{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,6]],"date-time":"2026-01-06T13:42:35Z","timestamp":1767706955027},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2022,9,12]],"date-time":"2022-09-12T00:00:00Z","timestamp":1662940800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,9,12]],"date-time":"2022-09-12T00:00:00Z","timestamp":1662940800000},"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":["Front. Comput. Sci."],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1007\/s11704-022-1627-2","type":"journal-article","created":{"date-parts":[[2022,9,12]],"date-time":"2022-09-12T09:02:56Z","timestamp":1662973376000},"update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["APPCorp: a corpus for Android privacy policy document structure analysis"],"prefix":"10.1007","volume":"17","author":[{"given":"Shuang","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Baiyang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Renjie","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Meishan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,9,12]]},"reference":[{"issue":"3","key":"1627_CR1","first-page":"543","volume":"4","author":"A M McDonald","year":"2008","unstructured":"McDonald A M, Cranor L F. The cost of reading privacy policies. A Journal of Law and Policy for the Information Society, 2008, 4(3): 543\u2013568","journal-title":"A Journal of Law and Policy for the Information Society"},{"key":"1627_CR2","volume-title":"Towards automatic classification of privacy policy text","author":"F Liu","year":"2018","unstructured":"Liu F, Wilson S, Story P, Zimmeck S, Sadeh N. Towards automatic classification of privacy policy text. Pittsburgh: School of Computer Science, Carnegie Mellon University, 2018"},{"key":"1627_CR3","doi-asserted-by":"crossref","unstructured":"Wilson S, Schaub F, Dara A A, Liu F, Cherivirala S, Leon P G, Andersen M S, Zimmeck S, Sathyendra K M, Russell N C, Norton T B, Hovy E, Reidenberg J, Sadeh N. The creation and analysis of a website privacy policy corpus. In: Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics. 2016, 1330\u20131340","DOI":"10.18653\/v1\/P16-1126"},{"issue":"3","key":"1627_CR4","doi-asserted-by":"publisher","first-page":"66","DOI":"10.2478\/popets-2019-0037","volume":"2019","author":"S Zimmeck","year":"2019","unstructured":"Zimmeck S, Story P, Smullen D, Ravichander A, Wang Z Q, Reidenberg J, Russell N C, Sadeh N. MAPS: scaling privacy compliance analysis to a million apps. Proceedings on Privacy Enhancing Technologies, 2019, 2019(3): 66\u201386","journal-title":"Proceedings on Privacy Enhancing Technologies"},{"key":"1627_CR5","doi-asserted-by":"crossref","unstructured":"Lebanoff L, Liu F. Automatic detection of vague words and sentences in privacy policies. In: Proceedings of 2018 Conference on Empirical Methods in Natural Language Processing. 2018, 3508\u20133517","DOI":"10.18653\/v1\/D18-1387"},{"issue":"5\u20136","key":"1627_CR6","first-page":"260","volume":"27","author":"J Kaur","year":"2018","unstructured":"Kaur J, Dara R A, Obimbo C, Song F, Menard K. A comprehensive keyword analysis of online privacy policies. Information Security Journal: A Global Perspective, 2018, 27(5\u20136): 260\u2013275","journal-title":"Information Security Journal: A Global Perspective"},{"key":"1627_CR7","doi-asserted-by":"crossref","unstructured":"Sarne D, Schler J, Singer A, Sela A, Bar Siman Tov I. Unsupervised topic extraction from privacy policies. In: Proceedings of 2019 World Wide Web Conference. 2019, 563\u2013568","DOI":"10.1145\/3308560.3317585"},{"issue":"3","key":"1627_CR8","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/BF00994018","volume":"20","author":"C Cortes","year":"1995","unstructured":"Cortes C, Vapnik V. Support-vector networks. Machine Learning, 1995, 20(3): 273\u2013297","journal-title":"Machine Learning"},{"key":"1627_CR9","doi-asserted-by":"crossref","unstructured":"Yang Z, Yang D, Dyer C, He X, Smola A, Hovy E. Hierarchical attention networks for document classification. In: Proceedings of 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2016, 1480\u20131489","DOI":"10.18653\/v1\/N16-1174"},{"key":"1627_CR10","unstructured":"Sathyendra K M, Wilson S, Schaub F, Zimmeck S, Sadeh N. Identifying the provision of choices in privacy policy text. In: Proceedings of 2017 Conference on Empirical Methods in Natural Language Processing. 2017, 2774\u20132779"},{"key":"1627_CR11","unstructured":"Kumar V B, Iyengar R, Nisal N, Feng Y, Habib H, Story P, Cherivirala S, Hagan M, Cranor L, Wilson S, Schaub F, Sadeh N. Finding a choice in a haystack: automatic extraction of opt-out statements from privacy policy text. In: Proceedings of Web Conference 2020. 2020, 1943\u20131954"},{"key":"1627_CR12","unstructured":"Liu F, Ramanath R, Sadeh N, Smith N A. A step towards usable privacy policy: automatic alignment of privacy statements. In: Proceedings of COLING 2014, the 25th International Conference on Computational Linguistics: Technical Papers. 2014, 884\u2013894"},{"key":"1627_CR13","doi-asserted-by":"crossref","unstructured":"Tesfay W B, Hofmann P, Nakamura T, Kiyomoto S, Serna J. I read but don\u2019t agree: privacy policy benchmarking using machine learning and the EU GDPR. In: Proceedings of Web Conference 2018. 2018, 163\u2013166","DOI":"10.1145\/3184558.3186969"},{"key":"1627_CR14","doi-asserted-by":"crossref","unstructured":"Ravichander A, Black A W, Wilson S, Norton T, Sadeh N. Question answering for privacy policies: combining computational and legal perspectives. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing. 2019, 4947\u20134958","DOI":"10.18653\/v1\/D19-1500"},{"key":"1627_CR15","unstructured":"Kumar V B, Ravichander A, Story S, Sadeh N. Quantifying the effect of in-domain distributed word representations: a study of privacy policies. In: Proceedings of AAAI Spring Symposium on Privacy-Enhancing Artificial Intelligence and Language Technologies. 2019"},{"key":"1627_CR16","doi-asserted-by":"crossref","unstructured":"Pennington J, Socher R, Manning C. GloVe: global vectors for word representation. In: Proceedings of 2014 Conference on Empirical Methods in Natural Language Processing. 2014, 1532\u20131543","DOI":"10.3115\/v1\/D14-1162"},{"key":"1627_CR17","doi-asserted-by":"crossref","unstructured":"Zimmeck S, Wang Z, Zou L, Iyengar R, Liu B, Schaub F, Wilson S, Sadeh N, Bellovin S, Reidenberg J. Automated analysis of privacy requirements for mobile apps. In: Proceedings of 2016 AAAI Fall Symposium Series. 2016","DOI":"10.14722\/ndss.2017.23034"},{"key":"1627_CR18","doi-asserted-by":"crossref","unstructured":"Chang C, Li H, Zhang Y, Du S, Cao H, Zhu H. Automated and personalized privacy policy extraction under GDPR consideration. In: Proceedings of the 14th International Conference on Wireless Algorithms, Systems, and Applications. 2019, 43\u201354","DOI":"10.1007\/978-3-030-23597-0_4"},{"key":"1627_CR19","doi-asserted-by":"crossref","unstructured":"Liu S, Zhao B, Guo R, Meng G, Zhang F, Zhang M. Have you been properly notified? Automatic compliance analysis of privacy policy text with GDPR article. In: Proceedings of Web Conference 2021. 2021, 2154\u20132164","DOI":"10.1145\/3442381.3450022"},{"issue":"5","key":"1627_CR20","doi-asserted-by":"publisher","first-page":"345","DOI":"10.1007\/s00287-019-01201-1","volume":"42","author":"M Degeling","year":"2019","unstructured":"Degeling M, Utz C, Lentzsch C, Hosseini H, Schaub F, Holz T. We value your privacy\u2026 now take some cookies: measuring the GDPR\u2019s impact on web privacy. Informatik Spektrum, 2019, 42(5): 345\u2013346","journal-title":"Informatik Spektrum"},{"key":"1627_CR21","doi-asserted-by":"crossref","unstructured":"Yang J, Zhang Y, Li L, Li X. YEDDA: a lightweight collaborative text span annotation tool. In: Proceedings of ACL 2018, System Demonstrations. 2018, 31\u201336","DOI":"10.18653\/v1\/P18-4006"},{"issue":"5","key":"1627_CR22","doi-asserted-by":"publisher","first-page":"378","DOI":"10.1037\/h0031619","volume":"76","author":"J L Fleiss","year":"1971","unstructured":"Fleiss J L. Measuring nominal scale agreement among many raters. Psychological Bulletin, 1971, 76(5): 378\u2013382","journal-title":"Psychological Bulletin"},{"key":"1627_CR23","unstructured":"Wang S, Manning C. Baselines and bigrams: simple, good sentiment and topic classification. In: Proceedings of the 50th Annual Meeting of the Association for Computational Linguistics. 2012, 90\u201394"},{"key":"1627_CR24","unstructured":"Ramos J. Using TF-IDF to determine word relevance in document queries. In: Proceedings of the 1st Instructional Conference on Machine Learning. 2003, 29\u201348"},{"key":"1627_CR25","doi-asserted-by":"crossref","unstructured":"Graves A, Jaitly N, Mohamed A R. Hybrid speech recognition with deep bidirectional LSTM. In: Proceedings of 2013 IEEE Workshop on Automatic Speech Recognition and Understanding. 2013, 273\u2013278","DOI":"10.1109\/ASRU.2013.6707742"},{"key":"1627_CR26","unstructured":"Mikolov T, Sutskever I, Chen K, Corrado G, Dean J. Distributed representations of words and phrases and their compositionality. In: Proceedings of the 26th International Conference on Neural Information Processing Systems. 2013, 3111\u20133119"},{"key":"1627_CR27","unstructured":"Devlin J, Chang M W, Lee K, Toutanova K. BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1. 2019, 4171\u20134186"},{"key":"1627_CR28","doi-asserted-by":"crossref","unstructured":"Sun C, Qiu X, Xu Y, Huang X. How to Fine-tune BERT for text classification? In: Proceedings of the 18th China National Conference on Chinese Computational Linguistics. 2019, 194\u2013206","DOI":"10.1007\/978-3-030-32381-3_16"},{"key":"1627_CR29","unstructured":"Veli\u010dkovi\u0107 P, Cucurull G, Casanova A, Romero A, Li\u00f2 P, Bengio Y. Graph attention networks. 2017, arXiv preprint arXiv: 1710.10903"},{"key":"1627_CR30","doi-asserted-by":"crossref","unstructured":"Cho K, Van Merri\u00ebnboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y. Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of 2014 Conference on Empirical Methods in Natural Language Processing. 2014, 1724\u20131734","DOI":"10.3115\/v1\/D14-1179"},{"key":"1627_CR31","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa F, Varoquaux G, Gramfort A, Michel V, Thirion B, Grisel O, Blondel M, Prettenhofer P, Weiss R, Dubourg V, Vanderplas J, Passos A, Cournapeau D, Brucher M, Perrot M, Duchesnay \u00c9. Scikit-learn: machine learning in python. The Journal of Machine Learning Research, 2011, 12: 2825\u20132830","journal-title":"The Journal of Machine Learning Research"},{"key":"1627_CR32","unstructured":"Fey M, Lenssen J E. Fast graph representation learning with PyTorch Geometric. 2019, arXiv preprint arXiv: 1903.02428"},{"key":"1627_CR33","unstructured":"Kingma D P, Ba J. Adam: a method for stochastic optimization. 2017, arXiv preprint arXiv: 1412.6980"}],"container-title":["Frontiers of Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-022-1627-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11704-022-1627-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11704-022-1627-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,19]],"date-time":"2024-07-19T20:27:39Z","timestamp":1721420859000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11704-022-1627-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,12]]},"references-count":33,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,6]]}},"alternative-id":["1627"],"URL":"https:\/\/doi.org\/10.1007\/s11704-022-1627-2","relation":{},"ISSN":["2095-2228","2095-2236"],"issn-type":[{"value":"2095-2228","type":"print"},{"value":"2095-2236","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9,12]]},"assertion":[{"value":"4 November 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 February 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"12 September 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}],"article-number":"173320"}}