{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T20:51:49Z","timestamp":1757623909597,"version":"3.44.0"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783032020482"},{"type":"electronic","value":"9783032020499"}],"license":[{"start":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T00:00:00Z","timestamp":1755475200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T00:00:00Z","timestamp":1755475200000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-02049-9_29","type":"book-chapter","created":{"date-parts":[[2025,8,20]],"date-time":"2025-08-20T19:51:48Z","timestamp":1755719508000},"page":"363-380","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Classifying Public and\u00a0Private Documents Using Context-Based Predictions"],"prefix":"10.1007","author":[{"given":"Abrar Hasin","family":"Kamal","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6587-5313","authenticated-orcid":false,"given":"Anne V. D. M.","family":"Kayem","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,8,18]]},"reference":[{"key":"29_CR1","unstructured":"We Are Social & Meltwater: Digital 2024 Global Overview Report (2024). https:\/\/datareportal.com\/reports\/digital-2024-global-overview-report. Accessed 07 Oct 2024"},{"key":"29_CR2","unstructured":"Rydning, D.R.J.G.J., Reinsel, J., Gantz, J.: The digitization of the world from edge to core. Framingham: International Data Corporation, 16, 1\u201328 (2018)"},{"issue":"2","key":"29_CR3","first-page":"137","volume":"35","author":"A Gandomi","year":"2015","unstructured":"Gandomi, A., Haider, M.: Beyond the hype: Big data concepts, methods, and analytics. Int. J. Inf. Manage. 35(2), 137\u2013144 (2015)","journal-title":"Int. J. Inf. Manage."},{"key":"29_CR4","first-page":"433","volume":"49","author":"A Tsesis","year":"2014","unstructured":"Tsesis, A.: The right to erasure: privacy, data brokers, and the indefinite retention of data. Wake Forest L. Rev. 49, 433 (2014)","journal-title":"Wake Forest L. Rev."},{"key":"29_CR5","unstructured":"Poyraz, O.I., Bouazzaoui, S., Keskin, O., McShane, M., Pinto, C.A.: Cyber-assets at risk (CAR): the cost of personally identifiable information data breaches. In: In ICCWS 2020 15th International Conference on Cyber Warfare and Security, vol. 402, March 2020"},{"issue":"4","key":"29_CR6","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1109\/TDSC.2017.2698472","volume":"16","author":"Y Sei","year":"2017","unstructured":"Sei, Y., Okumura, H., Takenouchi, T., Ohsuga, A.: Anonymization of sensitive quasi-identifiers for l-diversity and t-closeness. IEEE Trans. Dependable Secure Comput. 16(4), 580\u2013593 (2017)","journal-title":"IEEE Trans. Dependable Secure Comput."},{"issue":"1","key":"29_CR7","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1093\/cybsec\/tyw003","volume":"2","author":"B Edwards","year":"2016","unstructured":"Edwards, B., Hofmeyr, S., Forrest, S.: Hype and heavy tails: a closer look at data breaches. J. Cybersecur. 2(1), 3\u201314 (2016)","journal-title":"J. Cybersecur."},{"key":"29_CR8","unstructured":"Zou, Y., Mhaidli, A. H., McCall, A., Schaub, F.: \u201c I\u2019ve Got Nothing to Lose\u201d: consumers\u2019 risk perceptions and protective actions after the Equifax data breach. In: Fourteenth Symposium on Usable Privacy and Security, SOUPS 2018, pp. 197\u2013216 (2018)"},{"key":"29_CR9","unstructured":"Ponemon Institute: Cost of a Data Breach 2024 (IBM) (2024)"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Sarjito, A.: Data security and privacy in the digital era: challenges for modern government. JIAN-Jurnal Ilmiah Administrasi Negara 8(3), 01\u201313 (2024)","DOI":"10.56071\/jian.v8i3.933"},{"key":"29_CR11","doi-asserted-by":"publisher","unstructured":"Teo, T.W., Choy, B.H.: STEM education in Singapore. In: Tan, O.S., Low, E.L., Tay, E.G., Yan, Y.K. (eds.) Singapore Math and Science Education Innovation. Empowering Teaching and Learning through Policies and Practice: Singapore and International Perspectives, vol. 1. Springer, Singapore (2021). https:\/\/doi.org\/10.1007\/978-981-16-1357-9_3","DOI":"10.1007\/978-981-16-1357-9_3"},{"key":"29_CR12","unstructured":"Enron Corp & Cohen, William W.: Enron Email Dataset. United States Federal Energy Regulatory Commissioniler, comp [Philadelphia, PA: William W. Cohen, MLD, CMU] [Software, E-Resource] Retrieved from the Library of Congress (2015). https:\/\/www.loc.gov\/item\/2018487913\/"},{"key":"29_CR13","unstructured":"Schwartz, P.M., Solove, D.J.: Pii 2.0: privacy and a new approach to personal information. Privacy and Security Law Report (2012)"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Ren, J., Rao, A., Lindorfer, M., Legout, A., Choffnes, D.: ReCon: revealing and controlling PII leaks in mobile network traffic. In: Proceedings of the 14th Annual International Conference on Mobile Systems, Applications, and Services, pp. 361\u2013374, June 2016","DOI":"10.1145\/2906388.2906392"},{"issue":"5","key":"29_CR15","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1080\/01930826.2019.1616973","volume":"59","author":"MD Rysavy","year":"2019","unstructured":"Rysavy, M.D., Michalak, R.: Data privacy and academic libraries: non-PII, PII, and librarians\u2019 reflections (Part 1). J. Libr. Adm. 59(5), 532\u2013547 (2019)","journal-title":"J. Libr. Adm."},{"key":"29_CR16","doi-asserted-by":"crossref","unstructured":"Voigt, P., Von dem Bussche, A.: The EU General Data Protection Regulation (GDPR). A Practical Guide, 1st edn. Springer, Cham (2017). 10(3152676), 10-5555","DOI":"10.1007\/978-3-319-57959-7"},{"key":"29_CR17","unstructured":"Office for Civil Rights: Summary of the HIPAA privacy rule (2003)"},{"key":"29_CR18","first-page":"1135","volume":"2","author":"D Jaar","year":"2008","unstructured":"Jaar, D., Zeller, P.E.: Canadian privacy law: the personal information protection and electronic documents act (PIPEDA). Int. In-House Counsel J. 2, 1135 (2008)","journal-title":"Int. In-House Counsel J."},{"key":"29_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"142","DOI":"10.1007\/978-3-540-88011-0_18","volume-title":"Cooperative Design, Visualization, and Engineering","author":"L Korba","year":"2008","unstructured":"Korba, L.: Private data discovery for privacy compliance in collaborative environments. In: Luo, Y. (ed.) CDVE 2008. LNCS, vol. 5220, pp. 142\u2013150. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-88011-0_18"},{"issue":"1","key":"29_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1140\/epjds\/s13688-022-00324-y","volume":"11","author":"L Bioglio","year":"2022","unstructured":"Bioglio, L., Pensa, R.G.: Analysis and classification of privacy-sensitive content in social media posts. EPJ Data Sci. 11(1), 1\u201324 (2022). https:\/\/doi.org\/10.1140\/epjds\/s13688-022-00324-y","journal-title":"EPJ Data Sci."},{"key":"29_CR21","unstructured":"Stillwell, D.J., Kosinski, M.: myPersonality Project website (2015)"},{"issue":"9","key":"29_CR22","doi-asserted-by":"publisher","first-page":"2365","DOI":"10.1007\/s10115-021-01592-2","volume":"63","author":"R Geetha","year":"2021","unstructured":"Geetha, R., Karthika, S., Kumaraguru, P.: Tweet-scan-post: a system for analysis of sensitive private data disclosure in online social media. Knowl. Inf. Syst. 63(9), 2365\u20132404 (2021). https:\/\/doi.org\/10.1007\/s10115-021-01592-2","journal-title":"Knowl. Inf. Syst."},{"key":"29_CR23","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"500","DOI":"10.1007\/978-3-319-06028-6_48","volume-title":"Advances in Information Retrieval","author":"G McDonald","year":"2014","unstructured":"McDonald, G., Macdonald, C., Ounis, I., Gollins, T.: Towards a classifier for digital sensitivity review. In: de Rijke, M., et al. (eds.) ECIR 2014. LNCS, vol. 8416, pp. 500\u2013506. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-06028-6_48"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"McDonald, G., Macdonald, C., Ounis, I.: Using part-of-speech n-grams for sensitive-text classification. In: Proceedings of the 2015 International Conference on the Theory of Information Retrieval, pp. 381\u2013384, September 2015","DOI":"10.1145\/2808194.2809496"},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"Tesfay, W. B., Serna, J., Rannenberg, K.: PrivacyBot: detecting privacy sensitive information in unstructured texts. In: 2019 Sixth International Conference on Social Networks Analysis, Management and Security (SNAMS), pp. 53\u201360. IEEE, October 2019","DOI":"10.1109\/SNAMS.2019.8931855"},{"key":"29_CR26","doi-asserted-by":"crossref","unstructured":"Aisopos, F., Papadakis, G., Tserpes, K., Varvarigou, T.: Content vs. context for sentiment analysis: a comparative analysis over microblogs. In: Proceedings of the 23rd ACM Conference on Hypertext and Social Media, pp. 187\u2013196, June 2012","DOI":"10.1145\/2309996.2310028"},{"key":"29_CR27","unstructured":"Cyber Security Intelligence: British railway passengers attacked. Cyber Security Intelligence, 27 September 2024. https:\/\/www.cybersecurityintelligence.com\/blog\/british-railway-passengers-attacked-7979.html"},{"key":"29_CR28","unstructured":"Shetty, J., Adibi, J.: The Enron email dataset database schema and brief statistical report. Inf. Sci. Inst. Tech. Rep. Univ. Southern California 4(1), 120\u2013128 (2004)"},{"key":"29_CR29","unstructured":"Litel, A.: Tweets of Congress. GitHub (2020). https:\/\/github.com\/alexlitel\/congresstweets. Accessed 3 Nov 2024"},{"key":"29_CR30","unstructured":"Tkachenko, M., Malyuk, M., Holmanyuk, A., Liubimov, N.: Label studio: data labeling software (2020). https:\/\/github.com\/heartexlabs\/label-studio"},{"key":"29_CR31","unstructured":"Wasserman, L.: All of Statistics: A Concise Course in Statistical Inference. Springer, New York (2010). ISBN: 9781441923226 1441923225"}],"container-title":["Lecture Notes in Computer Science","Database and Expert Systems Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-02049-9_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T09:50:19Z","timestamp":1757411419000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-02049-9_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,18]]},"ISBN":["9783032020482","9783032020499"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-02049-9_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,8,18]]},"assertion":[{"value":"18 August 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"DEXA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Database and Expert Systems Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bangkok","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Thailand","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"36","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"dexa2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.dexa.org\/2025\/dexa2025.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}