Conversations, Machine Learning and Privacy: LinkedIn's Path Towards Transforming Interaction with Its Members

Abstract

At LinkedIn, we believe that having the right conversations with our members is key to unlocking economic opportunity for them. For us, these conversations are in a broader context than traditionally defined dialogues. A typical dialogue usually only considers a limited time-window as context and is trying to satisfy an immediate intent. Advanced dialogue systems allow an user to take a number of turns, in that short-time window, to get clear on the user's intent. However, our members are having conversations with us over long periods of time about their long-term goals, such as staying informed, growing a professional network, advancing a career, getting a job, finding qualified leads, etc. These conversational goals are often hierarchical. For example, getting a great job is a key part of advancing your career. Our goal at LinkedIn is to be able to have simultaneous conversations with our members on all of these levels. To do this, we have to build machine learning systems that understand that there are multiple multi-level conversations going on. We have made strong headway in building components of this conversational vision by learning how to approximate long-term member value and defining an optimization framework that can incorporate multiple conflicting objectives. These problems consider the states of these conversations when interacting with our members and actively make decisions that optimize this ongoing dialogue. We have a challenging and interesting road ahead. In this talk, Igor will present the current state of LinkedIn's machine-learning efforts towards building robust, long-term conversational systems. He will then discuss the potential privacy and ethical issues surrounding having these conversational interactions through an ever-increasing number of touchpoints with our members.