SENSOR: An ML-Enhanced Online Annotation Tool to Uncover Privacy Concerns from User Reviews in Social-Media Applications

TL;DR

This paper presents SENSOR, an ML-based online annotation tool that classifies social media user reviews into privacy-related categories, aiding developers in addressing privacy concerns effectively.

Contribution

It introduces the GRACE annotation model and SENSOR tool, specifically designed to classify privacy-related reviews, with high accuracy demonstrated on a large dataset.

Findings

GRACE achieved macro F1-score of 0.9434

High inter-rater agreement with Cohen's Kappa of 0.87

SENSOR effectively identifies privacy concerns in user reviews

Abstract

The widespread use of social media applications has raised significant privacy concerns, often highlighted in user reviews. These reviews also provide developers with valuable insights into improving apps by addressing issues and introducing better features. However, the sheer volume and nuanced nature of reviews make manual identification and prioritization of privacy-related concerns challenging for developers. Previous studies have developed software utilities to automatically classify user reviews as privacy-relevant, privacy-irrelevant, bug reports, feature requests, etc., using machine learning. Notably, there is a lack of focus on classifying reviews specifically as privacy-related feature requests, privacy-related bug reports, or privacy-irrelevant. This paper introduces SENtinel SORt (SENSOR), an automated online annotation tool designed to help developers annotate and classify user reviews into these categories. For automating the annotation of such reviews, this paper introduces the annotation model, GRACE (GRU-based Attention with CBOW Embedding), using Gated Recurrent Units (GRU) with Continuous Bag of Words (CBOW) and Attention mechanism. Approximately 16000 user reviews from seven popular social media apps on Google Play Store, including Instagram, Facebook, WhatsApp, Snapchat, X (formerly Twitter), Facebook Lite, and Line were analyzed. Two annotators manually labelled the reviews, achieving a Cohen's Kappa value of 0.87, ensuring a labeled dataset with high inter-rater agreement for training machine learning models. Among the models tested, GRACE demonstrated the best performance (macro F1-score: 0.9434, macro ROC-AUC: 0.9934, and accuracy: 95.10%) despite class imbalance. SENSOR demonstrates significant potential to assist developers with extracting and addressing privacy-related feature requests or bug reports from user reviews, enhancing user privacy and trust.