{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T04:12:21Z","timestamp":1749096741288,"version":"3.41.0"},"reference-count":108,"publisher":"Springer Science and Business Media LLC","issue":"3-4","license":[{"start":{"date-parts":[[2016,8,4]],"date-time":"2016-08-04T00:00:00Z","timestamp":1470268800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Data Sci Anal"],"published-print":{"date-parts":[[2016,11]]},"DOI":"10.1007\/s41060-016-0016-z","type":"journal-article","created":{"date-parts":[[2016,8,4]],"date-time":"2016-08-04T09:51:55Z","timestamp":1470304315000},"page":"177-197","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["A new data science research program: evaluation, metrology, standards, and community outreach"],"prefix":"10.1007","volume":"1","author":[{"given":"Bonnie J.","family":"Dorr","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Craig S.","family":"Greenberg","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peter","family":"Fontana","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mark","family":"Przybocki","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marion","family":"Le Bras","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cathryn","family":"Ploehn","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7894-7830","authenticated-orcid":false,"given":"Oleg","family":"Aulov","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martial","family":"Michel","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"E. Jim","family":"Golden","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wo","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2016,8,4]]},"reference":[{"key":"16_CR1","doi-asserted-by":"crossref","unstructured":"Dorr, B.J., Greenberg, C.S., Fontana, P., Przybocki, M., Le Bras, M., Ploehn, C., Aulov, O., Michel, M., Golden, E.J., Chang, W.: The NIST data science initiative, In: IEEE International Conference on Data Science and Advanced Analytics (DSAA), pp. 1\u201310. IEEE (2015)","DOI":"10.1109\/DSAA.2015.7344805"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Dorr, B., Greenberg, C., Fontana, P., Przybocki, M., Le Bras, M., Ploehn, C., Aulov, O., Chang, W.: The NIST IAD data science evaluation series: part of the NIST information access division data science research program. In: Proceedings of IEEE BigData 2015, pp. 2575\u20132577. IEEE, Santa Clara, CA (2015)","DOI":"10.1109\/BigData.2015.7364096"},{"key":"16_CR3","unstructured":"Smith, M.: The White House names Dr. D.J. Patil as the first U.S. chief data scientist. www.whitehouse.gov\/blog\/2015\/02\/18\/white-house-names-dr-dj-patil-first-us-chief-data-scientist (2015)"},{"key":"16_CR4","unstructured":"Cao, L., Motoda, H., Karypis, G., Boethals, B.: DSAA trends and controversies. In: International Conference on Data Science and Advanced Analytics (DSAA). Shanghai (2014)"},{"issue":"5","key":"16_CR5","doi-asserted-by":"publisher","first-page":"1936","DOI":"10.1109\/TITS.2014.2305334","volume":"15","author":"S Yang","year":"2014","unstructured":"Yang, S., Kalpakis, K., Biem, A.: Detecting road traffic events by coupling multiple timeseries with a nonparametric bayesian method. IEEE Trans. Intell. Transp. Syst. 15(5), 1936 (2014). doi: 10.1109\/TITS.2014.2305334","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"issue":"3","key":"16_CR6","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1145\/1541880.1541882","volume":"41","author":"V Chandola","year":"2009","unstructured":"Chandola, V., Banerjee, A., Kumar, V.: Anomaly detection: a survey. ACM Comput. Surv. (CSUR) 41(3), 15 (2009)","journal-title":"ACM Comput. Surv. (CSUR)"},{"key":"16_CR7","volume-title":"Conceptual Modeling: Foundations and Applications","author":"R Fagin","year":"2009","unstructured":"Fagin, R., Haas, L., Hern\u00e1ndez, M., Miller, R.J., Popa, L., Velegrakis, Y.: Conceptual Modeling: Foundations and Applications. Springer, New York (2009)"},{"issue":"12","key":"16_CR8","doi-asserted-by":"crossref","first-page":"2018","DOI":"10.14778\/2367502.2367564","volume":"5","author":"L Getoor","year":"2012","unstructured":"Getoor, L., Machanavajjhala, A.: Entity resolution: theory, practice & open challenges. Proc. VLDB Endow. 5(12), 2018 (2012)","journal-title":"Proc. VLDB Endow."},{"key":"16_CR9","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-642-31164-2","volume-title":"Data Matching: Concepts and Techniques for Record Linkage, Entity Resolution, and Duplicate Detection, Data-Centric Systems and Applications","author":"P Christen","year":"2012","unstructured":"Christen, P.: Data Matching: Concepts and Techniques for Record Linkage, Entity Resolution, and Duplicate Detection, Data-Centric Systems and Applications. Springer, Berlin (2012)"},{"key":"16_CR10","unstructured":"Sleeman, J., Finin, T., Joshi, A.: Entity type recognition for heterogeneous semantic graphs. In: 2013 AAAI Fall Symposium Series (2013)"},{"key":"16_CR11","unstructured":"Jeevan, M.: Fundamental methods of data science: Classification, regression and similarity matching. http:\/\/www.kdnuggets.com\/2015\/01\/fundamental-methods-data-science-classification-regression-similarity-matching.html (2015)"},{"volume-title":"Predicting Structured Data (Neural Information Processing)","year":"2007","key":"16_CR12","unstructured":"Bakir, G.N., Hofmann, T., Schlkopf, B., Smola, A.J., Taskar, B., Vishwanathan, S.V.N. (eds.): Predicting Structured Data (Neural Information Processing). The MIT Press, Cambridge (2007)"},{"key":"16_CR13","unstructured":"Lafferty, J.D., McCallum, A., Pereira, F.C.N.: Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In: ICML \u201901 Proceedings of the Eighteenth International Conference on Machine Learning, pp. 282\u2013289. Morgan Kaufmann Publishers Inc., San Francisco, CA, USA (2001)"},{"issue":"3","key":"16_CR14","doi-asserted-by":"crossref","first-page":"238","DOI":"10.2307\/1403797","volume":"57","author":"E Fix","year":"1989","unstructured":"Fix, E., Hodges, J.J.L.: Discriminatory analysis. Nonparametric discrimination: consistency properties. Stat. Rev. Rev. Int. Stat. 57(3), 238 (1989)","journal-title":"Stat. Rev. Rev. Int. Stat."},{"issue":"3","key":"16_CR15","doi-asserted-by":"crossref","first-page":"233","DOI":"10.2307\/1403796","volume":"57","author":"BW Silverman","year":"1989","unstructured":"Silverman, B.W., Jones, M.C.: An important contribution to nonparametric discriminant analysis and density estimation: commentary on Fix and Hodges (1951). Int. Stat. Rev. Rev. Int. Stat. 57(3), 233 (1989)","journal-title":"Int. Stat. Rev. Rev. Int. Stat."},{"key":"16_CR16","unstructured":"Mayfield, C., Neville, J., Prabhakar, S.: A statistical method for integrated data cleaning and imputation. Technical Report 09-008, Purdue University (2009)"},{"key":"16_CR17","unstructured":"Bengio, Y., Goodfellow, I.J., Courville A.: Deep learning. http:\/\/www.iro.umontreal.ca\/bengioy\/dlbook (2015)"},{"key":"16_CR18","doi-asserted-by":"publisher","unstructured":"Katariya, N., Iyer, A., Sarawagi, S.: Active evaluation of classifiers on large datasets. In: 2013 IEEE 13th International Conference on Data Mining, vol. 0 , pp. 329\u2013338. IEEE Computer Society, Los Alamitos, CA, USA (2012). doi: 10.1109\/ICDM.2012.161","DOI":"10.1109\/ICDM.2012.161"},{"key":"16_CR19","unstructured":"Text retrieval conference. http:\/\/trec.nist.gov (2014)"},{"key":"16_CR20","doi-asserted-by":"crossref","DOI":"10.1017\/CBO9780511802270","volume-title":"Atmospheric Modeling, Data Assimilation and Predictability","author":"E Kalnay","year":"2002","unstructured":"Kalnay, E.: Atmospheric Modeling, Data Assimilation and Predictability, 1st edn. Cambridge University Press, New York (2002)","edition":"1"},{"issue":"75","key":"16_CR21","first-page":"81","volume":"2","author":"O Talagrand","year":"1997","unstructured":"Talagrand, O.: Assimilation of observations: an introduction. Meteorol Soc Jpn Ser 2(75), 81 (1997)","journal-title":"Meteorol Soc Jpn Ser"},{"key":"16_CR22","unstructured":"Waltz, E., Llinas, J. et\u00a0al.: Multisensor data fusion, vol. 685. Artech house Boston (1990)"},{"key":"16_CR23","unstructured":"Joshi, V., Rajamani, N., Katsuki, T., Prathapaneni, N., Subramaniam, L.V.: Information fusion based learning for frugal traffic state sensing. IJCAI. Citeseer (2013)"},{"key":"16_CR24","volume-title":"Information Visualization, Third Edition: Perception for Design","author":"C Ware","year":"2012","unstructured":"Ware, C.: Information Visualization, Third Edition: Perception for Design, 3rd edn. Morgan Kaufmann, Waltham (2012)","edition":"3"},{"key":"16_CR25","volume-title":"The Craft of Information Visualization: Readings and Reflections","author":"BB Bederson","year":"2003","unstructured":"Bederson, B.B., Shneiderman, B.: The Craft of Information Visualization: Readings and Reflections. Morgan Kaufmann Publishers Inc., San Francisco (2003)"},{"key":"16_CR26","unstructured":"Jos\u00e9 Cardoso, C., Kacsuk, P.: Parallel Program development for cluster computing: methodology, tools and integrated environments. Vol. 5. Nova Publishers, Commack, NY, USA (2001)"},{"key":"16_CR27","volume-title":"Design for Information: An Introduction to the Histories, Theories, and Best Practices Behind Effective Information Visualizations","author":"I Meirelles","year":"2013","unstructured":"Meirelles, I.: Design for Information: An Introduction to the Histories, Theories, and Best Practices Behind Effective Information Visualizations. Rockport Publishers, Beverly (2013)"},{"key":"16_CR28","volume-title":"The Art Of Computer Systems Performance Analysis: Techniques For Experimental Design, Measurement","author":"R Jain","year":"1991","unstructured":"Jain, R.: The Art Of Computer Systems Performance Analysis: Techniques For Experimental Design, Measurement. Wiley, Hoboken (1991)"},{"key":"16_CR29","unstructured":"De Kergommeaux, J.C., Maillet, E., Vincent, J.: Monitoring parallel programs for performance tuning in cluster environments. In: Kacsuk, P., Cunha, J.C. (eds.) Parallel Program Development for Cluster Computing: Methodology, Tools and Integrated Environments (2001)"},{"key":"16_CR30","first-page":"1157","volume":"3","author":"I Guyon","year":"2003","unstructured":"Guyon, I., Elisseeff, A.: An introduction to variable and feature selection. J. Mach. Learn. Res. 3, 1157 (2003)","journal-title":"J. Mach. Learn. Res."},{"key":"16_CR31","unstructured":"Zaki, M., Obradovic, Z., Tan, P.N., Banerjee, A., Kamath, C., Parthasarathy S. (eds.): In: Proceedings of the 2014 SIAM International Conference on Data Mining. Society for Industrial and Applied Mathematics (2014)"},{"key":"16_CR32","unstructured":"Big data privacy workshop: Advancing the state of the art in technology and practice. http:\/\/web.mit.edu\/bigdata-priv\/ (2014)"},{"key":"16_CR33","unstructured":"Allasia, W., Bailer, W., Gordea, S., Chang, W.: A novel metadata standard for multimedia preservation. In: Proceedings of iPres (2014)"},{"key":"16_CR34","doi-asserted-by":"crossref","unstructured":"Chang, W.: Preliminary digital preservation interoperability framework (dpif) results. In: Archiving Conference, vol. 2010, pp. 202\u2013202. Society for Imaging, Science and Technology (2010)","DOI":"10.2352\/issn.2168-3204.2010.7.1.art00038"},{"key":"16_CR35","doi-asserted-by":"crossref","unstructured":"Chang, W.: Advanced digital image preservation data management architecture. In: Archiving Conference, vol. 2009, pp. 178\u2013182 Society for Imaging, Science and Technology (2009)","DOI":"10.2352\/issn.2168-3204.2009.6.1.art00038"},{"key":"16_CR36","unstructured":"Chang, W.: 1st ISO\/IEC JTC 1 study group on big data meeting. http:\/\/jtc1bigdatasg.nist.gov\/"},{"key":"16_CR37","unstructured":"Chang, W.: NIST special publication 1500-6 information technology laboratory: DRAFT NIST big data interoperability framework: volume 6, reference architecture. NIST, Gaithersburg, MD (2015)"},{"key":"16_CR38","unstructured":"Chang, W.: NIST big data public working group (NBD-PWG) request for public comment. http:\/\/bigdatawg.nist.gov\/V1_output_docs.php (2015)"},{"key":"16_CR39","unstructured":"Reynolds, D.: Speaker and language recognition: a guided safari. Keynote Speech Odyssey (2008). Accessed 15 Sept 2015"},{"key":"16_CR40","doi-asserted-by":"crossref","unstructured":"Doddington, G.: Automatic evaluation of machine translation quality using n-gram co-occurrence statistics, In: Proceedings of the Second International Conference on Human Language Technology Research, pp. 138\u2013145 (2002)","DOI":"10.3115\/1289189.1289273"},{"issue":"23","key":"16_CR41","first-page":"15","volume":"20","author":"M Przybocki","year":"2006","unstructured":"Przybocki, M., Martin, A.: NIST speaker recognition evaluation chronicles. Comput. Speech Lang. 20(23), 15 (2006)","journal-title":"Comput. Speech Lang."},{"key":"16_CR42","unstructured":"NIST open machine translation evaluation. http:\/\/nist.gov\/itl\/iad\/mig\/openmt15.cfm (2015)"},{"key":"16_CR43","unstructured":"NIST open machine translation evaluation. http:\/\/www.itl.nist.gov\/iad\/mig\/tests\/mt\/ (2001)"},{"key":"16_CR44","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Association for Computational Linguistics (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"16_CR45","unstructured":"NIST open handwriting recognition and translation evaluation (OpenHaRT). http:\/\/www.nist.gov\/itl\/iad\/mig\/hart.cfm (2010)"},{"key":"16_CR46","doi-asserted-by":"crossref","unstructured":"Dorr, B.J., Olive, J., McCary, J., Christanson, C.: Chapter 5: machine translation evaluation and optimization. In: Olive, J., Christianson, C., McCary, J. (eds.) Handbook of natural language processing and machine translation: DARPA global autonomous language exploitation, Springer, New York, pp. 745\u2013843 (2011)","DOI":"10.1007\/978-1-4419-7713-7_5"},{"issue":"3","key":"16_CR47","doi-asserted-by":"crossref","first-page":"S53","DOI":"10.1016\/j.jadohealth.2005.05.008","volume":"37","author":"K Gallagher","year":"2005","unstructured":"Gallagher, K., Stanley, A., Shearer, D., Klerman, L.V.: Challenges in data collection, analysis, and distribution of information in community coalition demonstration projects. J. Adolesc. Health 37(3), S53 (2005)","journal-title":"J. Adolesc. Health"},{"issue":"4","key":"16_CR48","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1109\/MCG.2003.1210860","volume":"23","author":"R Korsar","year":"2003","unstructured":"Korsar, R., Healey, C., Interrante, V., Laidlaw, D., Ware, C.: Thoughts on user studies: why, how, and when. Comput. Graph. Appl. 23(4), 20 (2003)","journal-title":"Comput. Graph. Appl."},{"issue":"9","key":"16_CR49","doi-asserted-by":"crossref","first-page":"1520","DOI":"10.1109\/TVCG.2011.279","volume":"18","author":"H Lam","year":"2012","unstructured":"Lam, H., Bertini, E., Isenberg, P., Plaisant, C., Carpendale, S.: Empirical studies in information visualization: seven scenarios. IEEE Trans. Vis. Comput. Graph. 18(9), 1520 (2012)","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"issue":"12","key":"16_CR50","doi-asserted-by":"crossref","first-page":"2818","DOI":"10.1109\/TVCG.2013.126","volume":"19","author":"T Isenberg","year":"2013","unstructured":"Isenberg, T., Isenberg, P., Chen, J., Sedlmair, M., Moller, T.: A systematic review on the practice of evaluating visualization. IEEE Trans. Vis. Comput. Graph. 19(12), 2818 (2013)","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"16_CR51","unstructured":"VAST challenge 2012. http:\/\/vacommunity.org\/VAST+Challenge+2012 (2012)"},{"key":"16_CR52","unstructured":"VAST challenge 2013. http:\/\/vacommunity.org\/VAST+Challenge+2013 (2013)"},{"key":"16_CR53","unstructured":"VAST challenge 2014. http:\/\/vacommunity.org\/VAST+Challenge+2013 (2014)"},{"key":"16_CR54","doi-asserted-by":"crossref","unstructured":"Harman, D.: Overview of the first text retrieval conference. In: Proceedings of the 16th Annual International ACM\/SIGIR Conference, pp. 36\u201348 (1993)","DOI":"10.1145\/160688.160692"},{"issue":"2","key":"16_CR55","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1145\/146565.146567","volume":"26","author":"D Harman","year":"1993","unstructured":"Harman, D.: The darpa tipster project. SIGIR Forum 26(2), 26 (1993)","journal-title":"SIGIR Forum"},{"key":"16_CR56","unstructured":"NIST TRECVid surveillance event detection evaluation. http:\/\/nist.gov\/itl\/iad\/mig\/sed.cfm (2015)"},{"key":"16_CR57","unstructured":"NIST TRECVid multimedia event detection evaluation. http:\/\/nist.gov\/itl\/iad\/mig\/med.cfm (2015)"},{"key":"16_CR58","unstructured":"Snover, M., Dorr, B.J., Schwartz, R., Micciulla, L., Makhoul, J.: A study of translation edit rate with targeted human annotation. In: Proceedings of Association for Machine Translation in the Americas. http:\/\/www.cs.umd.edu\/~snover\/tercom\/ (2006)"},{"key":"16_CR59","unstructured":"Sawade, C., Landwehr, N., Bickel, S., Scheffer, T.: Active risk estimation. In: Proceedings of the 27th International Conference on Machine Learning (ICML-10), pp. 951\u2013958 (2010)"},{"issue":"6","key":"16_CR60","doi-asserted-by":"crossref","first-page":"54","DOI":"10.1145\/2666680","volume":"58","author":"R Zafarani","year":"2015","unstructured":"Zafarani, R., Liu, H.: Evaluation without ground truth in social media research. Commun. ACM 58(6), 54 (2015)","journal-title":"Commun. ACM"},{"key":"16_CR61","unstructured":"NIST open handwriting recognition and translation evaluation (OpenHaRT). http:\/\/www.nist.gov\/itl\/iad\/mig\/hart.cfm (2013)"},{"key":"16_CR62","doi-asserted-by":"crossref","first-page":"1936","DOI":"10.1109\/TITS.2014.2305334","volume":"15","author":"S Yang","year":"2014","unstructured":"Yang, S., Kalpakis, K.: Detecting road traffic events by coupling multiple timeseries with a nonparametric bayesian method. IEEE Trans. Intell. Transp. Syst. 15, 1936 (2014)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"16_CR63","doi-asserted-by":"crossref","unstructured":"Yang, S., Kalpakis, K., Biem, A.: Spatio-temporal coupled bayesian robust principal component analysis for road traffic event detection. In: 16th International IEEE Conference on Intelligent Transportation Systems-(ITSC), pp. 392\u2013398. IEEE (2013)","DOI":"10.1109\/ITSC.2013.6728263"},{"key":"16_CR64","unstructured":"Waze. https:\/\/www.waze.com\/ (2015)"},{"key":"16_CR65","unstructured":"Illinois traffic alert system. http:\/\/www.iltrafficalert.com\/ (2015)"},{"key":"16_CR66","unstructured":"Twitraffic in uk. http:\/\/twitraffic.co.uk\/ (2015)"},{"key":"16_CR67","unstructured":"Wibisono, A., Sina, I., Ihsannuddin, M.A., Hafizh, A., Hardjono, B., Nurhadiyatna, A., Jatmiko, W., Mursanto, D.P.: Traffic intelligent system architecture based on social media information. In: International Conference on Advanced Computer Science and Information Systems (ICACSIS). Depok, Indonesia (2012)"},{"key":"16_CR68","doi-asserted-by":"crossref","unstructured":"Sakaki, T., Matsuo, Y., Yanagihara, T., Chandrasiri, N.P., Nawa, K.: Real-time event extraction for driving information from social sensors. In: Proceedings of the IEEE International Conference on Cyber Technology in Automation, Control and Intelligent Systems. Bangkok, Thailand (2012)","DOI":"10.1109\/CYBER.2012.6392557"},{"key":"16_CR69","unstructured":"Wang, D., Al-Rubaie, A., Davies, J., Clarke, S.S.: Traffic intelligent system architecture based on social media information. In: IEEE Symposium on Evolving and Autonomous Learning Systems (EALS). Orlando, FL (2014)"},{"key":"16_CR70","doi-asserted-by":"crossref","unstructured":"Liu, J., Wilson, A., Gunning, D.: Workflow-based human-in-the-loop data analytics. In: Proceedings of the 2014 Workshop on Human Centered Big Data Research, p. 49. ACM (2014)","DOI":"10.1145\/2609876.2609888"},{"key":"16_CR71","doi-asserted-by":"crossref","unstructured":"Chen, M., Floridi, L., Borgo, R.: What is visualization really for? In: Floridi, L., Phyllis, I. (eds.) The Philosophy of Information Quality, vol. 358 pp. 75\u201393. Springer, Cham (ZG), Switzerland (2014)","DOI":"10.1007\/978-3-319-07121-3_5"},{"key":"16_CR72","unstructured":"Kidder, K.L., Haring, J.M., Bishop, R.J., Trent, J.D., Pham, L.D.: System for automated workflow in a network management and operations system. US Patent 6,445,774 (2002)"},{"key":"16_CR73","unstructured":"The power of combining big data analytics with business process workflow. CGI Whitepaper, Montreal, Quebec, Canada (2013)"},{"key":"16_CR74","doi-asserted-by":"crossref","unstructured":"Rostoker, C., Wagner, A., Hoos, H.: A parallel workflow for real-time correlation and clustering of high-frequency stock market data. In: Parallel and Distributed Processing Symposium, 2007. IPDPS 2007. IEEE International, pp. 1\u201310. IEEE (2007)","DOI":"10.1109\/IPDPS.2007.370216"},{"key":"16_CR75","doi-asserted-by":"crossref","unstructured":"Yu, H., Qingwei, X., Bin, H., Jianyong, W.: An integrative software system for biomedical information analysis workflow. In: BioMedical Information Engineering, 2009. FBIE 2009. International Conference on Future, pp. 61\u201364. IEEE (2009)","DOI":"10.1109\/FBIE.2009.5405792"},{"key":"16_CR76","volume-title":"The Craft of Information Visualization: Readings and Reflections","author":"BB Bederson","year":"2003","unstructured":"Bederson, B.B., Shneiderman, B.: The Craft of Information Visualization: Readings and Reflections. Morgan Kaufmann, Burlington (2003)"},{"key":"16_CR77","volume-title":"Information Visualization: Perception for Design","author":"C Ware","year":"2012","unstructured":"Ware, C.: Information Visualization: Perception for Design. Elsevier, Amsterdam (2012)"},{"key":"16_CR78","unstructured":"Text REtrieval Conference. http:\/\/trec.nist.gov (2015)"},{"key":"16_CR79","unstructured":"Tassey, G., Rowe, B.R., Wood, D.W., Link, A.N., Simoni, D.A.: Economic impact assessment of NIST\u2019s Text REtrieval conference (TREC) program, Report prepared for National Institute of Technology (NIST) (2010)"},{"key":"16_CR80","unstructured":"Lott, J.N.: The quality control of the integrated surface hourly database. In: 84th American Meteorological Society Annual Meeting, vol. 7.8. American Meterological Society, Seattle, WA. http:\/\/www1.ncdc.noaa.gov\/pub\/data\/inventories\/ish-qc.pdf (2004)"},{"key":"16_CR81","doi-asserted-by":"crossref","unstructured":"Martin, A.F., Doddington, G.R., Kamm, T., Ordowski, M., Przybocki, M.A.: The DET curve in assessment of detection task performance. In: Fifth European Conference on Speech Communication and Technology, EUROSPEECH 1997. Rhodes, Greece. http:\/\/www.isca-speech.org\/archive\/eurospeech_1997\/e97_1895.html (1997)","DOI":"10.21437\/Eurospeech.1997-504"},{"key":"16_CR82","unstructured":"Marr, B.: Why only one of the 5 Vs of big data really matters. http:\/\/www.ibmbigdatahub.com\/blog\/why-only-one-5-vs-big-data-really-matters (2015)"},{"key":"16_CR83","unstructured":"McNulty, E.: Understanding big data, dataconomy. http:\/\/dataconomy.com\/seven-vs-big-data\/ (2014)"},{"key":"16_CR84","unstructured":"Laney, D.: 3D data management: Controlling data volume, velocity, variety. http:\/\/blogs.gartner.com\/doug-laney\/deja-vvvue-others-claiming-gartners-volume-velocity-variety-construct-for-big-data\/ (2001)"},{"key":"16_CR85","unstructured":"IBM. The four V\u2019s of big data. http:\/\/www.ibmbigdatahub.com\/infographic\/four-vs-big-data (2013)"},{"issue":"1","key":"16_CR86","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1609\/aimag.v36i1.2565","volume":"36","author":"CA Knoblock","year":"2015","unstructured":"Knoblock, C.A., Szekely, P.: Exploiting semantics for big data integration. AI Mag. 36(1), 25 (2015)","journal-title":"AI Mag."},{"issue":"1","key":"16_CR87","doi-asserted-by":"crossref","first-page":"65","DOI":"10.1609\/aimag.v36i1.2568","volume":"36","author":"J Pujara","year":"2015","unstructured":"Pujara, J., Miao, H., Getoor, L., Cohen, W.W.: Using semantics & statistics to turn data into knowledge. AI Mag. 36(1), 65 (2015)","journal-title":"AI Mag."},{"key":"16_CR88","unstructured":"Franklin, M.: Big data and data science: some hype but real opportunities. https:\/\/www.cise.ufl.edu\/content\/uf-informatics-institute-inaugural-symposium (2015)"},{"issue":"Suppl 8: S1","key":"16_CR89","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/1471-2164-15-S8-S1","volume":"15","author":"SS Morrison","year":"2014","unstructured":"Morrison, S.S., Pyzh, R., Jeon, M.S., Amaro, C., Roig, F.J., Baker-Austin, C., Oliver, J.D., Gibas, C.J.: Impact of analytic provenance in genome analysis. BMC Genomics 15(Suppl 8: S1), 1 (2014)","journal-title":"BMC Genomics"},{"key":"16_CR90","first-page":"29","volume":"4","author":"D George","year":"2005","unstructured":"George, D.: Understanding structural and semantic heterogeneity in the context of database schema integration. J. Dep. Comput. 4, 29 (2005)","journal-title":"J. Dep. Comput."},{"key":"16_CR91","unstructured":"Mittal, A., Goel, A.: Stock prediction using twitter sentiment analysis Standford University, CS229. http:\/\/cs229.stanford.edu\/proj2011\/GoelMittal-StockMarketPredictionUsingTwitterSentimentAnalysis.pdf (2012)"},{"key":"16_CR92","unstructured":"Doermann, D.: Visual media forensics: knowing when seeing is believing. https:\/\/www.cise.ufl.edu\/content\/uf-informatics-institute-inaugural-symposium (2015)"},{"issue":"3","key":"16_CR93","doi-asserted-by":"crossref","first-page":"22","DOI":"10.1002\/scin.2015.187003022","volume":"187","author":"TH Saey","year":"2015","unstructured":"Saey, T.H.: Big data studies come with replication challenges. Sci. News 187(3), 22 (2015)","journal-title":"Sci. News"},{"issue":"2","key":"16_CR94","doi-asserted-by":"crossref","first-page":"1","DOI":"10.2200\/S00362ED1V01Y201105DTM016","volume":"3","author":"D Suciu","year":"2011","unstructured":"Suciu, D., Olteanu, D., R\u00e9, C., Koch, C.: Probabilistic databases. Synth. Lect. Data Manag. 3(2), 1 (2011)","journal-title":"Synth. Lect. Data Manag."},{"key":"16_CR95","unstructured":"Foote, K.E.: The geographer\u2019s craft project. http:\/\/www.colorado.edu\/geography\/gcraft\/contents.html (2015)"},{"key":"16_CR96","doi-asserted-by":"crossref","unstructured":"Datta, A.: Privacy through accountability: A computer science perspective. In: International Conference on Distributed Computing and Internet Technology, pp. 43\u201349. Springer, Bhubaneswar, India (2014)","DOI":"10.1007\/978-3-319-04483-5_5"},{"key":"16_CR97","unstructured":"Meliou, A., Gatterbauer, W., Suciu, D.: Bringing provenance to its full potential using causal reasoning. TaPP, Crete, Greece (2011)"},{"key":"16_CR98","doi-asserted-by":"publisher","unstructured":"Buneman, P., Khanna, S., Tan, W.C.: Data provenance: some basic issues. In: Kapoor, S., Prasad S. (eds.) FST TCS 2000: Foundations of Software Technology and Theoretical Computer Science. Lecture Notes in Computer Science, vol. 1974, pp. 87\u201393. Springer, Berlin (2000). doi: 10.1007\/3-540-44450-5_6","DOI":"10.1007\/3-540-44450-5_6"},{"issue":"4","key":"16_CR99","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1561\/1900000006","volume":"1","author":"LC James Cheney","year":"2007","unstructured":"James Cheney, L.C., Tan, W.C.: Provenance in databases: why, how, and where. Found. Trends Databases 1(4), 379 (2007). doi: 10.1561\/1900000006","journal-title":"Found. Trends Databases"},{"issue":"3","key":"16_CR100","doi-asserted-by":"publisher","first-page":"31","DOI":"10.1145\/1084805.1084812","volume":"34","author":"YL Simmhan","year":"2005","unstructured":"Simmhan, Y.L., Plale, B., Gannon, D.: A survey of data provenance in e-science. SIGMOD Rec. 34(3), 31 (2005). doi: 10.1145\/1084805.1084812","journal-title":"SIGMOD Rec."},{"key":"16_CR101","doi-asserted-by":"crossref","DOI":"10.1057\/9781137379283","volume-title":"Predictive Analytics, Data Mining and Big Data: Myths, Misconceptions and Methods","author":"S Finlay","year":"2014","unstructured":"Finlay, S.: Predictive Analytics, Data Mining and Big Data: Myths, Misconceptions and Methods. Palgrave Macmillan, London (2014)"},{"key":"16_CR102","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1214\/09-SS057","volume":"3","author":"J Pearl","year":"2009","unstructured":"Pearl, J.: Causal inference in statistics: an overview. Stat. Surv. 3, 96 (2009). doi: 10.1214\/09-SS057","journal-title":"Stat. Surv."},{"issue":"2","key":"16_CR103","doi-asserted-by":"publisher","first-page":"77","DOI":"10.4018\/ijagr.2015040105","volume":"6","author":"J Gelernter","year":"2015","unstructured":"Gelernter, J., Carley, K.M.: Spatiotemporal network analysis and visualization. Int. J. Appl. Geospatial Res. 6(2), 77 (2015). doi: 10.4018\/ijagr.2015040105","journal-title":"Int. J. Appl. Geospatial Res."},{"issue":"1","key":"16_CR104","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/2945.981847","volume":"8","author":"DA Keim","year":"2002","unstructured":"Keim, D.A.: Information visualization and visual data mining. IEEE Trans. Vis. Comput. Graph. 8(1), 1 (2002). doi: 10.1109\/2945.981847","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"16_CR105","unstructured":"Fayyad, U., Wierse, A., Grinstein, G.: Information Visualization in Data Mining and Knowledge Discovery. The Morgan Kaufmann series in data management systems (Morgan Kaufmann, 2002)"},{"key":"16_CR106","volume-title":"Information Dashboard Design: Displaying Data for At-a-glance Monitoring","author":"S Few","year":"2013","unstructured":"Few, S.: Information Dashboard Design: Displaying Data for At-a-glance Monitoring. Analytics Press, Burlingame (2013)"},{"key":"16_CR107","doi-asserted-by":"crossref","unstructured":"Li, C., Aggarwal, C., Wang, J.: On anonymization of multi-graphs. In: Proceedings of the 2011 SIAM International Conference on Data Mining, Proceedings, pp. 711\u2013722. Society for Industrial and Applied Mathematics (2011)","DOI":"10.1137\/1.9781611972818.61"},{"key":"16_CR108","doi-asserted-by":"crossref","unstructured":"Tai, C.H., Philip, S.Y., Yang, D.N., Chen, M.S.: Structural diversity for privacy in publishing social networks. In: Liu, B., Liu, H., Clifton, C., Washio, T., Kamath, C. (eds.) Proceedings of the 2011 SIAM International Conference on Data Mining, pp. 35\u201346. Society for Industrial and Applied Mathematics, Philadelphia, PA (2011)","DOI":"10.1137\/1.9781611972818.4"}],"container-title":["International Journal of Data Science and Analytics"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-016-0016-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s41060-016-0016-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s41060-016-0016-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,4]],"date-time":"2025-06-04T12:35:38Z","timestamp":1749040538000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s41060-016-0016-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2016,8,4]]},"references-count":108,"journal-issue":{"issue":"3-4","published-print":{"date-parts":[[2016,11]]}},"alternative-id":["16"],"URL":"https:\/\/doi.org\/10.1007\/s41060-016-0016-z","relation":{},"ISSN":["2364-415X","2364-4168"],"issn-type":[{"type":"print","value":"2364-415X"},{"type":"electronic","value":"2364-4168"}],"subject":[],"published":{"date-parts":[[2016,8,4]]}}}