Emotion Flip Reasoning in Multiparty Conversations
Authors:
- Shivani KumarSKShivani Kumar
- Shubham DudejaSDShubham Dudeja
- Shad AkhtarSAShad Akhtar
- Tanmoy ChakrabortyTCTanmoy Chakraborty
Preprint
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.Keywords
All Related Versions
This publication has 32 references indexed in Scilit:
- Discovering emotion and reasoning its flip in multi-party conversations using masked memory network and transformerKnowledge-Based Systems, 2022
- A multi-view network for real-time emotion recognition in conversationsKnowledge-Based Systems, 2022
- Recognizing Emotion Cause in ConversationsCognitive Computation, 2021
- DECN: Dialogical emotion correction network for conversational emotion recognitionNeurocomputing, 2021
- Conversational transfer learning for emotion recognitionInformation Fusion, 2021
- A survey on empathetic dialogue systemsInformation Fusion, 2020
- EEG-based emotion recognition using an end-to-end regional-asymmetric convolutional neural networkKnowledge-Based Systems, 2020
- Emotion and sentiment analysis from Twitter textJournal of Computational Science, 2019
- Intelligent facial emotion recognition using moth-firefly optimizationKnowledge-Based Systems, 2016
- Speech emotion recognition using amplitude modulation parameters and a combined feature selection procedureKnowledge-Based Systems, 2014