Prediction of ice-breaking between participants using prosodic features in the first meeting dialogue

In the human-human first meeting dialogue, people tend to have a chat before their main topics to break tension or the "ice." This phenomenon is called "ice-breaking." For realizing this kind of natural conversations in dialogue systems, we address prediction of ice-breaking using prosodic features in dialogue. This will allow for the systems to change conversation topics smoothly. At first, we statistically analyze relationships between prosodic features and ice-breaking events, to select the useful feature sets showing significant effects. Then, prediction of ice-breaking is conducted by a logistic regression model with these features, which shows a promising result.