Lune

ACL Findings2023

Towards Open-Domain Twitter User Profile Inference

Haoyang Wen, Zhenxin Xiao, Eduard H. Hovy, Alexander G. Hauptmann

Abstract

Twitter user profile inference utilizes information from Twitter to predict user attributes (e.g., occupation, location), which is controversial because of its usefulness for downstream applications and its potential to reveal users' privacy.Therefore, it is important for researchers to determine the extent of profiling in a safe environment to facilitate proper use and make the public aware of the potential risks.Contrary to existing approaches on limited attributes, we explore open-domain Twitter user profile inference.We conduct a case study where we collect publicly available WikiData public figure profiles and use diverse WikiData predicates for profile inference.After removing sensitive attributes, our data contains over 150K public figure profiles from WikiData, over 50 different attribute predicates, and over 700K attribute values.We further propose a promptbased generation method, which can infer values that are implicitly mentioned in the Twitter information.Experimental results show that the generation-based approach can infer more comprehensive user profiles than baseline extraction-based methods, but limitations still remain to be applied for real-world use.We also enclose a detailed ethical statement for our data, potential benefits and risks from this work, and our efforts to mitigate the risks. 1 1 To prevent potential misuse of our resources, we will only release our resources for research purposes based on individual requests.Please see our ethics statement section for details and contact us directly for resource access.

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

Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers2

  1. Do LLMs suffer from Multi-Party Hangover? A Diagnostic Approach to Addressee Recognition and Response Selection in ConversationsNicolò Penzo, Maryam Sajedinia, Bruno Lepri, Sara Tonelli et al.EMNLP 2024 · 2 citations
  2. Transitive Consistency Constrained Learning for Entity-to-Entity Stance DetectionHaoyang Wen, Eduard H. Hovy, Alexander HauptmannACL 2024

Builds on3

  1. The Power of Scale for Parameter-Efficient Prompt TuningBrian Lester, Rami Al-Rfou, Noah ConstantEMNLP 2021 · 94 citations
  2. Employing Personal Word Embeddings for Personalized SearchJing Yao, Zhicheng Dou, Ji-Rong WenSIGIR 2020 · 41 citations
  3. Target Inference in Argument Conclusion GenerationMilad Alshomary, Shahbaz Syed, Martin Potthast, Henning WachsmuthACL 2020 · 27 citations

Related papers

  1. You Are Who You Know and How You Behave: Attribute Inference Attacks via Users' Social Friends and BehaviorsNeil Zhenqiang Gong, Bin LiuUSENIX Security 2016 · 156 citations
  2. CHARM: Inferring Personal Attributes from ConversationsAnna Tigunova, Andrew Yates, Paramita Mirza, Gerhard WeikumEMNLP 2020 · 20 citations
  3. Please Forget Where I Was Last Summer: The Privacy Risks of Public Location (Meta)DataKostas Drakonakis, Panagiotis Ilia, Sotiris Ioannidis, Jason PolakisNDSS 2019 · 37 citations
  4. Setting the Record Straighter on Shadow BanningErwan Le Merrer, Benoît Morgan, Gilles TrédanINFOCOM 2021 · 6 citations
  5. Improving Candidate Retrieval with Entity Profile Generation for Wikidata Entity LinkingTuan Manh Lai, Heng Ji, ChengXiang ZhaiACL Findings 2022 · 18 citations
Dusk over the sea between two cliffs drawn in fine vertical lines