@inproceedings{sun-etal-2026-emotiontalk,
title = "{E}motion{T}alk: An Interactive {C}hinese Multimodal Emotion Dataset With Rich Annotations",
author = "Sun, Haoqin and
Zhao, Jinghua and
Wang, Xuechen and
Zhao, Shiwan and
Zhou, Jiaming and
Wang, Hui and
Yang, Xi and
Wang, Yequan and
Lin, Yonghua",
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.440/",
pages = "9054--9071",
ISBN = "979-8-89176-395-1",
abstract = "The advancement of Multimodal Emotion Recognition (MER) in Chinese is significantly hindered by the scarcity of high-quality, spontaneous dialogue datasets compared to their English counterparts. In this work, we introduce EmotionTalk, the first interactive Chinese multimodal dataset designed to capture the nuance of authentic emotional interplay. Collected from 19 professional actors, the dataset spans 23.6 hours of dyadic conversations across diverse scenarios. A key contribution of EmotionTalk is its multi-grained annotation system, which integrates standard categorical and dimensional labels with fine-grained emotional speaking style captions, enabling research into interpretable emotion analysis. We establish comprehensive benchmarks for emotion recognition and captioning tasks, verifying the dataset{'}s effectiveness and the necessity of multimodal fusion. EmotionTalk serves as a critical resource for bridging the gap in non-English affective computing and is publicly released for the research community."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2026-emotiontalk">
<titleInfo>
<title>EmotionTalk: An Interactive Chinese Multimodal Emotion Dataset With Rich Annotations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haoqin</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinghua</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuechen</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shiwan</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiaming</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hui</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yequan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yonghua</namePart>
<namePart type="family">Lin</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>The advancement of Multimodal Emotion Recognition (MER) in Chinese is significantly hindered by the scarcity of high-quality, spontaneous dialogue datasets compared to their English counterparts. In this work, we introduce EmotionTalk, the first interactive Chinese multimodal dataset designed to capture the nuance of authentic emotional interplay. Collected from 19 professional actors, the dataset spans 23.6 hours of dyadic conversations across diverse scenarios. A key contribution of EmotionTalk is its multi-grained annotation system, which integrates standard categorical and dimensional labels with fine-grained emotional speaking style captions, enabling research into interpretable emotion analysis. We establish comprehensive benchmarks for emotion recognition and captioning tasks, verifying the dataset’s effectiveness and the necessity of multimodal fusion. EmotionTalk serves as a critical resource for bridging the gap in non-English affective computing and is publicly released for the research community.</abstract>
<identifier type="citekey">sun-etal-2026-emotiontalk</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.440/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>9054</start>
<end>9071</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T EmotionTalk: An Interactive Chinese Multimodal Emotion Dataset With Rich Annotations
%A Sun, Haoqin
%A Zhao, Jinghua
%A Wang, Xuechen
%A Zhao, Shiwan
%A Zhou, Jiaming
%A Wang, Hui
%A Yang, Xi
%A Wang, Yequan
%A Lin, Yonghua
%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 sun-etal-2026-emotiontalk
%X The advancement of Multimodal Emotion Recognition (MER) in Chinese is significantly hindered by the scarcity of high-quality, spontaneous dialogue datasets compared to their English counterparts. In this work, we introduce EmotionTalk, the first interactive Chinese multimodal dataset designed to capture the nuance of authentic emotional interplay. Collected from 19 professional actors, the dataset spans 23.6 hours of dyadic conversations across diverse scenarios. A key contribution of EmotionTalk is its multi-grained annotation system, which integrates standard categorical and dimensional labels with fine-grained emotional speaking style captions, enabling research into interpretable emotion analysis. We establish comprehensive benchmarks for emotion recognition and captioning tasks, verifying the dataset’s effectiveness and the necessity of multimodal fusion. EmotionTalk serves as a critical resource for bridging the gap in non-English affective computing and is publicly released for the research community.
%U https://aclanthology.org/2026.findings-acl.440/
%P 9054-9071
Markdown (Informal)
[EmotionTalk: An Interactive Chinese Multimodal Emotion Dataset With Rich Annotations](https://aclanthology.org/2026.findings-acl.440/) (Sun et al., Findings 2026)
ACL
- Haoqin Sun, Jinghua Zhao, Xuechen Wang, Shiwan Zhao, Jiaming Zhou, Hui Wang, Xi Yang, Yequan Wang, and Yonghua Lin. 2026. EmotionTalk: An Interactive Chinese Multimodal Emotion Dataset With Rich Annotations. In Findings of the Association for Computational Linguistics: ACL 2026, pages 9054–9071, San Diego, California, United States. Association for Computational Linguistics.