T, Bowers S, Zinn D, Lud\u00e4scher B (2009) Scientific workflow design for mere mortals. FGCS 25:541\u2013551","journal-title":"FGCS"},{"key":"10705_CR107","doi-asserted-by":"publisher","unstructured":"Mi Q, Bao Q, Cui L (2023) Identifying topics and trends in devops: a study of stack overflow posts. In: 2023 49th Euromicro Conference on Software Engineering and Advanced Applications (SEAA). pp 402\u2013409. https:\/\/doi.org\/10.1109\/SEAA60479.2023.00067","DOI":"10.1109\/SEAA60479.2023.00067"},{"key":"10705_CR108","doi-asserted-by":"crossref","unstructured":"M\u00f6lder F, Jablonski KP, Letcher B, Hall MB, Tomkins-Tinch CH, Sochat V, Forster J, Lee S, Twardziok SO, Kanitz A, et al (2021) Sustainable data analysis with snakemake. F1000Research. 10","DOI":"10.12688\/f1000research.29032.2"},{"key":"10705_CR109","doi-asserted-by":"crossref","unstructured":"Mork R, Martin P, Zhao Z (2015) Contemporary challenges for data-intensive scientific workflow management systems. In: Proceedings of the 10th workshop on workflows in support of large-scale science. pp 1\u201311","DOI":"10.1145\/2822332.2822336"},{"key":"10705_CR110","unstructured":"myExperiment (2024) myExperiment Workflows. https:\/\/www.myexperiment.org\/workflows. Accessed Jan 2024"},{"key":"10705_CR111","doi-asserted-by":"publisher","first-page":"25138","DOI":"10.1109\/ACCESS.2019.2899985","volume":"7","author":"F Nadeem","year":"2019","unstructured":"Nadeem F, Alghazzawi D, Mashat A, Faqeeh K, Almalaise A (2019) Using machine learning ensemble methods to predict execution time of e-science workflows in heterogeneous distributed systems. IEEE Access 7:25138\u201325149","journal-title":"IEEE Access"},{"key":"10705_CR112","doi-asserted-by":"crossref","unstructured":"Nadi S, Kr\u00fcger S, Mezini M, Bodden E (2016) Jumping through hoops: why do Java developers struggle with cryptography APIs? In: Proceedings of the 38th international conference on software engineering. pp 935\u2013946","DOI":"10.1145\/2884781.2884790"},{"issue":"6","key":"10705_CR113","doi-asserted-by":"publisher","first-page":"1186","DOI":"10.1109\/TKDE.2017.2669982","volume":"29","author":"L Nie","year":"2017","unstructured":"Nie L, Wei X, Zhang D, Wang X, Gao Z, Yang Y (2017) Data-driven answer selection in community QA systems. IEEE Trans Knowl Data Eng 29(6):1186\u20131198","journal-title":"IEEE Trans Knowl Data Eng"},{"key":"10705_CR114","unstructured":"Nouri A, Davis PE, Subedi P, Parashar M (2021) Exploring the role of machine learning in scientific workflows: opportunities and challenges. arXiv:2110.13999"},{"issue":"17","key":"10705_CR115","doi-asserted-by":"publisher","first-page":"3045","DOI":"10.1093\/bioinformatics\/bth361","volume":"20","author":"T Oinn","year":"2004","unstructured":"Oinn T, Addis M, Ferris J, Marvin D, Senger M, Greenwood M, Carver T, Glover K, Pocock MR, Wipat A et al (2004) Taverna: a tool for the composition and enactment of bioinformatics workflows. Bioinformatics 20(17):3045\u20133054","journal-title":"Bioinformatics"},{"key":"10705_CR116","doi-asserted-by":"crossref","unstructured":"Olabarriaga S, Pierantoni G, Taffoni G, Sciacca E, Jaghoori M, Korkhov V, Castelli G, Vuerli C, Becciani U, Carley E, et al (2014) Scientific workflow management\u2013for whom? In: 2014 IEEE 10th International conference on e-science, vol 1. IEEE, pp 298\u2013305","DOI":"10.1109\/eScience.2014.8"},{"key":"10705_CR117","doi-asserted-by":"crossref","unstructured":"Openja M, Adams B, Khomh F (2020) Analysis of modern release engineering topics:\u2013a large-scale study using stackoverflow\u2013. In: 2020 IEEE International Conference on Software Maintenance and Evolution (ICSME). IEEE, pp 104\u2013114","DOI":"10.1109\/ICSME46990.2020.00020"},{"issue":"8","key":"10705_CR118","doi-asserted-by":"publisher","first-page":"2572","DOI":"10.1093\/bioinformatics\/btz956","volume":"36","author":"S Pal","year":"2020","unstructured":"Pal S, Przytycka TM (2020) Bioinformatics pipeline using JUDI: Just Do It! Bioinformatics 36(8):2572\u20132574","journal-title":"Bioinformatics"},{"key":"10705_CR119","doi-asserted-by":"publisher","unstructured":"Parlina, A., Maryati, I (2023) Leveraging bertopic for the analysis of scientific papers on seaweed. In: 2023 international conference on computer, control, informatics and its applications (IC3INA). p 279\u2013283. https:\/\/doi.org\/10.1109\/IC3INA60834.2023.10285737","DOI":"10.1109\/IC3INA60834.2023.10285737"},{"key":"10705_CR120","unstructured":"pditommaso (2024) Workflow systems. https:\/\/github.com\/pditommaso\/awesome-pipeline. Accessed Jan 2024"},{"key":"10705_CR121","doi-asserted-by":"crossref","unstructured":"Procko T, Davidoff A, Elvira T, Ochoa O (2023) Towards improved scientific knowledge proliferation: Leveraging large language models on the traditional scientific writing workflow. Available at SSRN 4594836","DOI":"10.2139\/ssrn.4594836"},{"key":"10705_CR122","doi-asserted-by":"publisher","first-page":"010","DOI":"10.1093\/database\/bas010","volume":"2012","author":"R Rak","year":"2012","unstructured":"Rak R, Rowley A, Black W, Ananiadou S (2012) Argo: an integrative, interactive, text mining-based workbench supporting curation. Database 2012:010","journal-title":"Database"},{"key":"10705_CR123","doi-asserted-by":"crossref","unstructured":"Rocklin M, et al (2015) Dask: parallel computation with blocked algorithms and task scheduling. In: SciPy. pp 126\u2013132","DOI":"10.25080\/Majora-7b98e3ed-013"},{"key":"10705_CR124","doi-asserted-by":"crossref","unstructured":"Rosen C, Shihab E (2016) What are mobile developers asking about? a large scale study using stack overflow. ESE 21","DOI":"10.1007\/s10664-015-9379-3"},{"issue":"11","key":"10705_CR125","doi-asserted-by":"publisher","first-page":"1525","DOI":"10.1093\/bioinformatics\/bts167","volume":"28","author":"SP Sadedin","year":"2012","unstructured":"Sadedin SP, Pope B, Oshlack A (2012) Bpipe: a tool for running and managing bioinformatics pipelines. Bioinformatics 28(11):1525\u20131526","journal-title":"Bioinformatics"},{"key":"10705_CR126","unstructured":"Salim MA, Uram TD, Childers JT, Balaprakash P, Vishwanath V, Papka ME (2019) Balsam: automated scheduling and execution of dynamic, data-intensive HPC workflows. arXiv:1909.08704"},{"key":"10705_CR127","doi-asserted-by":"publisher","first-page":"030","DOI":"10.1093\/gigascience\/giae030","volume":"13","author":"M S\u00e4nger","year":"2024","unstructured":"S\u00e4nger M, De Mecquenem N, Lewi\u0144ska KE, Bountris V, Lehmann F, Leser U, Kosch T (2024) A qualitative assessment of using ChatGPT as large language model for scientific workflow development. GigaScience 13:030","journal-title":"GigaScience"},{"issue":"1","key":"10705_CR128","first-page":"243180","volume":"2015","author":"I Santana-Perez","year":"2015","unstructured":"Santana-Perez I, P\u00e9rez-Hern\u00e1ndez MS (2015) Towards reproducibility in scientific workflows: an infrastructure-based approach. Sci Program 2015(1):243180","journal-title":"Sci Program"},{"key":"10705_CR129","doi-asserted-by":"crossref","unstructured":"Savage T, Dit B, Gethers M, Poshyvanyk D (2010) Topic xp: Exploring topics in source code using latent Dirichlet allocation. In: 2010 IEEE international conference on software maintenance. IEEE, pp 1\u20136","DOI":"10.1109\/ICSM.2010.5609654"},{"key":"10705_CR130","doi-asserted-by":"crossref","unstructured":"Scoccia GL, Migliarini P, Autili M (2021) Challenges in developing desktop web apps: a study of stack overflow and Github. In: 2021 IEEE\/ACM 18th international conference on mining software repositories (MSR). IEEE, pp 271\u2013282","DOI":"10.1109\/MSR52588.2021.00039"},{"key":"10705_CR131","doi-asserted-by":"publisher","first-page":"256","DOI":"10.1016\/j.future.2017.01.001","volume":"75","author":"RJ Sethi","year":"2017","unstructured":"Sethi RJ, Gil Y (2017) Scientific workflows in data analysis: bridging expertise across multiple domains. Futur Gener Comput Syst 75:256\u2013270","journal-title":"Futur Gener Comput Syst"},{"key":"10705_CR132","unstructured":"Snakemake (2024) SnakeMake Workflows. https:\/\/nf-co.re\/. Accessed Jan 2024"},{"key":"10705_CR133","doi-asserted-by":"crossref","unstructured":"Souza CR, Redmiles DF (2008) An empirical study of software developers\u2019 management of dependencies and changes. In: Proceedings of the 30th international conference on software engineering. pp 241\u2013250","DOI":"10.1145\/1368088.1368122"},{"key":"10705_CR134","doi-asserted-by":"publisher","unstructured":"Spearman Rank Correlation Coefficient (2008). pp 502\u2013505. Springer, New York, NY. https:\/\/doi.org\/10.1007\/978-0-387-32833-1_379","DOI":"10.1007\/978-0-387-32833-1_379"},{"key":"10705_CR135","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s13062-015-0071-8","volume":"10","author":"O Spjuth","year":"2015","unstructured":"Spjuth O, Bongcam-Rudloff E, Hern\u00e1ndez GC, Forer L, Giovacchini M, Guimera RV, Kallio A, Korpelainen E, Ka\u0144du\u0142a MM, Krachunov M et al (2015) Experiences with workflows for automating data-intensive bioinformatics. Biol Direct 10:1\u201312","journal-title":"Biol Direct"},{"key":"10705_CR136","doi-asserted-by":"publisher","unstructured":"Suwonchoochit N, Senivongse T (2021) Classification of database technology problems on stack overflow. In: 2021 IEEE\/ACIS 19th International Conference on Software Engineering Research, Management and Applications (SERA). pp 21\u201326.https:\/\/doi.org\/10.1109\/SERA51205.2021.9509047","DOI":"10.1109\/SERA51205.2021.9509047"},{"key":"10705_CR137","doi-asserted-by":"crossref","unstructured":"Thomas SW, Adams B, Hassan AE, Blostein D (2011) Modeling the evolution of topics in source code histories. In: Proceedings of the 8th working conference on mining software repositories. pp 173\u2013182","DOI":"10.1145\/1985441.1985467"},{"key":"10705_CR138","doi-asserted-by":"crossref","unstructured":"Thomas SW (2011) Mining software repositories using topic models. In: Proceedings of the 33rd international conference on software engineering. pp 1138\u20131139","DOI":"10.1145\/1985793.1986020"},{"key":"10705_CR139","doi-asserted-by":"crossref","unstructured":"Tian K, Revelle M, Poshyvanyk D (2009) Using latent Dirichlet allocation for automatic categorization of software. In: 2009 6th IEEE international working conference on mining software repositories. IEEE, pp 163\u2013166","DOI":"10.1109\/MSR.2009.5069496"},{"issue":"5","key":"10705_CR140","doi-asserted-by":"publisher","first-page":"62","DOI":"10.1109\/MCSE.2014.80","volume":"16","author":"J Towns","year":"2014","unstructured":"Towns J, Cockerill T, Dahan M, Foster I, Gaither K, Grimshaw A, Hazlewood V, Lathrop S, Lifka D, Peterson GD, Roskies R, Scott JR, Wilkins-Diehr N (2014) XSEDE: accelerating scientific discovery. Comput Sci Eng 16(5):62\u201374. https:\/\/doi.org\/10.1109\/MCSE.2014.80","journal-title":"Comput Sci Eng"},{"key":"10705_CR141","doi-asserted-by":"crossref","unstructured":"Treude C, Barzilay O, Storey M-A (2011) How do programmers ask and answer questions on the web? (nier track). In: Proceedings of the 33rd international conference on software engineering. pp 804\u2013807","DOI":"10.1145\/1985793.1985907"},{"key":"10705_CR142","doi-asserted-by":"crossref","unstructured":"Treude C, Wagner M (2019) Predicting good configurations for Github and stack overflow topic models. In: 2019 IEEE\/ACM 16th International Conference on Mining Software Repositories (MSR). IEEE, pp 84\u201395","DOI":"10.1109\/MSR.2019.00022"},{"key":"10705_CR143","unstructured":"Vasiliev Y (2020) Natural language processing with Python and spaCy: a practical introduction. No Starch Press"},{"issue":"4","key":"10705_CR144","doi-asserted-by":"publisher","first-page":"314","DOI":"10.1038\/nbt.3772","volume":"35","author":"J Vivian","year":"2017","unstructured":"Vivian J, Rao AA, Nothaft FA, Ketchum C, Armstrong J, Novak A, Pfeil J, Narkizian J, Deran AD, Musselman-Brown A et al (2017) Toil enables reproducible, open source, big biomedical data analyses. Nat Biotechnol 35(4):314\u2013316","journal-title":"Nat Biotechnol"},{"key":"10705_CR145","unstructured":"Voss K, Gentry J, Auwera G (2017) Full-stack genomics pipelining with GATK4+ WDL+ Cromwell. F1000Research 2017"},{"key":"10705_CR146","doi-asserted-by":"crossref","unstructured":"Wang Z, Chen J, Chen J, Chen H (2023) Identifying interdisciplinary topics and their evolution based on BERTopic. Scientometrics, 1\u201326","DOI":"10.1007\/s11192-023-04776-5"},{"key":"10705_CR147","doi-asserted-by":"crossref","unstructured":"Wang X, Lee M, Pinchbeck A, Fard F (2019) Where does LDA sit for Github? In: 2019 34th IEEE\/ACM International Conference on Automated Software Engineering Workshop (ASEW). IEEE, pp 94\u201397","DOI":"10.1109\/ASEW.2019.00037"},{"key":"10705_CR148","doi-asserted-by":"crossref","unstructured":"Wang S, Lo D, Jiang L (2013) An empirical study on developer interactions in stackoverflow. In: Proceedings of the 28th annual ACM symposium on applied computing. pp 1019\u20131024","DOI":"10.1145\/2480362.2480557"},{"key":"10705_CR149","unstructured":"Wikipedia (2024) Scientific workflow system. https:\/\/en.wikipedia.org\/wiki\/Scientific_workflow_system. Accessed Jan 2024"},{"key":"10705_CR150","doi-asserted-by":"crossref","unstructured":"Wohlin C, Runeson P, H\u00f6st M, Ohlsson MC, Regnell B, Wessl\u00e9n A (2012) Experimentation in software engineering. Springer Science & Business Media","DOI":"10.1007\/978-3-642-29044-2"},{"key":"10705_CR151","unstructured":"WorkflowHub (2024) WorkflowHub Community. https:\/\/workflowhub.eu\/workflows. Accessed Jan 2024"},{"issue":"10","key":"10705_CR152","doi-asserted-by":"publisher","first-page":"1161","DOI":"10.1038\/s41592-021-01254-9","volume":"18","author":"L Wratten","year":"2021","unstructured":"Wratten L, Wilm A, G\u00f6ke J (2021) Reproducible, scalable, and shareable analysis pipelines with bioinformatics workflow managers. Nat Methods 18(10):1161\u20131168","journal-title":"Nat Methods"},{"key":"10705_CR153","first-page":"910","volume":"31","author":"X-L Yang","year":"2016","unstructured":"Yang X-L, Lo D, Xia X, Wan Z-Y, Sun J-L (2016) What security questions do developers ask? a large-scale study of stack overflow posts. JCST 31:910\u2013924","journal-title":"JCST"},{"key":"10705_CR154","doi-asserted-by":"crossref","unstructured":"Yan X, Guo J, Lan Y, Cheng X (2013) A biterm topic model for short texts. In: Proceedings of the 22nd international conference on World Wide Web. pp 1445\u20131456","DOI":"10.1145\/2488388.2488514"},{"key":"10705_CR155","doi-asserted-by":"publisher","first-page":"767","DOI":"10.1007\/s11192-014-1321-8","volume":"100","author":"C-K Yau","year":"2014","unstructured":"Yau C-K, Porter A, Newman N, Suominen A (2014) Clustering scientific documents with topic modeling. Scientometrics 100:767\u2013786","journal-title":"Scientometrics"},{"key":"10705_CR156","doi-asserted-by":"crossref","unstructured":"Yi X, Allan J (2009) A comparative study of utilizing topic models for information retrieval. In: Advances in Information Retrieval: 31th European conference on IR research, ECIR 2009, Toulouse, France, April 6-9, 2009. Proceedings 31. Springer, pp 29\u201341","DOI":"10.1007\/978-3-642-00958-7_6"},{"issue":"3","key":"10705_CR157","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1145\/1084805.1084814","volume":"34","author":"J Yu","year":"2005","unstructured":"Yu J, Buyya R (2005) A taxonomy of scientific workflow systems for grid computing. ACM SIGMOD Rec 34(3):44\u201349","journal-title":"ACM SIGMOD Rec"},{"key":"10705_CR158","unstructured":"Zaharia M, Chowdhury M, Franklin MJ, Shenker S, Stoica I (2010) Spark: cluster computing with working sets. In: 2nd USENIX workshop on hot topics in cloud computing (HotCloud 10)"},{"key":"10705_CR159","doi-asserted-by":"crossref","unstructured":"Zhai Z, Liu B, Xu H, Jia P (2011) Constrained LDA for grouping product features in opinion mining. In: Advances in knowledge discovery and data mining: 15th Pacific-Asia Conference, PAKDD 2011, Shenzhen, China, May 24-27, 2011, Proceedings, Part I 15. Springer, pp 448\u2013459","DOI":"10.1007\/978-3-642-20841-6_37"},{"key":"10705_CR160","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1016\/j.future.2015.10.012","volume":"65","author":"F Zhao","year":"2016","unstructured":"Zhao F, Zhu Y, Jin H, Yang LT (2016) A personalized hashtag recommendation approach using LDA-based topic model in microblog environment. Futur Gener Comput Syst 65:196\u2013206","journal-title":"Futur Gener Comput Syst"},{"key":"10705_CR161","doi-asserted-by":"crossref","unstructured":"Zhao Y, Fei X, Raicu I, Lu S (2011) Opportunities and challenges in running scientific workflows on the cloud. In: CyberC. IEEE","DOI":"10.1109\/CyberC.2011.80"},{"key":"10705_CR162","doi-asserted-by":"crossref","unstructured":"Zhao Y, Raicu I, Foster, I (2008) Scientific workflow systems for 21st century, new bottle or new wine? In: 2008 IEEE congress on services-Part I. IEEE, pp 467\u2013471","DOI":"10.1109\/SERVICES-1.2008.79"},{"key":"10705_CR163","doi-asserted-by":"publisher","first-page":"573","DOI":"10.1016\/j.ins.2016.05.047","volume":"367","author":"S Zoghbi","year":"2016","unstructured":"Zoghbi S, Vuli\u0107 I, Moens M-F (2016) Latent Dirichlet allocation for linking user-generated content and e-commerce data. Inf Sci 367:573\u2013599","journal-title":"Inf Sci"},{"key":"10705_CR164","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1016\/j.infsof.2016.12.003","volume":"84","author":"J Zou","year":"2017","unstructured":"Zou J, Xu L, Yang M, Zhang X, Yang D (2017) Towards comprehending the non-functional requirements through developers\u2019 eyes: an exploration of stack overflow using topic analysis. Inf Softw Technol 84:19\u201332","journal-title":"Inf Softw Technol"}],"container-title":["Empirical Software Engineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-025-10705-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10664-025-10705-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10664-025-10705-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,13]],"date-time":"2025-09-13T10:03:38Z","timestamp":1757757818000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10664-025-10705-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,1]]},"references-count":164,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["10705"],"URL":"https:\/\/doi.org\/10.1007\/s10664-025-10705-2","relation":{},"ISSN":["1382-3256","1573-7616"],"issn-type":[{"value":"1382-3256","type":"print"},{"value":"1573-7616","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,8,1]]},"assertion":[{"value":"15 July 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 August 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not Applicable","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical Approval"}},{"value":"Not Applicable","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed Consent"}},{"value":"We have no conflict of interest.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}},{"value":"Not Applicable","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Clinical Trial Number in the manuscript"}}],"article-number":"151"}}