Lune

NDSS2025Top-tier venue

PolicyPulse: Precision Semantic Role Extraction for Enhanced Privacy Policy Comprehension

Andrick Adhikari, Sanchari Das, Rinku Dewri

Abstract

—The effectiveness of natural language privacy policies continues to be clouded by concerns surrounding their readability, ambiguity, and accessibility. Despite multiple design alternatives proposed over the years, natural language policies are still the primary format for organizations to communicate privacy practices to users. Current NLP techniques are often drawn towards generating high-level overviews, or specialized towards a single aspect of consumer privacy communication; the flexibility to apply them for multiple tasks is missing. To this aid, we present PolicyPulse, an information extraction pipeline designed to process privacy policies into usable formats. PolicyPulse employs a specialized XLNet classifier, and leverages a BERT-based model for semantic role labeling to extract phrases from policy sentences, while maintaining the semantic relations between predicates and their arguments. Our classification model was trained on 13 , 946 manually annotated semantic frames, and achieves a F1-score of 0 . 97 on identifying privacy practices communicated using clauses within a sentence. We emphasize the versatility of PolicyPulse through prototype applications to support requirement-driven policy presentations, question-answering systems, and privacy preference checking.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

2 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • PolicyLint: Investigating Internal Privacy Policy Contradictions on Google Play cites Polisis: Automated Analysis and Presentation of Privacy Policies Using Deep Learning
  • Scrollytelling as an Alternative Format for Privacy Policies cites Evaluating Privacy Policies under Modern Privacy Laws At Scale: An LLM-Based Automated Approach
  • Scrollytelling as an Alternative Format for Privacy Policies cites Polisis: Automated Analysis and Presentation of Privacy Policies Using Deep Learning
  • Finding a Choice in a Haystack: Automatic Extraction of Opt-Out Statements from Privacy Policy Text cites "It's a scavenger hunt": Usability of Websites' Opt-Out and Data Deletion Choices
  • Finding a Choice in a Haystack: Automatic Extraction of Opt-Out Statements from Privacy Policy Text cites Polisis: Automated Analysis and Presentation of Privacy Policies Using Deep Learning
  • Evaluating Privacy Policies under Modern Privacy Laws At Scale: An LLM-Based Automated Approach cites PolicyLint: Investigating Internal Privacy Policy Contradictions on Google Play
  • Evaluating Privacy Policies under Modern Privacy Laws At Scale: An LLM-Based Automated Approach cites Finding a Choice in a Haystack: Automatic Extraction of Opt-Out Statements from Privacy Policy Text
  • Evaluating Privacy Policies under Modern Privacy Laws At Scale: An LLM-Based Automated Approach cites Privacy Policies over Time: Curation and Analysis of a Million-Document Dataset
  • Evaluating Privacy Policies under Modern Privacy Laws At Scale: An LLM-Based Automated Approach cites Polisis: Automated Analysis and Presentation of Privacy Policies Using Deep Learning
  • Privacy Policies over Time: Curation and Analysis of a Million-Document Dataset cites Finding a Choice in a Haystack: Automatic Extraction of Opt-Out Statements from Privacy Policy Text
  • Privacy Policies over Time: Curation and Analysis of a Million-Document Dataset cites "It's a scavenger hunt": Usability of Websites' Opt-Out and Data Deletion Choices
  • Privacy Policies over Time: Curation and Analysis of a Million-Document Dataset cites Polisis: Automated Analysis and Presentation of Privacy Policies Using Deep Learning
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. Scrollytelling as an Alternative Format for Privacy PoliciesGonzalo Gabriel Méndez, Jose SuchCHI 2026 · 1 citation
  2. Evaluating Privacy Policies under Modern Privacy Laws At Scale: An LLM-Based Automated ApproachQinge Xie, Karthik Ramakrishnan, Frank LiUSENIX Security 2025

Builds on10

  1. Polisis: Automated Analysis and Presentation of Privacy Policies Using Deep LearningHamza Harkous, Kassem Fawaz, Rémi Lebret, Florian Schaub et al.USENIX Security 2018 · 400 citations
  2. PolicyLint: Investigating Internal Privacy Policy Contradictions on Google PlayBenjamin Andow, Samin Yaseer Mahmud, Wenyu Wang, Justin Whitaker et al.USENIX Security 2019 · 185 citations
  3. Privacy Policies over Time: Curation and Analysis of a Million-Document DatasetRyan Amos, Gunes Acar, Elena Lucherini, Mihir Kshirsagar et al.WWW 2021 · 135 citations
  4. "It's a scavenger hunt": Usability of Websites' Opt-Out and Data Deletion ChoicesHana Habib, Sarah Pearman, Jiamin Wang, Yixin Zou et al.CHI 2020 · 113 citations
  5. Finding a Choice in a Haystack: Automatic Extraction of Opt-Out Statements from Privacy Policy TextVinayshekhar Bannihatti Kumar, Roger Iyengar, Namita Nisal, Yuanyuan Feng et al.WWW 2020 · 93 citations

Related papers

  1. Privacy at Scale: Introducing the PrivaSeer Corpus of Web Privacy PoliciesMukund Srinath, Shomir Wilson, C. Lee GilesACL 2021
  2. Intent Classification and Slot Filling for Privacy PoliciesWasi Uddin Ahmad, Jianfeng Chi, Tu Le, Thomas Norton et al.ACL 2021
  3. PoliGraph: Automated Privacy Policy Analysis using Knowledge GraphsHao Cui, Rahmadi Trimananda, Athina Markopoulou, Scott JordanUSENIX Security 2023
  4. PolicyQA: A Reading Comprehension Dataset for Privacy PoliciesWasi Uddin Ahmad, Jianfeng Chi, Yuan Tian, Kai-Wei ChangEMNLP Findings 2020 · 56 citations
  5. Empowering Users in Digital Privacy Management through Interactive LLM-Based AgentsBolun Sun, Yifan Zhou, Haiyun JiangICLR 2025
Dusk over the sea between two cliffs drawn in fine vertical lines