{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T08:11:02Z","timestamp":1778573462460,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":51,"publisher":"ACM","license":[{"start":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T00:00:00Z","timestamp":1742860800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,3,25]]},"DOI":"10.1145\/3709025.3712215","type":"proceedings-article","created":{"date-parts":[[2025,3,13]],"date-time":"2025-03-13T18:20:11Z","timestamp":1741890011000},"page":"55-63","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Multilingual Scraper of Privacy Policies and Terms of Service"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-6700-7607","authenticated-orcid":false,"given":"David","family":"Bernhard","sequence":"first","affiliation":[{"name":"ETH Zurich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3769-7961","authenticated-orcid":false,"given":"Luka","family":"Nenadic","sequence":"additional","affiliation":[{"name":"ETH Zurich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6259-2238","authenticated-orcid":false,"given":"Stefan","family":"Bechtold","sequence":"additional","affiliation":[{"name":"ETH Zurich"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7419-2784","authenticated-orcid":false,"given":"Karel","family":"Kubicek","sequence":"additional","affiliation":[{"name":"ETH Zurich, Inria"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,3,25]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.56553\/popets-2023-0074"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3442381.3450048"},{"key":"e_1_3_2_1_3_1","volume-title":"Tristan Dhellemmes, Abhilasha Ravichander, Peter Story, Jasmine Mangat, Rex Chen, Martin Degeling","author":"Arora Siddhant","year":"2022","unstructured":"Siddhant Arora, Henry Hosseini, Christine Utz, Vinayshekhar Bannihatti Kumar, Tristan Dhellemmes, Abhilasha Ravichander, Peter Story, Jasmine Mangat, Rex Chen, Martin Degeling, Thomas Norton, Thomas Hupperich, Shomir Wilson, and Norman Sadeh. 2022. A Tale of two regulatory Rrgimes: Creation and analysis of a bilingual privacy policy corpus. In Proceedings of the Thirteenth Language Resources and Evaluation Conference, Nicoletta Calzolari, Fr\u00e9d\u00e9ric B\u00e9chet, Philippe Blache, Khalid Choukri, Christopher Cieri, Thierry Declerck, Sara Goggi, Hitoshi Isahara, Bente Maegaard, Joseph Mariani, H\u00e9l\u00e8ne Mazo, Jan Odijk, and Stelios Piperidis (Eds.). European Language Resources Association, Marseille, FR, 5460--5472. https:\/\/aclanthology.org\/2022.lrec-1.585"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","unstructured":"Dimitris Asimopoulos Ilias Siniosoglou Vasileios Argyriou Thomai Karamitsou Eleftherios Fountoukidis Sotirios K. Goudos Ioannis D. Moscholios Konstantinos E. Psannis and Panagiotis Sarigiannidis. 2024. Benchmarking advanced text anonymisation methods: A comparative study on novel and traditional approaches. https:\/\/doi.org\/10.48550\/arXiv.2404.14465","DOI":"10.48550\/arXiv.2404.14465"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1086\/674424"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-49028-7_9"},{"key":"e_1_3_2_1_7_1","first-page":"893","article-title":"Messy contracts","volume":"3","author":"Benoliel Uri","year":"2024","unstructured":"Uri Benoliel and Shmuel I. Becher. 2024. Messy contracts. University of Illinois Law Review 3 (2024), 893--938. https:\/\/illinoislawreview.org\/wp-content\/uploads\/2024\/07\/Benoliel.pdf","journal-title":"University of Illinois Law Review"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-36096-1_8"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1093\/jla\/laad001"},{"key":"e_1_3_2_1_10_1","first-page":"662","article-title":"Contracting for personal data","volume":"94","author":"Davis Kevin E","year":"2019","unstructured":"Kevin E Davis and Florencia Marotta-Wurgler. 2019. Contracting for personal data. New York University Law Review 94 (2019), 662--705. https:\/\/www.nyulawreview.org\/issues\/volume-94-number-4\/contracting-for-personal-data\/","journal-title":"New York University Law Review"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1177\/2755323X241237619"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2019.23378"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512214"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2407.16615"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.nllp-1.1"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3106426.3106427"},{"key":"e_1_3_2_1_17_1","first-page":"1155","article-title":"Cost-based California Effects","volume":"39","author":"Frankenreiter Jens","year":"2022","unstructured":"Jens Frankenreiter. 2022. Cost-based California Effects. Yale Journal on Regulation 39 (2022), 1155. https:\/\/www.yalejreg.com\/print\/cost-based-california-effects\/","journal-title":"Yale Journal on Regulation"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","unstructured":"Andrea Galassi Kasper Drazewski Marco Lippi and Paolo Torroni. 2020. Cross-lingual annotation projection in legal texts. In Proceedings of the 28th International Conference on Computational Linguistics Donia Scott Nuria Bel and Chengqing Zong (Eds.). International Committee on Computational Linguistics Barcelona Spain (Online) 915--926. https:\/\/doi.org\/10.18653\/v1\/2020.coling-main.79","DOI":"10.18653\/v1\/2020.coling-main.79"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Neel Guha Julian Nyarko Daniel Ho Christopher R\u00e9 Adam Chilton Aditya Narayana Alex Chohlas-Wood Austin Peters Brandon Waldon Daniel Rockmore Diego Zambrano Dmitry Talisman Enam Hoque Faiz Surani Frank Fagan Galit Sarfaty Gregory Dickinson Haggai Porat Jason Hegland Jessica Wu Joe Nudell Joel Niklaus John Nay Jonathan Choi Kevin Tobia Margaret Hagan Megan Ma Michael Livermore Nikon Rasumov-Rahe Nils Holzenberger Noam Kolt Peter Henderson Sean Rehaag Sharad Goel Shang Gao Spencer Williams Sunny Gandhi Tom Zur Varun Iyer and Zehua Li. 2023. LegalBench: A collaboratively built benchmark for measuring legal reasoning in large language models. https:\/\/digitalcommons.osgoode.yorku.ca\/all_papers\/380","DOI":"10.2139\/ssrn.4583531"},{"key":"e_1_3_2_1_20_1","volume-title":"27th USENIX Security Symposium (USENIX Security 18)","author":"Harkous Hamza","year":"2018","unstructured":"Hamza Harkous, Kassem Fawaz, R\u00e9mi Lebret, Florian Schaub, Kang G. Shin, and Karl Aberer. 2018. Polisis: Automated analysis and presentation of privacy policies using deep learning. In 27th USENIX Security Symposium (USENIX Security 18). USENIX Association, Baltimore, MD, 531--548. https:\/\/www.usenix.org\/conference\/usenixsecurity18\/presentation\/harkous"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.2478\/popets-2021-0081"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.56553\/popets-2024-0058"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.15779\/Z382B8VC90"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3466722"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10603-022-09520-9"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1387"},{"key":"e_1_3_2_1_27_1","volume-title":"Proceedings of the Third Workshop on Automated Semantic Analysis of Information in Legal Text. RWTH Aachen","author":"Liepin R.","year":"2019","unstructured":"R. Liepin, a, Giuseppe Contissa, K. Drazewski, F. Lagioia, Marco Lippi, H. Micklitz, Przemyslaw Palka, G. Sartor, and Paolo Torroni. 2019. GDPR privacy policies in CLAUDETTE: Challenges of omission, context and multilingualism. In Proceedings of the Third Workshop on Automated Semantic Analysis of Information in Legal Text. RWTH Aachen, Montreal, CA, 1--7. https:\/\/www.semanticscholar.org\/paper\/GDPR-Privacy-Policies-in-CLAUDETTE%3A-Challenges-of-Liepi%C5%86a-Contissa\/fc2daaa4171db92bd30cc67199374cda06b562ca"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.2478\/popets-2020-0004"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.3233\/978-1-61499-838-9-145"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10506-019-09243-2"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-19-7513-4_2"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1086\/689753"},{"key":"e_1_3_2_1_33_1","first-page":"240","article-title":"Set in stone? Change and innovation in consumer standard-form contracts","volume":"88","author":"Marotta-Wurgler Florencia","year":"2013","unstructured":"Florencia Marotta-Wurgler and Robert Taylor. 2013. Set in stone? Change and innovation in consumer standard-form contracts. New York University Law Review 88 (2013), 240--285. https:\/\/www.nyulawreview.org\/wp-content\/uploads\/2018\/08\/NYULawReview-88-1-MarottaWurgler-Taylor.pdf","journal-title":"New York University Law Review"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.56553\/popets-2023-0111"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10603-017-9353-0"},{"key":"e_1_3_2_1_36_1","volume-title":"Presidio: Data Protection and De-identification SDK. https:\/\/github.com\/microsoft\/presidio\/ Accessed: 2025-01-14.","year":"2025","unstructured":"Microsoft. 2025. Presidio: Data Protection and De-identification SDK. https:\/\/github.com\/microsoft\/presidio\/ Accessed: 2025-01-14."},{"key":"e_1_3_2_1_37_1","volume-title":"Heterogeneous Data Management, Polystores, and Analytics for Healthcare","author":"Mohan Jayashree","unstructured":"Jayashree Mohan, Melissa Wasserman, and Vijay Chidambaram. 2019. Analyzing GDPR compliance through the lens of privacy policy. In Heterogeneous Data Management, Polystores, and Analytics for Healthcare, Vijay Gadepally, Timothy Mattson, Michael Stonebraker, Fusheng Wang, Gang Luo, Yanhui Laing, and Alevtina Dubovitskaya (Eds.). Springer International Publishing, Cham, 82--95."},{"key":"e_1_3_2_1_38_1","volume-title":"How many websites are there in the world?","author":"Nick Huss","year":"2024","unstructured":"Huss Nick. 2024. How many websites are there in the world? (2024). https:\/\/siteefy.com\/how-many-websites-are-there\/"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1080\/1369118X.2018.1486870"},{"key":"e_1_3_2_1_40_1","volume-title":"The End of Ownership: Personal Property in the Digital Economy","author":"Perzanowski Aaron","unstructured":"Aaron Perzanowski and Jason Schultz. 2016. The End of Ownership: Personal Property in the Digital Economy. MIT Press, Cambridge, MA."},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1287\/mksc.2021.1339"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3517745.3561444"},{"key":"e_1_3_2_1_43_1","volume-title":"Aleecia M McDonald, Joel R Reidenberg, Noah A Smith, Fei Liu, N Cameron Russell, Florian Schaub, et al.","author":"Sadeh Norman","year":"2013","unstructured":"Norman Sadeh, Alessandro Acquisti, Travis D Breaux, Lorrie Faith Cranor, Aleecia M McDonald, Joel R Reidenberg, Noah A Smith, Fei Liu, N Cameron Russell, Florian Schaub, et al. 2013. Usable privacy policy project. In Technical report, Technical Report, CMU-ISR-13-119. Carnegie Mellon University, Pittsburgh, Pennsylvania. https:\/\/usableprivacy.org\/data"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.15779\/Z38HT2GC9C"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.2307\/1339552"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.532"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3613904.3642597"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1145\/3590152"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1126"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3389685"},{"key":"e_1_3_2_1_51_1","first-page":"66","volume-title":"Proceedings on Privacy Enhancing Technologies 2019","author":"Zimmeck Sebastian","year":"2019","unstructured":"Sebastian Zimmeck, Peter Story, Daniel Smullen, Abhilasha Ravichander, Ziqi Wang, Joel R. Reidenberg, N. Cameron Russell, and Norman M. Sadeh. 2019. MAPS: Scaling privacy compliance analysis to a million apps. Proceedings on Privacy Enhancing Technologies 2019 (2019), 66 - 86."}],"event":{"name":"CSLAW '25: Symposium on Computer Science and Law","location":"Munich Germany","acronym":"CSLAW '25","sponsor":["ACM Association for Computing Machinery"]},"container-title":["Proceedings of the Symposium on Computer Science and Law on ZZZ"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3709025.3712215","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3709025.3712215","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T19:47:40Z","timestamp":1756237660000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3709025.3712215"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3,25]]},"references-count":51,"alternative-id":["10.1145\/3709025.3712215","10.1145\/3709025"],"URL":"https:\/\/doi.org\/10.1145\/3709025.3712215","relation":{},"subject":[],"published":{"date-parts":[[2025,3,25]]},"assertion":[{"value":"2025-03-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}