Survival text regression for time-to-event prediction in conversations

Abstract

Time-to-event prediction tasks are common in conversation modelling, for applications such as predicting the length of a conversation or when a user will stop contributing to a platform. Despite the fact that it is natural to frame such predictions as regression tasks, recent work has modelled them as classification tasks, determining whether the time-to-event is greater than a pre-determined cut-off point. While this allows for the application of classification models which are well studied in NLP, it imposes a formulation that is contrived, as well as less informative. In this paper, we explore how to handle time-to-event forecasting in conversations as regression tasks. We focus on a family of regression techniques known as survival regression, which are commonly used in the context of healthcare and reliability engineering. We adapt these models to time-to-event prediction in conversations, using linguistic markers as features. On three datasets, we demonstrate that they outperform commonly considered text regression methods and comparable classification models.