Leveraging Deep Learning to Understand Users’ Views about Privacy

A Joint CS/ProperData Seminar

We will start with a brief overview of some of the work the Applied Privacy Research group at Google is engaged in. Then we will focus on text analysis pipelines we’ve been developing to automatically extract privacy insights from smartphone app reviews. We design a multi-stage methodology that leverages recent advances in NLP and LLMs, to identify whether or not a review discusses a privacy related topic, to assign a 2-level hierarchy of topic tags, to summarize thematically similar privacy reviews, and to assign emotion tags to each review . We’ll summarize our methodology for each of these steps and then present examples of what this analysis pipeline uncovers when applied to 600M app reviews. We share some long-term trends, country level comparisons, and uncover a surprising number of privacy positive reviews. We will discuss how this approach to understanding user opinions about privacy can complement traditional methods of user studies and surveys, and how it can be leveraged to provide actionable insights to 3P developers.

Bio: Nina Taft is a Principal Scientist/Director at Google where she leads the Applied Privacy Research group. Nina received her PhD from UC Berkeley, and has worked in industrial research labs since then – at SRI, Sprint Labs, Intel Berkeley Labs, and Technicolor Research before joining Google. For many years, Nina worked in the field of networking, focused on Internet traffic modeling, traffic matrix estimation, and intrusion detection. In 2017 she received the top-10 women in networking IEEE N2Women award. In the last decade, she has been working on privacy enhancing technologies with a focus on applications of machine learning for privacy. She has been chair of the SIGCOMM, IMC and PAM conferences, has published over 90 papers, and holds 10 patents.