{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,12]],"date-time":"2026-10-12T17:56:15Z","timestamp":1791827775802,"version":"4.3.4"},"publisher-location":"New York, NY, USA","reference-count":70,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,17]]},"DOI":"10.1145\/3756681.3756958","type":"proceedings-article","created":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T08:30:04Z","timestamp":1766565004000},"page":"102-113","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Automatic Classification of Software Repositories: a Systematic Mapping Study"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5679-6912","authenticated-orcid":false,"given":"Stefano","family":"Balla","sequence":"first","affiliation":[{"name":"DISI - Universit\u00e0 di Bologna, Bologna, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5961-7940","authenticated-orcid":false,"given":"Thomas","family":"Degueule","sequence":"additional","affiliation":[{"name":"Univ. Bordeaux, Bordeaux, France and CNRS, Bordeaux INP, LaBRI, UMR 5800, Bordeaux, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4569-6868","authenticated-orcid":false,"given":"Romain","family":"Robbes","sequence":"additional","affiliation":[{"name":"Univ. Bordeaux, Bordeaux, France and CNRS, Bordeaux INP, LaBRI, UMR 5800, Bordeaux, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8284-7218","authenticated-orcid":false,"given":"Jean-R\u00e9my","family":"Falleri","sequence":"additional","affiliation":[{"name":"Univ. Bordeaux, CNRS, Bordeaux INP, LaBRI, UMR 5800, Bordeaux, France and Institut Universitaire de France, Bordeaux, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4576-136X","authenticated-orcid":false,"given":"Stefano","family":"Zacchiroli","sequence":"additional","affiliation":[{"name":"LTCI, T\u00e9l\u00e9com Paris, Institut Polytechnique de Paris, Palaiseau, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,12,24]]},"reference":[{"key":"e_1_3_3_2_2_2","doi-asserted-by":"publisher","unstructured":"Anonymous. 2025. Automatic Classification of Software Repositories: A Systematic Mapping Study - replication package. 10.5281\/zenodo.14773537","DOI":"10.5281\/zenodo.14773537"},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/ESEM.2019.8870181"},{"key":"e_1_3_3_2_4_2","doi-asserted-by":"publisher","unstructured":"Stefan Bellon Rainer Koschke Giulio Antoniol Jens Krinke and Ettore Merlo. 2007. Comparison and Evaluation of Clone Detection Tools. IEEE Transactions on Software Engineering 33 9 (Sept. 2007) 577\u2013591. 10.1109\/TSE.2007.70725Conference Name: IEEE Transactions on Software Engineering.","DOI":"10.1109\/TSE.2007.70725"},{"key":"e_1_3_3_2_5_2","unstructured":"Fiona Beyer and Kath Wright. 2011. Comprehensive searching for systematic reviews: a comparison of database performance. York: Centre for Reviews and Dissemination University of York (2011)."},{"key":"e_1_3_3_2_6_2","doi-asserted-by":"publisher","unstructured":"Jorge Calmon de\u00a0Almeida Biolchini Paula\u00a0Gomes Mian Ana C\u00e2ndida\u00a0Cruz Natali Tayana\u00a0Uch\u00f4a Conte and Guilherme\u00a0Horta Travassos. 2007. Scientific research ontology to support systematic review in software engineering. Adv. Eng. Informatics 21 2 (2007) 133\u2013151. 10.1016\/J.AEI.2006.11.006","DOI":"10.1016\/J.AEI.2006.11.006"},{"key":"e_1_3_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"e_1_3_3_2_8_2","first-page":"1","volume-title":"iPRES 2017 - 14th International Conference on Digital Preservation","author":"Di\u00a0Cosmo Roberto","year":"2017","unstructured":"Roberto Di\u00a0Cosmo and Stefano Zacchiroli. 2017. Software Heritage: Why and How to Preserve Software Source Code. In iPRES 2017 - 14th International Conference on Digital Preservation. PHAIDRA, Kyoto, Japan, 1\u201310. https:\/\/hal.science\/hal-01590958"},{"key":"e_1_3_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.139"},{"key":"e_1_3_3_2_10_2","doi-asserted-by":"publisher","unstructured":"Joseph\u00a0L. Fleiss. 1971. Measuring nominal scale agreement among many raters. Psychological Bulletin 76 5 (1971) 378\u2013382. 10.1037\/h0031619Place: US Publisher: American Psychological Association.","DOI":"10.1037\/h0031619"},{"key":"e_1_3_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1145\/2610384.2628055"},{"key":"e_1_3_3_2_12_2","doi-asserted-by":"publisher","unstructured":"Margaret Kipp and D.\u00a0Grant Campbell. 2010. Searching with Tags: Do Tags Help Users Find Things? Knowledge Organization 37 (Jan. 2010) 239\u2013255. 10.5771\/0943-7444-2010-4-239","DOI":"10.5771\/0943-7444-2010-4-239"},{"key":"e_1_3_3_2_13_2","doi-asserted-by":"publisher","unstructured":"Barbara Kitchenham O. Pearl\u00a0Brereton David Budgen Mark Turner John Bailey and Stephen Linkman. 2009. Systematic literature reviews in software engineering \u2013 A systematic literature review. Information and Software Technology 51 1 (Jan. 2009) 7\u201315. 10.1016\/j.infsof.2008.09.009","DOI":"10.1016\/j.infsof.2008.09.009"},{"key":"e_1_3_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE43902.2021.00040"},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2019.00031"},{"key":"e_1_3_3_2_16_2","doi-asserted-by":"publisher","unstructured":"Addi Malviya-Thakur Reed Milewicz Lavinia Paganini Ahmed Samir\u00a0Imam Mahmoud and Audris Mockus. 2023. SciCat: A Curated Dataset of Scientific Software Repositories. 10.48550\/arXiv.2312.06382arXiv:https:\/\/arXiv.org\/abs\/2312.06382 [cs].","DOI":"10.48550\/arXiv.2312.06382"},{"key":"e_1_3_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ESEM.2011.46"},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"publisher","DOI":"10.5555\/2227115.2227123"},{"key":"e_1_3_3_2_19_2","doi-asserted-by":"publisher","unstructured":"Kai Petersen Sairam Vakkalanka and Ludwik Kuzniarz. 2015. Guidelines for conducting systematic mapping studies in software engineering: An update. Information and Software Technology 64 (Aug. 2015) 1\u201318. 10.1016\/j.infsof.2015.03.007","DOI":"10.1016\/j.infsof.2015.03.007"},{"key":"e_1_3_3_2_20_2","doi-asserted-by":"publisher","unstructured":"Julian\u00a0Aron Prenner and Romain Robbes. 2022. Making the Most of Small Software Engineering Datasets With Modern Machine Learning. IEEE Transactions on Software Engineering 48 12 (Dec. 2022) 5050\u20135067. 10.1109\/TSE.2021.3135465Conference Name: IEEE Transactions on Software Engineering.","DOI":"10.1109\/TSE.2021.3135465"},{"key":"e_1_3_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSE.2003.1201189"},{"key":"e_1_3_3_2_22_2","doi-asserted-by":"publisher","unstructured":"James Sinclair and Michael Cardew-Hall. 2008. The folksonomy tag cloud: when is it useful? Journal of Information Science 34 1 (Feb. 2008) 15\u201329. 10.1177\/0165551506078083Publisher: SAGE Publications Ltd.","DOI":"10.1177\/0165551506078083"},{"key":"e_1_3_3_2_23_2","doi-asserted-by":"publisher","unstructured":"Hugo Touvron Thibaut Lavril Gautier Izacard Xavier Martinet Marie-Anne Lachaux Timoth\u00e9e Lacroix Baptiste Rozi\u00e8re Naman Goyal Eric Hambro Faisal Azhar Aurelien Rodriguez Armand Joulin Edouard Grave and Guillaume Lample. 2023. LLaMA: Open and Efficient Foundation Language Models. 10.48550\/arXiv.2302.13971arXiv:https:\/\/arXiv.org\/abs\/2302.13971 [cs].","DOI":"10.48550\/arXiv.2302.13971"},{"key":"e_1_3_3_2_24_2","doi-asserted-by":"publisher","unstructured":"Adam Tutko Austin\u00a0Z. Henley and Audris Mockus. 2022. How are Software Repositories Mined? A Systematic Literature Review of Workflows Methodologies Reproducibility and Tools. 10.48550\/arXiv.2204.08108arXiv:https:\/\/arXiv.org\/abs\/2204.08108 [cs].","DOI":"10.48550\/arXiv.2204.08108"},{"key":"e_1_3_3_2_25_2","unstructured":"Will\u00a0Segatto Vitor\u00a0Freitas. 2024. Parsifal. https:\/\/parsif.al\/"},{"key":"e_1_3_3_2_26_2","doi-asserted-by":"crossref","unstructured":"Claes Wohlin and Rafael Prikladnicki. 2013. Systematic literature reviews in software engineering. Inf. Softw. Technol. 55 6 (2013) 919\u2013920.","DOI":"10.1016\/j.infsof.2013.02.002"},{"key":"e_1_3_3_2_27_2","doi-asserted-by":"publisher","DOI":"10.5555\/2349018"},{"key":"e_1_3_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1016\/B978-0-12-804206-9.00027-1"},{"key":"e_1_3_3_3_2_2","doi-asserted-by":"publisher","unstructured":"Doaa Altarawy Hossameldin Shahin Ayat Mohammed and Na Meng. 2018. Lascad : Language-agnostic software categorization and similar application detection. Journal of Systems and Software 142 (Aug. 2018) 21\u201334. 10.1016\/j.jss.2018.04.018","DOI":"10.1016\/j.jss.2018.04.018"},{"key":"e_1_3_3_3_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/2972958.2972966"},{"key":"e_1_3_3_3_4_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSAC.2016.124"},{"key":"e_1_3_3_3_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3382494.3410690"},{"key":"e_1_3_3_3_6_2","doi-asserted-by":"publisher","unstructured":"Juri Di\u00a0Rocco Davide Di\u00a0Ruscio Claudio Di\u00a0Sipio Phuong\u00a0T. Nguyen and Riccardo Rubei. 2023. HybridRec: A recommender system for tagging GitHub repositories. Applied Intelligence 53 8 (April 2023) 9708\u20139730. 10.1007\/s10489-022-03864-y","DOI":"10.1007\/s10489-022-03864-y"},{"key":"e_1_3_3_3_7_2","doi-asserted-by":"publisher","DOI":"10.1145\/3383219.3383227"},{"key":"e_1_3_3_3_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/COMPSAC.2019.00013"},{"key":"e_1_3_3_3_9_2","doi-asserted-by":"publisher","DOI":"10.1109\/CSII.2019.00021"},{"key":"e_1_3_3_3_10_2","doi-asserted-by":"publisher","unstructured":"Maliheh Izadi Abbas Heydarnoori and Georgios Gousios. 2021. Topic recommendation for software repositories using multi-label classification algorithms. Empirical Software Engineering 26 5 (July 2021) 93. 10.1007\/s10664-021-09976-2","DOI":"10.1007\/s10664-021-09976-2"},{"key":"e_1_3_3_3_11_2","doi-asserted-by":"publisher","unstructured":"Maliheh Izadi Mahtab Nejati and Abbas Heydarnoori. 2023. Semantically-enhanced topic recommendation systems for software projects. Empirical Software Engineering 28 2 (Feb. 2023) 50. 10.1007\/s10664-022-10272-w","DOI":"10.1007\/s10664-022-10272-w"},{"key":"e_1_3_3_3_12_2","doi-asserted-by":"publisher","DOI":"10.1145\/3077136.3080753"},{"key":"e_1_3_3_3_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/IWPSE.2003.1231227"},{"key":"e_1_3_3_3_14_2","doi-asserted-by":"publisher","DOI":"10.1109\/APSEC.2004.69"},{"key":"e_1_3_3_3_15_2","doi-asserted-by":"publisher","unstructured":"Yesol Kim Seong-je Cho Sangchul Han and Ilsun You. 2018. A software classification scheme using binary-level characteristics for efficient software filtering. Soft Computing 22 2 (Jan. 2018) 595\u2013606. 10.1007\/s00500-016-2357-x","DOI":"10.1007\/s00500-016-2357-x"},{"key":"e_1_3_3_3_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/BCD2018.2018.00015"},{"key":"e_1_3_3_3_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME.2018.00056"},{"key":"e_1_3_3_3_18_2","doi-asserted-by":"publisher","DOI":"10.1109\/IITA.Workshops.2008.277"},{"key":"e_1_3_3_3_19_2","doi-asserted-by":"publisher","unstructured":"Mario Linares-V\u00e1squez Collin McMillan Denys Poshyvanyk and Mark Grechanik. 2014. On using machine learning to automatically classify software applications into domain categories. Empirical Software Engineering 19 3 (June 2014) 582\u2013618. 10.1007\/s10664-012-9230-z","DOI":"10.1007\/s10664-012-9230-z"},{"key":"e_1_3_3_3_20_2","doi-asserted-by":"publisher","DOI":"10.1145\/1321631.1321709"},{"key":"e_1_3_3_3_21_2","doi-asserted-by":"publisher","DOI":"10.1145\/3196398.3196446"},{"key":"e_1_3_3_3_22_2","doi-asserted-by":"publisher","DOI":"10.1145\/1342211.1342234"},{"key":"e_1_3_3_3_23_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSM.2011.6080801"},{"key":"e_1_3_3_3_24_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSCC59169.2023.10334939"},{"key":"e_1_3_3_3_25_2","doi-asserted-by":"publisher","unstructured":"Mathieu Nassif and Martin\u00a0P. Robillard. 2023. Identifying Concepts in Software Projects. IEEE Transactions on Software Engineering 49 7 (July 2023) 3660\u20133674. 10.1109\/TSE.2023.3265855Conference Name: IEEE Transactions on Software Engineering.","DOI":"10.1109\/TSE.2023.3265855"},{"key":"e_1_3_3_3_26_2","doi-asserted-by":"publisher","unstructured":"Peter Pickerill Heiko\u00a0Joshua Jungen Miros\u0142aw Ochodek Micha\u0142 Ma\u0107kowiak and Miroslaw Staron. 2020. PHANTOM: Curating GitHub for engineered software projects using time-series clustering. Empirical Software Engineering 25 4 (July 2020) 2897\u20132929. 10.1007\/s10664-020-09825-8","DOI":"10.1007\/s10664-020-09825-8"},{"key":"e_1_3_3_3_27_2","first-page":"149","volume-title":"23rd International Symposium on Research in Attacks, Intrusions and Defenses (RAID 2020)","author":"Rokon Md\u00a0Omar\u00a0Faruk","year":"2020","unstructured":"Md\u00a0Omar\u00a0Faruk Rokon, Risul Islam, Ahmad Darki, Evangelos\u00a0E. Papalexakis, and Michalis Faloutsos. 2020. {SourceFinder}: Finding Malware {Source-Code} from Publicly Available Repositories in {GitHub}. In 23rd International Symposium on Research in Attacks, Intrusions and Defenses (RAID 2020). USENIX Association, Donostia, Spain, 149\u2013163. https:\/\/www.usenix.org\/conference\/raid2020\/presentation\/omar"},{"key":"e_1_3_3_3_28_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSME52107.2021.00038"},{"key":"e_1_3_3_3_29_2","doi-asserted-by":"publisher","unstructured":"Cezar Sas Andrea Capiluppi Claudio Di\u00a0Sipio Juri Di\u00a0Rocco and Davide Di\u00a0Ruscio. 2023. GitRanking: A ranking of GitHub topics for software classification using active sampling. Software: Practice and Experience 53 10 (Oct. 2023) 1982\u20132006. 10.1002\/spe.3238","DOI":"10.1002\/spe.3238"},{"key":"e_1_3_3_3_30_2","doi-asserted-by":"publisher","DOI":"10.1145\/3366423.3380145"},{"key":"e_1_3_3_3_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3084226.3084287"},{"key":"e_1_3_3_3_32_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67190-1_34"},{"key":"e_1_3_3_3_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/MSR.2009.5069496"},{"key":"e_1_3_3_3_34_2","doi-asserted-by":"publisher","DOI":"10.1145\/775047.775141"},{"key":"e_1_3_3_3_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICSM.2013.35"},{"key":"e_1_3_3_3_36_2","doi-asserted-by":"publisher","unstructured":"Tao Wang Huaimin Wang Gang Yin Charles\u00a0X. Ling Xiao Li and Peng Zou. 2014. Tag recommendation for open source software. Frontiers of Computer Science 8 1 (Feb. 2014) 69\u201382. 10.1007\/s11704-013-2394-x","DOI":"10.1007\/s11704-013-2394-x"},{"key":"e_1_3_3_3_37_2","doi-asserted-by":"publisher","DOI":"10.1145\/2384416.2384419"},{"key":"e_1_3_3_3_38_2","doi-asserted-by":"publisher","DOI":"10.1109\/SANER56733.2023.00025"},{"key":"e_1_3_3_3_39_2","doi-asserted-by":"publisher","DOI":"10.1145\/3131704.3131706"},{"key":"e_1_3_3_3_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICWS60048.2023.00064"},{"key":"e_1_3_3_3_41_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15384-6_58"},{"key":"e_1_3_3_3_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/2666539.2666570"},{"key":"e_1_3_3_3_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2019.00098"},{"key":"e_1_3_3_3_44_2","doi-asserted-by":"publisher","unstructured":"Yuming Zhou and Baowen Xu. 2008. Predicting the maintainability of open source software using design metrics. Wuhan University Journal of Natural Sciences 13 1 (Feb. 2008) 14\u201320. 10.1007\/s11859-008-0104-6","DOI":"10.1007\/s11859-008-0104-6"}],"event":{"name":"EASE '25: Evaluation and Assessment in Software Engineering","location":"Istanbul Turkiye","acronym":"EASE '25"},"container-title":["Proceedings of the 29th International Conference on Evaluation and Assessment in Software Engineering"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3756681.3756958","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,24]],"date-time":"2025-12-24T08:44:06Z","timestamp":1766565846000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3756681.3756958"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,17]]},"references-count":70,"alternative-id":["10.1145\/3756681.3756958","10.1145\/3756681"],"URL":"https:\/\/doi.org\/10.1145\/3756681.3756958","relation":{},"subject":[],"published":{"date-parts":[[2025,6,17]]},"assertion":[{"value":"2025-12-24","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}