PrivaSeer: A Privacy Policy Search Engine

Abstract

Web privacy policies are used by organisations to disclose their privacy practices to users on the web. However, users often do not read privacy policies because they are too long, time consuming, or too complicated. Attempts to simplify privacy policies using natural language processing have achieved some success, but they face limitations of scalability and generalization. While this puts an onus on researchers and policy regulators to protect users against unfair privacy practices, they often lack a large-scale collection of policies to study the state of internet privacy. To remedy this bottleneck, we present PrivaSeer, the first privacy policy search engine. PrivaSeer has been indexed on 1,400,318 English language website privacy policies and can be used to search privacy policies based on text queries and several search facets. Results can be ranked by PageRank, query-based document relevance, and the probability that a document is a privacy policy. Results also can be filtered by readability, vagueness, industry, and mentions of tracking technology, self-regulatory bodies, or regulations and cross-border agreements in the policy text. PrivaSeer allows legal experts, researchers, and policy regulators to discover privacy trends and policy anomalies in privacy policies at scale. In this paper we present the search interface, ranking technique, and filtering techniques for PrivaSeer. We create two indexes of privacy policies: one including supplementary non-policy content present in privacy policy web pages and one without. We evaluate the functionality of PrivaSeer by comparing ranking techniques on these two indexes.

Understanding Website Privacy Policies—A Longitudinal Analysis Using Natural Language Processing

“…Nokhbeh Zaeem and Barber [23] created a corpus of over 100,000 privacy policies, categorized into 15 website categories, utilizing the DMOZ directory. PrivaSeer [12] is a privacy policy dataset and search engine containing approximately 1.4 million website privacy policies. It was built using web crawls from 2019 and 2020, utilizing URLs from "Common Crawl" and the "Free Company Dataset".…”

“…Some scholars have previously evaluated policy comprehensibility, focusing on shorter periods or single time points [4,7,[9][10][11][12]. In contrast, this study advances the literature on consumer comprehension by conducting a large-scale analysis covering an extended period and a wide range of websites.…”

“…Wagner [4] examined length (words and sentences), passive voice, various readability formulas (Flesch Reading Ease (FRE), Coleman-Liau score (CL), and Simple Measure Of Gobbledygook (SMOG)). Srinath et al [12] reported on the length of the privacy policy and the use of vague words in their private policy corpus. Compared to Srinath et al [12], Libert et al [13] and Wagner [4], the present work is based on the dataset of Amos et al [7], which extends substantially over several years.…”

“…Srinath et al [12] reported on the length of the privacy policy and the use of vague words in their private policy corpus. Compared to Srinath et al [12], Libert et al [13] and Wagner [4], the present work is based on the dataset of Amos et al [7], which extends substantially over several years. Furthermore, herein the length and indeterminacy are analyzed in function of the GDPR, website category, popularity level, and domain.…”

Privacy Policies of IoT Devices: Collection and Analysis

“…In [30], the authors developed the PrivaSeer search engine for searching and analyzing privacy policies according to the specified criteria such as readability level, completeness, and accuracy of formulations. This search engine has indexed more than 1.4 million privacy policies.…”