Predicting Evoked Emotions in Conversations

TL;DR

This paper introduces the novel task of predicting future emotions in multi-party conversations using deep neural networks, emphasizing the importance of self-dependency and recency modeling for accurate emotion prediction.

Contribution

It proposes a new problem of emotion prediction in conversations and develops two neural architectures, sequence and graph-based, to address it.

Findings

Self-dependency and recency are crucial for accurate predictions.

Sequence models perform well in short dialogues.

Graph neural models improve predictions in long dialogues.

Abstract

Understanding and predicting the emotional trajectory in multi-party multi-turn conversations is of great significance. Such information can be used, for example, to generate empathetic response in human-machine interaction or to inform models of pre-emptive toxicity detection. In this work, we introduce the novel problem of Predicting Emotions in Conversations (PEC) for the next turn (n+1), given combinations of textual and/or emotion input up to turn n. We systematically approach the problem by modeling three dimensions inherently connected to evoked emotions in dialogues, including (i) sequence modeling, (ii) self-dependency modeling, and (iii) recency modeling. These modeling dimensions are then incorporated into two deep neural network architectures, a sequence model and a graph convolutional network model. The former is designed to capture the sequence of utterances in a dialogue, while the latter captures the sequence of utterances and the network formation of multi-party dialogues. We perform a comprehensive empirical evaluation of the various proposed models for addressing the PEC problem. The results indicate (i) the importance of the self-dependency and recency model dimensions for the prediction task, (ii) the quality of simpler sequence models in short dialogues, (iii) the importance of the graph neural models in improving the predictions in long dialogues.