Emotion Flip Reasoning in Multiparty Conversations

TL;DR

This paper introduces a new task called Emotion Flip Reasoning in multiparty conversations, aiming to identify the instigator behind emotional changes, supported by a novel dataset and a Transformer-based neural model that achieves state-of-the-art results.

Contribution

The paper presents MELD-I, a dataset with ground-truth instigator labels, and proposes TGIF, a neural architecture that effectively captures dialogue context for emotion flip reasoning.

Findings

TGIF achieves 4-12% higher F1-score than baselines.

TGIF generalizes well in zero-shot settings.

Detailed analysis highlights model strengths and limitations.

Abstract

In a conversational dialogue, speakers may have different emotional states and their dynamics play an important role in understanding dialogue's emotional discourse. However, simply detecting emotions is not sufficient to entirely comprehend the speaker-specific changes in emotion that occur during a conversation. To understand the emotional dynamics of speakers in an efficient manner, it is imperative to identify the rationale or instigator behind any changes or flips in emotion expressed by the speaker. In this paper, we explore the task called Instigator based Emotion Flip Reasoning (EFR), which aims to identify the instigator behind a speaker's emotion flip within a conversation. For example, an emotion flip from joy to anger could be caused by an instigator like threat. To facilitate this task, we present MELD-I, a dataset that includes ground-truth EFR instigator labels, which are in line with emotional psychology. To evaluate the dataset, we propose a novel neural architecture called TGIF, which leverages Transformer encoders and stacked GRUs to capture the dialogue context, speaker dynamics, and emotion sequence in a conversation. Our evaluation demonstrates state-of-the-art performance (+4-12% increase in F1-score) against five baselines used for the task. Further, we establish the generalizability of TGIF on an unseen dataset in a zero-shot setting. Additionally, we provide a detailed analysis of the competing models, highlighting the advantages and limitations of our neural architecture.