# NLP Privacy Risk Identification in Social Media (NLP-PRISM): A Survey

arXiv: https://arxiv.org/abs/2602.15866 · HTML: https://mlsanity.com/paper/2602.15866/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 61 of its 210 references that are in the map.
- First posted on arXiv 26 Jan 2026.

## Builds on (most cited first, 30 of 61)

- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [Membership Inference Attacks against Machine Learning Models](https://mlsanity.com/paper/1610.05820/) (2016)
- [Automated Hate Speech Detection and the Problem of Offensive Language](https://mlsanity.com/paper/1703.04009/) (2017)
- [MELD: A Multimodal Multi-Party Dataset for Emotion Recognition in Conversations](https://mlsanity.com/paper/1810.02508/) (2018)
- [Analyzing Leakage of Personally Identifiable Information in Language Models](https://mlsanity.com/paper/2302.00539/) (2023)
- [Predicting the Type and Target of Offensive Posts in Social Media](https://mlsanity.com/paper/1902.09666/) (2019)
- [Membership Inference Attacks against Language Models via Neighbourhood Comparison](https://mlsanity.com/paper/2305.18462/) (2023)
- [SemEval-2019 Task 6: Identifying and Categorizing Offensive Language in Social Media (OffensEval)](https://mlsanity.com/paper/1903.08983/) (2019)
- [Demographic Dialectal Variation in Social Media: A Case Study of African-American English](https://mlsanity.com/paper/1608.08868/) (2016)
- [SemEval-2020 Task 12: Multilingual Offensive Language Identification in Social Media (OffensEval 2020)](https://mlsanity.com/paper/2006.07235/) (2020)
- [COLD: A Benchmark for Chinese Offensive Language Detection](https://mlsanity.com/paper/2201.06025/) (2022)
- [Agreeing to Disagree: Annotating Offensive Language Datasets with Annotators' Disagreement](https://mlsanity.com/paper/2109.13563/) (2021)
- [Multilingual Large Language Models Are Not (Yet) Code-Switchers](https://mlsanity.com/paper/2305.14235/) (2023)
- [SemEval-2020 Task 9: Overview of Sentiment Analysis of Code-Mixed Tweets](https://mlsanity.com/paper/2008.04277/) (2020)
- [The Impact of Multiple Parallel Phrase Suggestions on Email Input and Composition Behaviour of Native and Non-Native English Writers](https://mlsanity.com/paper/2101.09157/) (2021)
- [A Survey of Code-switching: Linguistic and Social Perspectives for Language Technologies](https://mlsanity.com/paper/2301.01967/) (2023)
- [Linguistic Bias in ChatGPT: Language Models Reinforce Dialect Discrimination](https://mlsanity.com/paper/2406.08818/) (2024)
- [SOLID: A Large-Scale Semi-Supervised Dataset for Offensive Language Identification](https://mlsanity.com/paper/2004.14454/) (2020)
- [Prompting Multilingual Large Language Models to Generate Code-Mixed Texts: The Case of South East Asian Languages](https://mlsanity.com/paper/2303.13592/) (2023)
- [Offensive Language Identification in Greek](https://mlsanity.com/paper/2003.07459/) (2020)
- [A Sentiment Analysis Dataset for Code-Mixed Malayalam-English](https://mlsanity.com/paper/2006.00210/) (2020)
- [DIALECTBENCH: A NLP Benchmark for Dialects, Varieties, and Closely-Related Languages](https://mlsanity.com/paper/2403.11009/) (2024)
- [Offensive Language and Hate Speech Detection for Danish](https://mlsanity.com/paper/1908.04531/) (2019)
- [NADI 2020: The First Nuanced Arabic Dialect Identification Shared Task](https://mlsanity.com/paper/2010.11334/) (2020)
- [Automatic Language Identification in Texts: A Survey](https://mlsanity.com/paper/1804.08186/) (2018)
- [SemEval-2023 Task 12: Sentiment Analysis for African Languages (AfriSenti-SemEval)](https://mlsanity.com/paper/2304.06845/) (2023)
- [You Only Prompt Once: On the Capabilities of Prompt Learning on Large Language Models to Tackle Toxic Content](https://mlsanity.com/paper/2308.05596/) (2023)
- [WASSA-2017 Shared Task on Emotion Intensity](https://mlsanity.com/paper/1708.03700/) (2017)
- [NADI 2021: The Second Nuanced Arabic Dialect Identification Shared Task](https://mlsanity.com/paper/2103.08466/) (2021)
- [ToxiCloakCN: Evaluating Robustness of Offensive Language Detection in Chinese with Cloaking Perturbations](https://mlsanity.com/paper/2406.12223/) (2024)

## Abstract (arXiv)

Natural Language Processing (NLP) is integral to social media analytics but often processes content containing Personally Identifiable Information (PII), behavioral cues, and metadata raising privacy risks such as surveillance, profiling, and targeted advertising. To systematically assess these risks, we review 203 peer-reviewed papers and propose the NLP Privacy Risk Identification in Social Media (NLP-PRISM) framework, which evaluates vulnerabilities across six dimensions: data collection, preprocessing, visibility, fairness, computational risk, and regulatory compliance. Our analysis shows that transformer models achieve F1-scores ranging from 0.58-0.84, but incur a 1% - 23% drop under privacy-preserving fine-tuning. Using NLP-PRISM, we examine privacy coverage in six NLP tasks: sentiment analysis (16), emotion detection (14), offensive language identification (19), code-mixed processing (39), native language identification (29), and dialect detection (24) revealing substantial gaps in privacy research. We further found a (reduced by 2% - 9%) trade-off in model utility, MIA AUC (membership inference attacks) 0.81, AIA accuracy 0.75 (attribute inference attacks). Finally, we advocate for stronger anonymization, privacy-aware learning, and fairness-driven training to enable ethical NLP in social media contexts.