Automated PII Extraction from Social Media for Raising Privacy Awareness: A Deep Transfer Learning Approach

TL;DR

This paper introduces DTL-PIIE, a deep transfer learning framework that improves automatic extraction of Personally Identifiable Information from social media, addressing data scarcity and variability issues with innovative techniques.

Contribution

The study proposes a novel transfer learning framework using GCNs for PII extraction, overcoming data and embedding limitations in social media privacy analysis.

Findings

Outperforms state-of-the-art DL IE models

Effectively transfers knowledge from public PII data

Utilizes GCNs to incorporate syntactic patterns

Abstract

Internet users have been exposing an increasing amount of Personally Identifiable Information (PII) on social media. Such exposed PII can cause severe losses to the users, and informing users of their PII exposure is crucial to raise their privacy awareness and encourage them to take protective measures. To this end, advanced automatic techniques are needed. While Information Extraction (IE) techniques can be used to extract the PII automatically, Deep Learning (DL)-based IE models alleviate the need for feature engineering and further improve the efficiency. However, DL-based IE models often require large-scale labeled data for training, but PII-labeled social media posts are difficult to obtain due to privacy concerns. Also, these models rely heavily on pre-trained word embeddings, while PII in social media often varies in forms and thus has no fixed representations in pre-trained word embeddings. In this study, we propose the Deep Transfer Learning for PII Extraction (DTL-PIIE) framework to address these two limitations. DTL-PIIE transfers knowledge learned from publicly available PII data to social media to address the problem of rare PII-labeled data. Moreover, our framework leverages Graph Convolutional Networks (GCNs) to incorporate syntactic patterns to guide PIIE without relying on pre-trained word embeddings. Evaluation against benchmark IE models indicates that our approach outperforms state-of-the-art DL-based IE models. Our framework can facilitate various applications, such as PII misuse prediction and privacy risk assessment, protecting the privacy of internet users.