Unsupervised Alignment of Privacy Policies using Hidden Markov Models

Ramanath, Rohan; Liu, Fei; Sadeh, Norman; Smith, Noah A.

doi:10.3115/v1/p14-2099

Cited by 45 publications

(26 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Chapter III of the GDPR describes the rights of the data subjects; the first (Article 12) is the right to be informed about the service provider's privacy practices "in a concise, transparent, intelligible and easily accessible form, using clear and plain language." The service provider has to communicate its practices regarding data collection and sharing (Articles 13 and 14) as well as the rights of users associated with data collection and processing (Articles [15][16][17][18][19][20][21][22].…”

Section: Gdpr Backgroundmentioning

confidence: 99%

“…The data used to train the classifier was composed of (1) a set of 1,000 privacy policies labeled as valid from the ACL/COLING 2014 privacy policies' dataset released by Ramanath et al [21] and (2) an invalid set consisting of the text from 1,000 web pages, fetched from random links within the homepages of the top 500 Alexa websites. We ensured that the latter pages do not have any of the keywords associated with privacy policies in their URL or title.…”

Section: A Policy Classifier Architecturementioning

confidence: 99%

See 1 more Smart Citation

The Privacy Policy Landscape After the GDPR

Lindén¹,

Khandelwal²,

Harkous

et al. 2020

Proceedings on Privacy Enhancing Technologies

114

View full text Add to dashboard Cite

The EU General Data Protection Regulation (GDPR) is one of the most demanding and comprehensive privacy regulations of all time. A year after it went into effect, we study its impact on the landscape of privacy policies online. We conduct the first longitudinal, in-depth, and at-scale assessment of privacy policies before and after the GDPR. We gauge the complete consumption cycle of these policies, from the first user impressions until the compliance assessment. We create a diverse corpus of two sets of 6,278 unique English-language privacy policies from inside and outside the EU, covering their pre-GDPR and the post-GDPR versions. The results of our tests and analyses suggest that the GDPR has been a catalyst for a major overhaul of the privacy policies inside and outside the EU. This overhaul of the policies, manifesting in extensive textual changes, especially for the EU-based websites, comes at mixed benefits to the users. While the privacy policies have become considerably longer, our user study with 470 participants on Amazon MTurk indicates a significant improvement in the visual representation of privacy policies from the users' perspective for the EU websites. We further develop a new workflow for the automated assessment of requirements in privacy policies. Using this workflow, we show that privacy policies cover more data practices and are more consistent with seven compliance requirements post the GDPR. We also assess how transparent the organizations are with their privacy practices by performing specificity analysis. In this analysis, we find evidence for positive changes triggered by the GDPR, with the specificity level improving on average. Still, we find the landscape of privacy policies to be in a transitional phase; many policies still do not meet several key GDPR requirements or their improved coverage comes with reduced specificity.

show abstract

Section: Gdpr Backgroundmentioning

confidence: 99%

Section: A Policy Classifier Architecturementioning

confidence: 99%

The Privacy Policy Landscape After the GDPR

Lindén¹,

Khandelwal²,

Harkous

et al. 2020

Proceedings on Privacy Enhancing Technologies

114

View full text Add to dashboard Cite

show abstract

“…Montemagni et al (2010) investigate the peculiarities of the language in legal text with respect to that in ordinary text by applying shallow parsing. Ramanath et al (2014) in-troduce an unsupervised model for the automatic alignment of privacy policies and show that Hidden Markov Models are more effective than clustering and topic models. Liu et al (2016a) modelled the language of vagueness in privacy policies using deep neural networks.…”

Section: Related Workmentioning

confidence: 99%

Identifying the Provision of Choices in Privacy Policy Text

Sathyendra

Wilson²,

Schaub

et al. 2017

Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing

Self Cite

View full text Add to dashboard Cite

Websites' and mobile apps' privacy policies, written in natural language, tend to be long and difficult to understand. Information privacy revolves around the fundamental principle of notice and choice, namely the idea that users should be able to make informed decisions about what information about them can be collected and how it can be used. Internet users want control over their privacy, but their choices are often hidden in long and convoluted privacy policy documents. Moreover, little (if any) prior work has been done to detect the provision of choices in text. We address this challenge of enabling user choice by automatically identifying and extracting pertinent choice language in privacy policies. In particular, we present a two-stage architecture of classification models to identify opt-out choices in privacy policy text, labelling common varieties of choices with a mean F1 score of 0.735. Our techniques enable the creation of systems to help Internet users to learn about their choices, thereby effectuating notice and choice and improving Internet privacy.

show abstract

“…Costante et al [7] use text classification to estimate a policy's completeness based on topic coverage. Other approaches have applied topic modeling to privacy policies [6,29] and have automatically grouped related sections and paragraphs of privacy policies [15,24]. Since the complexity and vagueness of privacy policy language makes it difficult to automatically extract complex data practices from privacy policies, we propose to use relevance models to select paragraphs that pertain to a specific data practice and to highlight those paragraphs for annotators.…”

Section: Related Workmentioning

confidence: 99%

Crowdsourcing Annotations for Websites' Privacy Policies

Wilson

Schaub

Ramanath

et al. 2016

Proceedings of the 25th International Conference on World Wide Web

Self Cite

View full text Add to dashboard Cite

Website privacy policies are often long and difficult to understand. While research shows that Internet users care about their privacy, they do not have time to understand the policies of every website they visit, and most users hardly ever read privacy policies. Several recent efforts aim to crowdsource the interpretation of privacy policies and use the resulting annotations to build more effective user interfaces that provide users with salient policy summaries. However, very little attention has been devoted to studying the accuracy and scalability of crowdsourced privacy policy annotations, the types of questions crowdworkers can effectively answer, and the ways in which their productivity can be enhanced. Prior research indicates that most Internet users often have great difficulty understanding privacy policies, suggesting limits to the effectiveness of crowdsourcing approaches. In this paper, we assess the viability of crowdsourcing privacy policy annotations. Our results suggest that, if carefully deployed, crowdsourcing can indeed result in the generation of non-trivial annotations and can also help identify elements of ambiguity in policies. We further introduce and evaluate a method to improve the annotation process by predicting and highlighting paragraphs relevant to specific data practices.

show abstract

Unsupervised Alignment of Privacy Policies using Hidden Markov Models

Cited by 45 publications

References 10 publications

The Privacy Policy Landscape After the GDPR

The Privacy Policy Landscape After the GDPR

Identifying the Provision of Choices in Privacy Policy Text

Crowdsourcing Annotations for Websites' Privacy Policies

Contact Info

Product

Resources

About