@inproceedings{bansal-etal-2022-shapes,
title = "Shapes of Emotions: Multimodal Emotion Recognition in Conversations via Emotion Shifts",
author = "Bansal, Keshav and
Agarwal, Harsh and
Joshi, Abhinav and
Modi, Ashutosh",
booktitle = "Proceedings of the First Workshop on Performance and Interpretability Evaluations of Multimodal, Multipurpose, Massive-Scale Models",
month = oct,
year = "2022",
address = "Virtual",
publisher = "International Conference on Computational Linguistics",
url = "https://aclanthology.org/2022.mmmpie-1.6",
pages = "44--56",
abstract = "Emotion Recognition in Conversations (ERC) is an important and active research area. Recent work has shown the benefits of using multiple modalities (e.g., text, audio, and video) for the ERC task. In a conversation, participants tend to maintain a particular emotional state unless some stimuli evokes a change. There is a continuous ebb and flow of emotions in a conversation. Inspired by this observation, we propose a multimodal ERC model and augment it with an emotion-shift component that improves performance. The proposed emotion-shift component is modular and can be added to any existing multimodal ERC model (with a few modifications). We experiment with different variants of the model, and results show that the inclusion of emotion shift signal helps the model to outperform existing models for ERC on MOSEI and IEMOCAP datasets.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bansal-etal-2022-shapes">
<titleInfo>
<title>Shapes of Emotions: Multimodal Emotion Recognition in Conversations via Emotion Shifts</title>
</titleInfo>
<name type="personal">
<namePart type="given">Keshav</namePart>
<namePart type="family">Bansal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Harsh</namePart>
<namePart type="family">Agarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Abhinav</namePart>
<namePart type="family">Joshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ashutosh</namePart>
<namePart type="family">Modi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Performance and Interpretability Evaluations of Multimodal, Multipurpose, Massive-Scale Models</title>
</titleInfo>
<originInfo>
<publisher>International Conference on Computational Linguistics</publisher>
<place>
<placeTerm type="text">Virtual</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Emotion Recognition in Conversations (ERC) is an important and active research area. Recent work has shown the benefits of using multiple modalities (e.g., text, audio, and video) for the ERC task. In a conversation, participants tend to maintain a particular emotional state unless some stimuli evokes a change. There is a continuous ebb and flow of emotions in a conversation. Inspired by this observation, we propose a multimodal ERC model and augment it with an emotion-shift component that improves performance. The proposed emotion-shift component is modular and can be added to any existing multimodal ERC model (with a few modifications). We experiment with different variants of the model, and results show that the inclusion of emotion shift signal helps the model to outperform existing models for ERC on MOSEI and IEMOCAP datasets.</abstract>
<identifier type="citekey">bansal-etal-2022-shapes</identifier>
<location>
<url>https://aclanthology.org/2022.mmmpie-1.6</url>
</location>
<part>
<date>2022-10</date>
<extent unit="page">
<start>44</start>
<end>56</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Shapes of Emotions: Multimodal Emotion Recognition in Conversations via Emotion Shifts
%A Bansal, Keshav
%A Agarwal, Harsh
%A Joshi, Abhinav
%A Modi, Ashutosh
%S Proceedings of the First Workshop on Performance and Interpretability Evaluations of Multimodal, Multipurpose, Massive-Scale Models
%D 2022
%8 October
%I International Conference on Computational Linguistics
%C Virtual
%F bansal-etal-2022-shapes
%X Emotion Recognition in Conversations (ERC) is an important and active research area. Recent work has shown the benefits of using multiple modalities (e.g., text, audio, and video) for the ERC task. In a conversation, participants tend to maintain a particular emotional state unless some stimuli evokes a change. There is a continuous ebb and flow of emotions in a conversation. Inspired by this observation, we propose a multimodal ERC model and augment it with an emotion-shift component that improves performance. The proposed emotion-shift component is modular and can be added to any existing multimodal ERC model (with a few modifications). We experiment with different variants of the model, and results show that the inclusion of emotion shift signal helps the model to outperform existing models for ERC on MOSEI and IEMOCAP datasets.
%U https://aclanthology.org/2022.mmmpie-1.6
%P 44-56
Markdown (Informal)
[Shapes of Emotions: Multimodal Emotion Recognition in Conversations via Emotion Shifts](https://aclanthology.org/2022.mmmpie-1.6) (Bansal et al., MMMPIE 2022)
ACL