@inproceedings{wilson-etal-2026-privacy,
title = "Privacy Later: Reflections on Design Decisions, Lessons Learned, and Open Problems of the {OPP}-115 Corpus a Decade After Release",
author = "Wilson, Shomir and
Schaub, Florian and
Sadeh, Norman",
editor = "Aletras, Nikolaos and
Chalkidis, Ilias and
Barrett, Leslie and
Goanț{\u{a}}, C{\u{a}}t{\u{a}}lina and
Preoțiuc-Pietro, Daniel and
Spanakis, Gerasimos and
Xu, Shanshan",
booktitle = "Proceedings of the Natural Legal Language Processing Workshop 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.nllp-1.10/",
pages = "94--100",
ISBN = "979-8-89176-494-1",
abstract = "The OPP-115 Corpus of annotated privacy policies was released by the Usable Privacy Policy Project in 2016 and was the first large-scale effort to annotate privacy policies in a fine level of detail. Since then, it has been used by natural language processing (NLP) researchers working on automated analysis of websites' and applications privacy policy documents, with efforts continuing in the present day. We share reflections on design decisions that went into the creation of the corpus and lessons learned from obstacles associated with it. Additionally, we describe open problems in research on privacy documents that the OPP-115 Corpus introduced or brought attention toward. These open problems show the continuing need for research on privacy policy text to support consumers' digital privacy."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="wilson-etal-2026-privacy">
<titleInfo>
<title>Privacy Later: Reflections on Design Decisions, Lessons Learned, and Open Problems of the OPP-115 Corpus a Decade After Release</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shomir</namePart>
<namePart type="family">Wilson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Florian</namePart>
<namePart type="family">Schaub</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Norman</namePart>
<namePart type="family">Sadeh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Natural Legal Language Processing Workshop 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nikolaos</namePart>
<namePart type="family">Aletras</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ilias</namePart>
<namePart type="family">Chalkidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leslie</namePart>
<namePart type="family">Barrett</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cătălina</namePart>
<namePart type="family">Goanță</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Daniel</namePart>
<namePart type="family">Preoțiuc-Pietro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerasimos</namePart>
<namePart type="family">Spanakis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shanshan</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-494-1</identifier>
</relatedItem>
<abstract>The OPP-115 Corpus of annotated privacy policies was released by the Usable Privacy Policy Project in 2016 and was the first large-scale effort to annotate privacy policies in a fine level of detail. Since then, it has been used by natural language processing (NLP) researchers working on automated analysis of websites’ and applications privacy policy documents, with efforts continuing in the present day. We share reflections on design decisions that went into the creation of the corpus and lessons learned from obstacles associated with it. Additionally, we describe open problems in research on privacy documents that the OPP-115 Corpus introduced or brought attention toward. These open problems show the continuing need for research on privacy policy text to support consumers’ digital privacy.</abstract>
<identifier type="citekey">wilson-etal-2026-privacy</identifier>
<location>
<url>https://aclanthology.org/2026.nllp-1.10/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>94</start>
<end>100</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Privacy Later: Reflections on Design Decisions, Lessons Learned, and Open Problems of the OPP-115 Corpus a Decade After Release
%A Wilson, Shomir
%A Schaub, Florian
%A Sadeh, Norman
%Y Aletras, Nikolaos
%Y Chalkidis, Ilias
%Y Barrett, Leslie
%Y Goanță, Cătălina
%Y Preoțiuc-Pietro, Daniel
%Y Spanakis, Gerasimos
%Y Xu, Shanshan
%S Proceedings of the Natural Legal Language Processing Workshop 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-494-1
%F wilson-etal-2026-privacy
%X The OPP-115 Corpus of annotated privacy policies was released by the Usable Privacy Policy Project in 2016 and was the first large-scale effort to annotate privacy policies in a fine level of detail. Since then, it has been used by natural language processing (NLP) researchers working on automated analysis of websites’ and applications privacy policy documents, with efforts continuing in the present day. We share reflections on design decisions that went into the creation of the corpus and lessons learned from obstacles associated with it. Additionally, we describe open problems in research on privacy documents that the OPP-115 Corpus introduced or brought attention toward. These open problems show the continuing need for research on privacy policy text to support consumers’ digital privacy.
%U https://aclanthology.org/2026.nllp-1.10/
%P 94-100
Markdown (Informal)
[Privacy Later: Reflections on Design Decisions, Lessons Learned, and Open Problems of the OPP-115 Corpus a Decade After Release](https://aclanthology.org/2026.nllp-1.10/) (Wilson et al., NLLP 2026)
ACL