As LLMs (large language models) are increasingly used to generate synthetic personas, particularly in data-limited domains such as health, privacy, and HCI, it becomes necessary to understand how these narratives represent identity, especially that of minority communities. In this paper, we audit synthetic personas generated by 3 LLMs (GPT4o, Gemini 1.5 Pro, Deepseek v2.5) through the lens of representational harm, focusing specifically on racial identity. Using a mixed-methods approach combining close reading, lexical analysis, and a parameterized creativity framework, we compare 1,512 LLM-generated persona to human-authored responses. Our findings reveal that LLMs disproportionately foreground racial markers, overproduce culturally coded language, and construct personas that are syntactically elaborate yet narratively reductive. These patterns result in a range of sociotechnical harms, including stereotyping, exoticism, erasure, and benevolent bias, that are often obfuscated by superficially positive narrations. We formalize this phenomenon as algorithmic othering, where minoritized identities are rendered hypervisible but less authentic.

Computing faculty at research universities are often expected to guide the work of undergraduate and graduate student researchers. This guidance is typically called advising or mentoring, but these terms belie the complexity of the relationship, which includes several related but distinct roles. I examine the guidance of student researchers in computing (abbreviated to research guidance or guidance throughout) within a facet framework, creating an inventory of roles that faculty members can hold. By expanding and disambiguating the language of guidance, this approach reveals the full breadth of faculty responsibilities toward student researchers, and it facilitates discussing conflicts between those responsibilities. Additionally, the facet framework permits greater flexibility for students seeking guidance, allowing them a robust support network without implying inadequacy in an individual faculty member's skills. I further argue that an over-reliance on singular terms like advising or mentoring for the guidance of student researchers obscures the full scope of faculty responsibilities and interferes with improvement of those as skills. Finally, I provide suggestions for how the facet framework can be utilized by faculty and institutions, and how it can be shared with students for their benefit.

A subset of students in computing Ph.D. programs aspire to become research-active faculty at universities. However, options are typically limited for students to learn about the work of faculty beyond the activities students personally witness. Additionally, while orientations and workshops are available to new faculty, these resources are ephemeral compared to the extended, years-long needs of junior faculty to assimilate professorial knowledge. The norms of independence and self-management distinguish university faculty from other career paths, and they further motivate creating supportive resources. I introduce a set of guides to help aspiring and new computing faculty learn the unwritten norms of the profession. I focus on creating materials to support pre-tenure faculty in positions with significant expectations for research, teaching, and service, motivated by the complexity of balancing those obligations. These materials target faculty in the United States, matching my positionality, although I write them to be as broadly applicable as possible. While similar materials exist, these guides contrast with others through their foci on day-to-day activities, sustainable effort, and understanding the significance of one's work. I describe three guides from the full set, which is available to the public online at https://shomir.net/advice.html. These three selections consist of a glossary of faculty terminology, a case study of a faculty member's experiences with grant proposals, and a experiential guide to tenure. Finally, I provide recommendations for others who are interested in creating similar materials to expand the available support for pre-tenure faculty.

Natural Language Processing tasks that aim to infer an author’s private states, e.g., emotions and opinions, from their written text, typically rely on datasets annotated by third-party annotators. However, the assumption that third-party annotators can accurately capture authors’ private states remains largely unexamined. In this study, we present human subjects experiments on emotion recognition tasks that directly compare third-party annotations with first-party (author-provided) emotion labels. Our findings reveal significant limitations in third-party annotations—whether provided by human annotators or large language models (LLMs)—in faithfully representing authors’ private states. However, LLMs outperform human annotators nearly across the board. We further explore methods to improve third-party annotation quality. We find that demographic similarity between first-party authors and third-party human annotators enhances annotation performance. While incorporating first-party demographic information into prompts leads to a marginal but statistically significant improvement in LLMs’ performance. We introduce a framework for evaluating the limitations of third-party annotations and call for refined annotation practices to accurately represent and model authors’ private states.

One approach to understanding the vastness and complexity of the web is to categorize websites into sectors that reflect the specific industries or domains in which they operate. However, existing website classification approaches often struggle to handle the noisy, unstructured, and lengthy nature of web content, and current datasets lack a universal sector classification labeling system specifically designed for the web. To address these issues, we introduce SoAC (Sector of Activity Corpus), a large-scale corpus comprising 195, 495 websites categorized into 10 broad sectors tailored for web content, which serves as the benchmark for evaluating our proposed classification framework, SoACer (Sector of Activity Classifier). Building on this resource, SoACer is a novel end-to-end classification framework that first fetches website information, then incorporates extractive summarization to condense noisy and lengthy content into a concise representation, and finally employs large language model (LLM) embeddings (Llama3-8B) combined with a classification head to achieve accurate sectoral prediction. Through extensive experiments, including ablation studies and detailed error analysis, we demonstrate that SoACer achieves an overall accuracy of 72.6% on our proposed SoAC dataset. Our ablation study confirms that extractive summarization not only reduces computational overhead but also enhances classification performance, while our error analysis reveals meaningful sector overlaps that underscore the need for multi-label and hierarchical classification frameworks. These findings provide a robust foundation for future exploration of advanced classification techniques that better capture the complex nature of modern website content.1

Our research investigates the impact of Generative Artificial Intelligence (GAI) models, specifically text-to-image generators (T2Is), on the representation of non-Western cultures, with a focus on Indian contexts. Despite the transformative potential of T2Is in content creation, concerns have arisen regarding biases that may lead to misrepresentations and marginalizations. Through a Non-Western community-centered approach and grounded theory analysis of 5 focus groups from diverse Indian subcultures, we explore how T2I outputs to English input prompts depict Indian culture and its subcultures, uncovering novel representational harms such as exoticism and cultural misappropriation. These findings highlight the urgent need for inclusive and culturally sensitive T2I systems. We propose design guidelines informed by a sociotechnical perspective, contributing to the development of more equitable and representative GAI technologies globally. Our work underscores the necessity of adopting a community-centered approach to comprehend the sociotechnical dynamics of these models, complementing existing work in this space while identifying and addressing the potential negative repercussions and harms that may arise as these models are deployed on a global scale.

The landscape of privacy laws and regulations around the world is complex and ever-changing. National and super-national laws, agreements, decrees, and other government-issued rules form a patchwork that companies must follow to operate internationally. To examine the status and evolution of this patchwork, we introduce the Privacy Law Corpus, of 1,043 privacy laws, regulations, and guidelines, covering 183 jurisdictions. This corpus enables a large-scale quantitative and qualitative examination of legal focus on privacy. We examine the temporal distribution of when privacy laws were created and illustrate the dramatic increase in privacy legislation over the past 50 years, although a finer-grained examination reveals that the rate of increase varies depending on the personal data types that privacy laws address. Our exploration also demonstrates that most privacy laws respectively address relatively few personal data types. Additionally, topic modeling results show the prevalence of common themes in privacy laws, such as finance, healthcare, and telecommunications. Finally, we release the corpus to the research community to promote further study.

Pranav Narayanan Venkit, Tatiana Chakravorti, Vipul Gupta, Heidi Biggs, Mukund Srinath, Koustava Goswami, Sarah Rajtmajer, Shomir Wilson. Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing. 2024.

Radios are essential for the operations of modern police departments, and they function as both a collaborative communication technology and a sociotechnical system. However, little prior research has examined their usage or their connections to individual privacy and the role of race in policing, two growing topics of concern in the US. As a case study, we examine the Chicago Police Department's (CPD's) use of broadcast police communications (BPC) to coordinate the activity of law enforcement officers (LEOs) in the city. From a recently assembled archive of 80, 775 hours of BPC associated with CPD operations, we analyze human-generated text transcripts of radio transmissions broadcast 9:00 AM to 5:00 PM on August 10th, 2018 in one majority Black, one majority White, and one majority Hispanic area of the city (24 hours of audio) to explore four research questions: (1) Do BPC reflect reported racial disparities in policing? (2) How and when is gender, race/ethnicity, and age mentioned in BPC? (3) To what extent do BPC include sensitive information, and who is put at most risk by this practice? (4) To what extent can large language models (LLMs) heighten this risk? We explore the vocabulary and speech acts used by police in BPC, comparing mentions of personal characteristics to local demographics, the personal information shared over BPC, and the privacy concerns that it poses. Analysis indicates (a) policing professionals in the city of Chicago exhibit disproportionate attention to Black members of the public regardless of context, (b) sociodemographic characteristics like gender, race/ethnicity, and age are primarily mentioned in BPC about event information, and (c) disproportionate attention introduces disproportionate privacy risks for Black members of the public. This study shows BPC can provide a novel window into disproportionate attention (i.e., via radio communications) by law enforcement officers to specific racial groups, leading to increased privacy vulnerability for those groups, particularly Black males.

We investigate the potential for nationality biases in natural language processing (NLP) models using human evaluation methods. Biased NLP models can perpetuate stereotypes and lead to algorithmic discrimination, posing a significant challenge to the fairness and justice of AI systems. Our study employs a two-step mixed-methods approach that includes both quantitative and qualitative analysis to identify and understand the impact of nationality bias in a text generation model. Through our human-centered quantitative analysis, we measure the extent of nationality bias in articles generated by AI sources. We then conduct open-ended interviews with participants, performing qualitative coding and thematic analysis to understand the implications of these biases on human readers. Our findings reveal that biased NLP models tend to replicate and amplify existing societal biases, which can translate to harm if used in a sociotechnical setting. The qualitative analysis from our interviews offers insights into the experience readers have when encountering such articles, highlighting the potential to shift a reader’s perception of a country. These findings emphasize the critical role of public perception in shaping AI’s impact on society and the need to correct biases in AI systems.

The General Data Protection Regulation (GDPR) and other recent privacy laws require organizations to post their privacy policies, and place specific expectations on organisations' privacy practices. Privacy policies take the form of documents written in natural language, and one of the expectations placed upon them is that they remain up to date. To investigate legal compliance with this recency requirement at a large scale, we create a novel pipeline that includes crawling, regex-based extraction, candidate date classification and date object creation to extract updated and effective dates from privacy policies written in English. We then analyze patterns in policy dates using four web crawls and find that only about 40% of privacy policies online contain a date, thereby making it difficult to assess their regulatory compliance. We also find that updates in privacy policies are temporally concentrated around passage of laws regulating digital privacy (such as the GDPR), and that more popular domains are more likely to have policy dates as well as more likely to update their policies regularly.

Legal jurisdictions around the world require organisations to post privacy policies on their websites. However, in spite of laws such as GDPR and CCPA reinforcing this requirement, organisations sometimes do not comply, and a variety of semi-compliant failure modes exist. To investigate the landscape of web privacy policies, we crawl the privacy policies from 7 million organisation websites with the goal of identifying when policies are unavailable. We conduct a large-scale investigation of the availability of privacy policies and identify potential reasons for unavailability such as dead links, documents with empty content, documents that consist solely of placeholder text, and documents unavailable in the specific languages offered by their respective websites. We estimate the frequencies of these failure modes and the overall unavailability of privacy policies on the web and find that privacy policies URLs are only available in 34% of websites. Further, 1.37% of these URLs are broken links and 1.23% of the valid links lead to pages without a policy. Further, to enable investigation of privacy policies at scale, we use the capture-recapture technique to estimate the total number of English language privacy policies on the web and the distribution of these documents across top level domains and sectors of commerce. We estimate the lower bound on the number of English language privacy policies to be around 3 million. Finally, we release the CoLIPPs Corpus containing around 600k policies and their metadata consisting of policy URL, length, readability, sector of commerce, and policy crawl date.

Pranav Narayanan Venkit, Sanjana Gautam, Ruchi Panchanadikar, Ting-Hao Huang, Shomir Wilson. Proceedings of the 17th Conference of the European Chapter of the Association for Computational Linguistics. 2023.

Pranav Venkit, Mukund Srinath, Sanjana Gautam, Saranya Venkatraman, Vipul Gupta, Rebecca Passonneau, Shomir Wilson. Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing. 2023.

Companies' privacy policies and their contents are being analyzed for many reasons, including to assess the readability, usability, and utility of privacy policies; to extract and analyze data practices of apps and websites; to assess compliance of companies with relevant laws and their own privacy policies, and to develop tools and machine learning models to summarize and read policies. Despite the importance and interest in studying privacy policies from researchers, regulators, and privacy activists, few best practices or approaches have emerged and infrastructure and tool support is scarce or scattered. In order to provide insight into how researchers study privacy policies and the challenges they face when doing so, we conducted 26 interviews with researchers from various disciplines who have conducted research on privacy policies. We provide insights on a range of challenges around policy selection, policy retrieval, and policy content analysis, as well as multiple overarching challenges researchers experienced across the research process. Based on our findings, we discuss opportunities to better facilitate privacy policy research, including research directions for methodologically advancing privacy policy analysis, potential structural changes around privacy policies, and avenues for fostering an interdisciplinary research community and maturing the field.

Pretrained language models (PLMs) have been shown to exhibit sociodemographic biases, such as against gender and race, raising concerns of downstream biases in language technologies. However, PLMs’ biases against people with disabilities (PWDs) have received little attention, in spite of their potential to cause similar harms. Using perturbation sensitivity analysis, we test an assortment of popular word embedding-based and transformer-based PLMs and show significant biases against PWDs in all of them. The results demonstrate how models trained on large corpora widely favor ableist language.

Over the past decade, researchers have started to explore the use of NLP to develop tools aimed at helping the public, vendors, and regulators analyze disclosures made in privacy policies. With the introduction of new privacy regulations, the language of privacy policies is also evolving, and disclosures made by the same organization are not always the same in different languages, especially when used to communicate with users who fall under different jurisdictions. This work explores the use of language technologies to capture and analyze these differences at scale. We introduce an annotation scheme designed to capture the nuances of two new landmark privacy regulations, namely the EU’s GDPR and California’s CCPA/CPRA. We then introduce the first bilingual corpus of mobile app privacy policies consisting of 64 privacy policies in English (292K words) and 91 privacy policies in German (478K words), respectively with manual annotations for 8K and 19K fine-grained data practices. The annotations are used to develop computational methods that can automatically extract “disclosures” from privacy policies. Analysis of a subset of 59 “semi-parallel” policies reveals differences that can be attributed to different regulatory regimes, suggesting that systematic analysis of policies using automated language technologies is indeed a worthwhile endeavor.

Formal documents often are organized into sections of text, each with a title, and extracting this structure remains an under-explored aspect of natural language processing. This iterative title-text structure is valuable data for building models for headline generation and section title generation, but there is no corpus that contains web documents annotated with titles and prose texts. Therefore, we propose the first title-text dataset on web documents that incorporates a wide variety of domains to facilitate downstream training. We also introduce STAPI (Section Title And Prose text Identifier), a two-step system for labeling section titles and prose text in HTML documents. To filter out unrelated content like document footers, its first step involves a filter that reads HTML documents and proposes a set of textual candidates. In the second step, a typographic classifier takes the candidates from the filter and categorizes each one into one of the three pre-defined classes (title, prose text, and miscellany). We show that STAPI significantly outperforms two baseline models in terms of title-text identification. We release our dataset along with a web application to facilitate supervised and semi-supervised training in this domain.

Doxing refers to the practice of disclosing sensitive personal information about a person without their consent. This form of cyberbullying is an unpleasant and sometimes dangerous phenomenon for online social networks. Although prior work exists on automated identification of other types of cyberbullying, a need exists for methods capable of detecting doxing on Twitter specifically. We propose and evaluate a set of approaches for automatically detecting second- and third-party disclosures on Twitter of sensitive private information, a subset of which constitutes doxing. We summarize our findings of common intentions behind doxing episodes and compare nine different approaches for automated detection based on string-matching and one-hot encoded heuristics, as well as word and contextualized string embedding representations of tweets. We identify an approach providing 96.86% accuracy and 97.37% recall using contextualized string embeddings and conclude by discussing the practicality of our proposed methods.

Abhilasha Ravichander, Alan W Black, Thomas Norton, Shomir Wilson, Norman Sadeh. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Mukund Srinath, Shomir Wilson, C Lee Giles. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers). 2021.

Terms of service documents are a common feature of organizations' websites. Although there is no blanket requirement for organizations to provide these documents, their provision often serves essential legal purposes. Users of a website are expected to agree with the contents of a terms of service document, but users tend to ignore these documents as they are often lengthy and difficult to comprehend. As a step towards understanding the landscape of these documents at a large scale, we present a first-of-its-kind terms of service corpus containing 247,212 English language terms of service documents obtained from company websites sampled from Free Company Dataset. We examine the URLs and contents of the documents and find that some websites that purport to post terms of service actually do not provide them. We analyze reasons for unavailability and determine the overall availability of terms of service in a given set of website domains. We also identify that some websites provide an agreement that combines terms of service with a privacy policy, which is often an obligatory separate document. Using topic modeling, we analyze the themes in these combined documents by comparing them with themes found in separate terms of service and privacy policies. Results suggest that such single-page agreements miss some of the most prevalent topics available in typical privacy policies and terms of service documents and that many disproportionately cover privacy policy topics as compared to terms of service topics.

Abstract Recent work has brought to light disparities in privacy-related concerns based on socioeconomic status, race and ethnicity. This paper examines relationships between U.S. based Twitter users’ socio-demographic characteristics and their privacy behaviors. Income, gender, age, race/ethnicity, education level and occupation are correlated with stated and observed privacy preferences of 110 active Twitter users. Contrary to our expectations, analyses suggest that neither socioeconomic status ( SES ) nor demographics is a significant predictor of the use of account security features. We do find that gender and education predict rate of self-disclosure, or voluntary sharing of personal information. We explore variability in the types of information disclosed amongst socio-demographic groups. Exploratory findings indicate that: 1) participants shared less personal information than they recall having shared in exit surveys; 2) there is no strong correlation between people’s stated attitudes and their observed behaviors.

The European Union’s General Data Protection Regulation (GDPR) has compelled businesses and other organizations to update their privacy policies to state specific information about their data practices. Simultaneously, researchers in natural language processing (NLP) have developed corpora and annotation schemes for extracting salient information from privacy policies, often independently of specific laws. To connect existing NLP research on privacy policies with the GDPR, we introduce a mapping from GDPR provisions to the OPP-115 annotation scheme, which serves as the basis for a growing number of projects to automatically classify privacy policy text. We show that assumptions made in the annotation scheme about the essential topics for a privacy policy reflect many of the same topics that the GDPR requires in these documents. This suggests that OPP-115 continues to be representative of the anatomy of a legally compliant privacy policy, and that the legal assumptions behind it represent the elements of data processing that ought to be disclosed within a policy for transparency. The correspondences we show between OPP-115 and the GDPR suggest the feasibility of bridging existing computational and legal research on privacy policies, benefiting both areas.

Website privacy policies sometimes provide users the option to opt-out of certain collections and uses of their personal data. Unfortunately, many privacy policies bury these instructions deep in their text, and few web users have the time or skill necessary to discover them. We describe a method for the automated detection of opt-out choices in privacy policy text and their presentation to users through a web browser extension. We describe the creation of two corpora of opt-out choices, which enable the training of classifiers to identify opt-outs in privacy policies. Our overall approach for extracting and classifying opt-out choices combines heuristics to identify commonly found opt-out hyperlinks with supervised machine learning to automatically identify less conspicuous instances. Our approach achieves a precision of 0.93 and a recall of 0.9. We introduce Opt-Out Easy, a web browser extension designed to present available opt-out choices to users as they browse the web. We evaluate the usability of our browser extension with a user study. We also present results of a large-scale analysis of opt-outs found in the text of thousands of the most popular websites.

Abhilasha Ravichander, Alan W Black, Shomir Wilson, Thomas Norton, Norman Sadeh. Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). 2019.

Website privacy policies are often long and difficult to understand. While research shows that Internet users care about their privacy, they do not have the time to understand the policies of every website they visit, and most users hardly ever read privacy policies. Some recent efforts have aimed to use a combination of crowdsourcing, machine learning, and natural language processing to interpret privacy policies at scale, thus producing annotations for use in interfaces that inform Internet users of salient policy details. However, little attention has been devoted to studying the accuracy of crowdsourced privacy policy annotations, how crowdworker productivity can be enhanced for such a task, and the levels of granularity that are feasible for automatic analysis of privacy policies. In this article, we present a trajectory of work addressing each of these topics. We include analyses of crowdworker performance, evaluation of a method to make a privacy-policy oriented task easier for crowdworkers, a coarse-grained approach to labeling segments of policy text with descriptive themes, and a fine-grained approach to identifying user choices described in policy text. Together, the results from these efforts show the effectiveness of using automated and semi-automated methods for extracting from privacy policies the data practice details that are salient to Internet users’ interests.

The text in many web documents is organized into a hierarchy of section titles and corresponding prose content, a structure which provides potentially exploitable information on discourse structure and topicality.However, this organization is generally discarded during text collection, and collecting it is not straightforward: the same visual organization can be implemented in a myriad of different ways in the underlying HTML.To remedy this, we present a flexible system for automatically extracting the hierarchical section titles and prose organization of web documents irrespective of differences in HTML representation.This system uses features from syntax, semantics, discourse and markup to build two models which classify HTML text into section titles and prose text.When tested on three different domains of web text, our domainindependent system achieves an overall precision of 0.82 and a recall of 0.98.The domaindependent variation produces very high precision (0.99) at the expense of recall (0.75).These results exhibit a robust level of accuracy suitable for enhancing question answering, information extraction, and summarization. 1

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 texts. 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.

Shomir Wilson, Florian Schaub, Aswarth Abhilash Dara, Frederick Liu, Sushain Cherivirala, Pedro Giovanni Leon, Mads Schaarup Andersen, Sebastian Zimmeck, Kanthashree Mysore Sathyendra, N. Cameron Russell, Thomas B. Norton, Eduard Hovy, Joel Reidenberg, Norman Sadeh. Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). 2016.

Writing intended to inform frequently contains references to document entities (DEs), a mixed class that includes orthographically structured items (e.g., illustrations, sections, lists) and discourse entities (arguments, suggestions, points).Such references are vital to the interpretation of documents, but they often eschew identifiers such as "Figure 1" for inexplicit phrases like "in this figure " or "from these premises".We examine inexplicit references to DEs, termed DE references, and recast the problem of their automatic detection into the determination of relevant word senses.We then show the feasibility of machine learning for the detection of DErelevant word senses, using a corpus of human-labeled synsets from WordNet.We test cross-domain performance by gathering lemmas and synsets from three corpora: website privacy policies, Wikipedia articles, and Wikibooks textbooks.Identifying DE references will enable language technologies to use the information encoded by them, permitting the automatic generation of finely-tuned descriptions of DEs and the presentation of richly-structured information to readers.

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.

In today's age of big data, websites are collecting an increasingly wide variety of information about their users. The texts of websites' privacy policies, which serve as legal agreements between service providers and users, are often long and difficult to understand. Automated analysis of those texts has the potential to help users better understand the implications of agreeing to such policies. In this work, we present a technique that combines machine learning and crowdsourcing to semi-automatically extract key aspects of website privacy policies that is scalable, fast, and cost-effective.

This paper describes an empirical study of 1.6M deleted tweets collected over a continuous one-week period from a set of 292K Twitter users. We examine several aggregate properties of deleted tweets, including their connections to other tweets (e.g., whether they are replies or retweets), the clients used to produce them, temporal aspects of deletion, and the presence of geotagging information. Some significant differences were discovered between the two collections, namely in the clients used to post them, their conversational aspects, the sentiment vocabulary present in them, and the days of the week they were posted. However, in other dimensions for which analysis was possible, no substantial differences were found. Finally, we discuss some ramifications of this work for understanding Twitter usage and management of one's privacy.

Location sharing is a popular feature of online social networks, but challenges remain in the effective presentation of privacy choices to users, whose location sharing preferences are complex and diverse. One proposed approach for capturing these nuances builds on the observation that key attributes of users' location sharing preferences can be represented by a small number of privacy profiles, which can provide a basis for configuring individual preferences. However, the impact of this approach on how users view their privacy is relatively unknown. We present a study evaluating the impact of this approach on users' location sharing preferences and their satisfaction with the decisions made by their resulting settings. The results suggest that this approach can influence users to share significantly more without a substantial difference in comfort. This further suggests that the provision of profiles for privacy settings must be carefully considered, as they can substantially alter sharing behavior.