{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T16:37:54Z","timestamp":1785170274357,"version":"3.55.0"},"publisher-location":"Cham","reference-count":25,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783031087509","type":"print"},{"value":"9783031087516","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":[[2022]]},"DOI":"10.1007\/978-3-031-08751-6_30","type":"book-chapter","created":{"date-parts":[[2022,6,21]],"date-time":"2022-06-21T02:03:15Z","timestamp":1655776995000},"page":"417-430","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Models and\u00a0Metrics for\u00a0Mining Meaningful Metadata"],"prefix":"10.1007","author":[{"given":"Tyler J.","family":"Skluzacek","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Erica","family":"Hsu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kyle","family":"Chard","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ian","family":"Foster","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,6,15]]},"reference":[{"key":"30_CR1","unstructured":"Libmagic(3) - linux man page, November 2009. https:\/\/linux.die.net\/man\/3\/libmagic"},{"key":"30_CR2","unstructured":"Cdiac, March 2018. https:\/\/cdiac.ess-dive.lbl.gov\/"},{"key":"30_CR3","doi-asserted-by":"crossref","unstructured":"Chard, R., et al.: Funcx: a federated function serving fabric for science. In: Proceedings of the 29th International Symposium on High-Performance Parallel and Distributed Computing, pp. 65\u201376 (2020)","DOI":"10.1145\/3369583.3392683"},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Deng, H., Runger, G., Tuv, E.: Bias of importance measures for multi-valued attributes and solutions. In: International Conference on Artificial Neural Networks, pp. 293\u2013300 (2011)","DOI":"10.1007\/978-3-642-21738-8_38"},{"key":"30_CR5","doi-asserted-by":"crossref","unstructured":"Deutsch, E.W., et al.: BDQC: a general-purpose analytics tool for domain-blind validation of big data. bioRxiv 258822 (2018)","DOI":"10.1101\/258822"},{"key":"30_CR6","doi-asserted-by":"crossref","unstructured":"Gopal, S., Yang, Y., Salomatin, K., et al.: Statistical learning for file-type identification. In: International Conference on Machine Learning and Applications, pp. 68\u201373 (2011)","DOI":"10.1109\/ICMLA.2011.135"},{"key":"30_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"320","DOI":"10.1007\/978-3-540-30544-6_34","volume-title":"Digital Libraries: International Collaboration and Cross-Fertilization","author":"Baden Hughes","year":"2004","unstructured":"Hughes, Baden: Metadata quality evaluation: experience from the open language archives community. In: Chen, Zhaoneng, Chen, Hsinchun, Miao, Qihao, Fu, Yuxi, Fox, Edward, Lim, Ee.-peng (eds.) ICADL 2004. LNCS, vol. 3334, pp. 320\u2013329. Springer, Heidelberg (2004). https:\/\/doi.org\/10.1007\/978-3-540-30544-6_34"},{"key":"30_CR8","doi-asserted-by":"publisher","unstructured":"Kir\u00e1ly, P.: Measuring Metadata Quality. Ph.D. thesis, Georg-August-Universit\u00e4t G\u00f6ttingen, June 2019. https:\/\/doi.org\/10.13140\/RG.2.2.33177.77920","DOI":"10.13140\/RG.2.2.33177.77920"},{"key":"30_CR9","unstructured":"Li, W.J., Wang, K., Stolfo, S.J., Herzog, B.: Fileprints: identifying file types by n-gram analysis. In: IEEE SMC Information Assurance Workshop, pp. 64\u201371 (2005)"},{"issue":"4","key":"30_CR10","doi-asserted-by":"publisher","first-page":"724","DOI":"10.1002\/asi.21706","volume":"63","author":"M Margaritopoulos","year":"2012","unstructured":"Margaritopoulos, M., Margaritopoulos, T., Mavridis, I., Manitsaris, A.: Quantifying and measuring metadata completeness. J. Am. Soc. Inform. Sci. Technol. 63(4), 724\u2013737 (2012)","journal-title":"J. Am. Soc. Inform. Sci. Technol."},{"key":"30_CR11","doi-asserted-by":"crossref","unstructured":"Marini, L., Gutierrez-Polo, I., et al.: Clowder: open source data management for long tail data. In: Practice and Experience on Advance Research Computing (2018)","DOI":"10.1145\/3219104.3219159"},{"key":"30_CR12","volume-title":"Tika in Action","author":"C Mattmann","year":"2011","unstructured":"Mattmann, C., Zitting, J.: Tika in Action. Manning Publications Co., USA (2011)"},{"key":"30_CR13","doi-asserted-by":"crossref","unstructured":"McDaniel, M., Heydari, M.H.: Content based file type detection algorithms. In: 36th Annual Hawaii Int\u2019l Conference on System Sciences, pp. 10-pp. IEEE (2003)","DOI":"10.1109\/HICSS.2003.1174905"},{"key":"30_CR14","doi-asserted-by":"publisher","unstructured":"Ochoa, X., Duval, E.: Automatic evaluation of metadata quality in digital repositories. Int. J. Digit. Lib. 67\u201391 (2009). https:\/\/doi.org\/10.1007\/s00799-009-0054-4","DOI":"10.1007\/s00799-009-0054-4"},{"key":"30_CR15","doi-asserted-by":"crossref","unstructured":"Poisel, R., Tjoa, S.: A comprehensive literature review of file carving. In: Int\u2019l Conference on Availability, Reliability and Security, pp. 475\u2013484. IEEE (2013)","DOI":"10.1109\/ARES.2013.62"},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Rodrigo, G., Henderson, M., et al.: ScienceSearch: enabling search through automatic metadata generation. In: 14th International Conference on e-Science, pp. 93\u2013104 (2018)","DOI":"10.1109\/eScience.2018.00025"},{"issue":"1","key":"30_CR17","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1145\/584091.584093","volume":"5","author":"CE Shannon","year":"2001","unstructured":"Shannon, C.E.: A mathematical theory of communication. ACM SIGMOBILE Mob. Comput. Commun. Rev. 5(1), 3\u201355 (2001)","journal-title":"ACM SIGMOBILE Mob. Comput. Commun. Rev."},{"key":"30_CR18","doi-asserted-by":"crossref","unstructured":"Skluzacek, T., et al.: A serverless framework for distributed bulk metadata extraction. In: 30th International Symposium on High-Performance Parallel and Distributed Computing (2021)","DOI":"10.1145\/3431379.3460636"},{"key":"30_CR19","doi-asserted-by":"crossref","unstructured":"Skluzacek, T.J., : Serverless workflows for indexing large scientific data. In: Int\u2019l Workshop on Serverless Computing, pp. 43\u201348 (2019)","DOI":"10.1145\/3366623.3368140"},{"key":"30_CR20","doi-asserted-by":"crossref","unstructured":"Skluzacek, T.J., et al.: Skluma: an extensible metadata extraction pipeline for disorganized data. In: IEEE 14th International Conference on e-Science, pp. 256\u2013266. IEEE (2018)","DOI":"10.1109\/eScience.2018.00040"},{"key":"30_CR21","doi-asserted-by":"crossref","unstructured":"Tabish, S.M., Shafiq, M.Z., Farooq, M.: Malware detection using statistical analysis of byte-level file content. In: ACM SIGKDD Workshop on CyberSecurity and Intelligence Informatics, pp. 23\u201331 (2009)","DOI":"10.1145\/1599272.1599278"},{"key":"30_CR22","doi-asserted-by":"crossref","unstructured":"Talburt, J.: The Flesch index: An easily programmable readability analysis algorithm. In: International Conference on Systems Documentation, pp. 114\u2013122 (1986)","DOI":"10.1145\/10563.10583"},{"key":"30_CR23","doi-asserted-by":"crossref","unstructured":"Vazhkudai, S.S., Harney, J., et al.: Constellation: a science graph network for scalable data and knowledge discovery in extreme-scale scientific collaborations. In: IEEE International Conference on Big Data, pp. 3052\u20133061 (2016)","DOI":"10.1109\/BigData.2016.7840959"},{"key":"30_CR24","doi-asserted-by":"publisher","unstructured":"Wang, L.L., Lo, K., et al.: Cord-19: The covid-19 open research dataset. arXiv:2004.10706 (2020). https:\/\/doi.org\/10.48550\/ARXIV.2004.10706","DOI":"10.48550\/ARXIV.2004.10706"},{"issue":"1","key":"30_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1471-2105-16-S12-S1","volume":"16","author":"Y Wang","year":"2015","unstructured":"Wang, Y., Li, Y., et al.: Efficient test for nonlinear dependence of two continuous variables. BMC Bioinform. 16(1), 1\u20138 (2015)","journal-title":"BMC Bioinform."}],"container-title":["Lecture Notes in Computer Science","Computational Science \u2013 ICCS 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-08751-6_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,21]],"date-time":"2026-06-21T00:04:59Z","timestamp":1782000299000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-08751-6_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031087509","9783031087516"],"references-count":25,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-08751-6_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"15 June 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICCS","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Science","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"London","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 June 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 June 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iccs-computsci2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.iccs-meeting.org\/iccs2022\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"474","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"175","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"78","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"37% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2.8","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}