Examining the Feasibility of Off-the-Shelf Algorithms for Masking Directly Identifiable Information in Social Media Data

TL;DR

This study evaluates the effectiveness of existing off-the-shelf algorithms in identifying and removing directly identifiable information from social media data, specifically tweets, to address privacy concerns.

Contribution

The paper introduces an annotated tweet dataset and a tool called Nightjar to assess the feasibility of using existing algorithms for privacy preservation in social media data.

Findings

Nightjar successfully identifies identifiable information in tweets

Annotated dataset provides a benchmark for future research

Feasibility of off-the-shelf algorithms is demonstrated

Abstract

The identification and removal/replacement of protected information from social media data is an understudied problem, despite being desirable from an ethical and legal perspective. This paper identifies types of potentially directly identifiable information (inspired by protected health information in clinical texts) contained in tweets that may be readily removed using off-the-shelf algorithms, introduces an English dataset of tweets annotated for identifiable information, and compiles these off-the-shelf algorithms into a tool (Nightjar) to evaluate the feasibility of using Nightjar to remove directly identifiable information from the tweets. Nightjar as well as the annotated data can be retrieved from https://bitbucket.org/mdredze/nightjar.