{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,4,25]],"date-time":"2025-04-25T04:22:23Z","timestamp":1745554943333,"version":"3.40.4"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819650316","type":"print"},{"value":"9789819650323","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-981-96-5032-3_7","type":"book-chapter","created":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T18:41:30Z","timestamp":1745520090000},"page":"113-126","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["StellarTop : An Integrated Multi-topic Dataset on\u00a0GitHub Repositories"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-8696-4069","authenticated-orcid":false,"given":"Zhiwei","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8645-3193","authenticated-orcid":false,"given":"Wenrui","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,4,25]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Borges, H., Hora, A., Valente, M.T.: Understanding the factors that impact the popularity of github repositories. In: 2016 IEEE International Conference on Software Maintenance and Evolution (ICSME), pp. 334\u2013344. IEEE (2016)","DOI":"10.1109\/ICSME.2016.31"},{"key":"7_CR2","doi-asserted-by":"crossref","unstructured":"Cao, Q., Zhao, B.: Application of open-source software in knowledge graph construction. In: e-Learning, e-Education, and Online Training: 6th EAI International Conference, eLEOT 2020, Changsha, China, 20\u201321 June 2020, Proceedings, Part II, vol. 6, pp. 97\u2013102. Springer (2020)","DOI":"10.1007\/978-3-030-63955-6_9"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Chen, D., Stolee, K.T., Menzies, T.: Replication can improve prior results: a github study of pull request acceptance. In: 2019 IEEE\/ACM 27th International Conference on Program Comprehension (ICPC), pp. 179\u2013190. IEEE (2019)","DOI":"10.1109\/ICPC.2019.00037"},{"key":"7_CR4","doi-asserted-by":"publisher","first-page":"1843","DOI":"10.1007\/s10664-015-9402-8","volume":"21","author":"TH Chen","year":"2016","unstructured":"Chen, T.H., Thomas, S.W., Hassan, A.E.: A survey on the use of topic models when mining software repositories. Empir. Softw. Eng. 21, 1843\u20131919 (2016)","journal-title":"Empir. Softw. Eng."},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Cosentino, V., Canovas\u00a0Izquierdo, J.L., Cabot, J.: A systematic mapping study of software development with github. IEEE Access 1\u20131 (2017)","DOI":"10.1109\/ACCESS.2017.2682323"},{"key":"7_CR6","doi-asserted-by":"crossref","unstructured":"Cosentino, V., Luis, J., Cabot, J.: Findings from github: methods, datasets and limitations. In: Proceedings of the 13th International Conference on Mining Software Repositories (MSR 2016) (2016)","DOI":"10.1145\/2901739.2901776"},{"key":"7_CR7","doi-asserted-by":"crossref","unstructured":"Di\u00a0Rocco, J., Di\u00a0Ruscio, D., Di\u00a0Sipio, C., Nguyen, P., Rubei, R.: Topfilter: an approach to recommend relevant github topics. In: Proceedings of the 14th ACM\/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM), pp. 1\u201311 (2020)","DOI":"10.1145\/3382494.3410690"},{"issue":"8","key":"7_CR8","doi-asserted-by":"publisher","first-page":"9708","DOI":"10.1007\/s10489-022-03864-y","volume":"53","author":"J Di Rocco","year":"2023","unstructured":"Di Rocco, J., Di Ruscio, D., Di Sipio, C., Nguyen, P.T., Rubei, R.: Hybridrec: a recommender system for tagging github repositories. Appl. Intell. 53(8), 9708\u20139730 (2023)","journal-title":"Appl. Intell."},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Di\u00a0Sipio, C., Rubei, R., Di\u00a0Ruscio, D., Nguyen, P.T.: A multinomial na\u00efve bayesian (mnb) network to automatically recommend topics for github repositories. In: Proceedings of the 24th International Conference on Evaluation and Assessment in Software Engineering, pp. 71\u201380 (2020)","DOI":"10.1145\/3383219.3383227"},{"key":"7_CR10","unstructured":"Gitea: https:\/\/about.gitea.cn (2023), Accessed 6 Dec 2023"},{"key":"7_CR11","unstructured":"GitHub: Github rest api - getting started. https:\/\/docs.github.com\/en\/rest\/guides\/getting-started-with-the-rest-api?apiVersion=2022-11-28 (2022), Accessed 6 Dec 2023"},{"key":"7_CR12","unstructured":"GitLab: https:\/\/about.gitlab.com (2023), Accessed 6 Dec 2023"},{"key":"7_CR13","doi-asserted-by":"crossref","unstructured":"Gousios, G., Spinellis, D.: Ghtorrent: Github\u2019s data from a firehose. In: 2012 9th IEEE Working Conference on Mining Software Repositories (MSR), pp. 12\u201321. IEEE (2012)","DOI":"10.1109\/MSR.2012.6224294"},{"key":"7_CR14","unstructured":"Grigorik, I.: The gh archive project. http:\/\/www.gharchive.org\/ (2015), Accessed 2024"},{"issue":"5","key":"7_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10664-021-09976-2","volume":"26","author":"M Izadi","year":"2021","unstructured":"Izadi, M., Heydarnoori, A., Gousios, G.: Topic recommendation for software repositories using multi-label classification algorithms. Empir. Softw. Eng. 26(5), 1\u201333 (2021). https:\/\/doi.org\/10.1007\/s10664-021-09976-2","journal-title":"Empir. Softw. Eng."},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Kalliamvakou, E., Gousios, G., Blincoe, K., Singer, L., German, D.M., Damian, D.: The promises and perils of mining github. In: Proceedings of the 11th Working Conference on Mining Software Repositories (MSR 2014) (2014)","DOI":"10.1145\/2597073.2597074"},{"issue":"11","key":"7_CR17","doi-asserted-by":"publisher","first-page":"2099","DOI":"10.1007\/s10994-020-05888-2","volume":"109","author":"S Khandagale","year":"2020","unstructured":"Khandagale, S., Xiao, H., Babbar, R.: Bonsai: diverse and shallow trees for extreme multi-label classification. Mach. Learn. 109(11), 2099\u20132119 (2020). https:\/\/doi.org\/10.1007\/s10994-020-05888-2","journal-title":"Mach. Learn."},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Ma, Y., Bogart, C., Amreen, S., et\u00a0al.: World of code: an infrastructure for mining the universe of open source vcs data. In: 2019 IEEE\/ACM 16th International Conference on Mining Software Repositories (MSR), pp. 143\u2013154. IEEE (2019)","DOI":"10.1109\/MSR.2019.00031"},{"key":"7_CR19","doi-asserted-by":"crossref","unstructured":"McDonald, N., Goggins, S.: Performance and participation in open source software on github. In: CHI 2013 Extended Abstracts on Human Factors in Computing Systems, CHI EA 2013, pp. 139-144. Association for Computing Machinery, New York, NY, USA (2013)","DOI":"10.1145\/2468356.2468382"},{"key":"7_CR20","doi-asserted-by":"crossref","unstructured":"Prabhu, Y., Kag, A., Harsola, S., Agrawal, R., Varma, M.: Parabel: partitioned label trees for extreme classification with application to dynamic search advertising. In: Proceedings of the 2018 World Wide Web Conference, pp. 993\u20131002 (2018)","DOI":"10.1145\/3178876.3185998"},{"key":"7_CR21","doi-asserted-by":"publisher","first-page":"1296","DOI":"10.1007\/s10664-018-9660-3","volume":"24","author":"G Prana","year":"2019","unstructured":"Prana, G., Treude, C., Thung, F., Atapattu, T., Lo, D.: Categorizing the content of github readme files. Empir. Softw. Eng. 24, 1296\u20131327 (2019)","journal-title":"Empir. Softw. Eng."},{"key":"7_CR22","doi-asserted-by":"crossref","unstructured":"Tan, X., Zhou, M., Sun, Z.: A first look at good first issues on github. In: Proceedings of the 28th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pp. 398\u2013409 (2020)","DOI":"10.1145\/3368089.3409746"},{"key":"7_CR23","doi-asserted-by":"crossref","unstructured":"Thomas, S.W., Adams, B., Hassan, A.E., Blostein, D.: Modeling the evolution of topics in source code histories. In: Proceedings of the 8th Working Conference on Mining Software Repositories, pp. 173\u2013182 (2011)","DOI":"10.1145\/1985441.1985467"},{"key":"7_CR24","doi-asserted-by":"crossref","unstructured":"Widyasari, R., Zhao, Z., Le\u00a0Cong, T., Kang, H.J., Lo, D.: Topic recommendation for github repositories: How far can extreme multi-label learning go? In: 2023 IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER), pp. 167\u2013178. IEEE (2023)","DOI":"10.1109\/SANER56733.2023.00025"},{"key":"7_CR25","doi-asserted-by":"crossref","unstructured":"Wu, X., Dong, X., Nguyen, T., Liu, C., Pan, L., Luu, A.T.: Infoctm: a mutual information maximization perspective of cross-lingual topic modeling (2023)","DOI":"10.1609\/aaai.v37i11.26612"},{"key":"7_CR26","doi-asserted-by":"crossref","unstructured":"Zhang, N., et al.: Long-tail relation extraction via knowledge graph embeddings and graph convolution networks. arXiv preprint arXiv:1903.01306 (2019)","DOI":"10.18653\/v1\/N19-1306"}],"container-title":["Lecture Notes in Computer Science","Benchmarking, Measuring, and Optimizing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-5032-3_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,24]],"date-time":"2025-04-24T18:41:45Z","timestamp":1745520105000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-5032-3_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819650316","9789819650323"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-5032-3_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"25 April 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"Bench","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Benchmarking, Measuring and Optimization","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guangzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"bench2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}