@inproceedings{nguyen-etal-2026-cmtd,
title = "{CMTD}: Cognitive Modeling with Traits and Distortions for Multimodal Emotion Recognition in Conversations",
author = "Nguyen, Minh-Tien and
Le, Huu-Loi and
Phan, Manh-Cuong and
Hotta, Hajime",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.41/",
pages = "839--854",
ISBN = "979-8-89176-395-1",
abstract = "This paper introduces a new multi-agent framework, CMTD (Cognitive Modeling with Traits and Distortions), for multimodal emotion recognition in conversations (MERC). Instead of relying on shallow analysis of emotions, CMTD reconstructs a cognitive model by taking advantage of stable personality traits, dynamic cognitive distortions, visual and acoustic features of interlocutors to enhance the emotional intelligence of LLMs. CMTD includes trait, distortion detection, vision, and speech agents that provide psychological and multimodal indicators for the fusion agent to make the final prediction. Experimental results on MELD and IEMOCAP show that traits temper negativity bias from distortions, and cognitive modeling with psychological, visual, and acoustic information can improve the performance of MERC.CMTD is flexible and easy to adapt to advanced emotional AI systems (Github link: https://github.com/Shaun-le/CMTD.git)."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="nguyen-etal-2026-cmtd">
<titleInfo>
<title>CMTD: Cognitive Modeling with Traits and Distortions for Multimodal Emotion Recognition in Conversations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Minh-Tien</namePart>
<namePart type="family">Nguyen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Huu-Loi</namePart>
<namePart type="family">Le</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Manh-Cuong</namePart>
<namePart type="family">Phan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hajime</namePart>
<namePart type="family">Hotta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>This paper introduces a new multi-agent framework, CMTD (Cognitive Modeling with Traits and Distortions), for multimodal emotion recognition in conversations (MERC). Instead of relying on shallow analysis of emotions, CMTD reconstructs a cognitive model by taking advantage of stable personality traits, dynamic cognitive distortions, visual and acoustic features of interlocutors to enhance the emotional intelligence of LLMs. CMTD includes trait, distortion detection, vision, and speech agents that provide psychological and multimodal indicators for the fusion agent to make the final prediction. Experimental results on MELD and IEMOCAP show that traits temper negativity bias from distortions, and cognitive modeling with psychological, visual, and acoustic information can improve the performance of MERC.CMTD is flexible and easy to adapt to advanced emotional AI systems (Github link: https://github.com/Shaun-le/CMTD.git).</abstract>
<identifier type="citekey">nguyen-etal-2026-cmtd</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.41/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>839</start>
<end>854</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CMTD: Cognitive Modeling with Traits and Distortions for Multimodal Emotion Recognition in Conversations
%A Nguyen, Minh-Tien
%A Le, Huu-Loi
%A Phan, Manh-Cuong
%A Hotta, Hajime
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F nguyen-etal-2026-cmtd
%X This paper introduces a new multi-agent framework, CMTD (Cognitive Modeling with Traits and Distortions), for multimodal emotion recognition in conversations (MERC). Instead of relying on shallow analysis of emotions, CMTD reconstructs a cognitive model by taking advantage of stable personality traits, dynamic cognitive distortions, visual and acoustic features of interlocutors to enhance the emotional intelligence of LLMs. CMTD includes trait, distortion detection, vision, and speech agents that provide psychological and multimodal indicators for the fusion agent to make the final prediction. Experimental results on MELD and IEMOCAP show that traits temper negativity bias from distortions, and cognitive modeling with psychological, visual, and acoustic information can improve the performance of MERC.CMTD is flexible and easy to adapt to advanced emotional AI systems (Github link: https://github.com/Shaun-le/CMTD.git).
%U https://aclanthology.org/2026.findings-acl.41/
%P 839-854
Markdown (Informal)
[CMTD: Cognitive Modeling with Traits and Distortions for Multimodal Emotion Recognition in Conversations](https://aclanthology.org/2026.findings-acl.41/) (Nguyen et al., Findings 2026)
ACL