@inproceedings{guan-etal-2026-sacred,
title = "{SACRED}: A Faithful Annotated Multimedia Multimodal Multilingual Dataset for Classifying Connectedness Types in Online Spirituality",
author = "Guan, Qinghao and
Pan, Yuchen and
Li, Donghao and
Zhang, Zishi and
Chen, Yiyang and
Li, Lu and
Canu, Flaminia and
Volkart, Emilia and
Schneider, Gerold",
editor = "Montejo-Raez, Arturo and
Grisot, Cristina and
Blochowiak, Joanna and
Ljube{\v{s}}i{\'c}, Nikola and
Battaner, Elena and
Rigau, German",
booktitle = "Proceedings of Shaping Multilingual, Multimodal {AI} for the Social Sciences and Humanities ({LLM}s4{SSH}) @ {LREC} 2026",
month = may,
year = "2026",
address = "Palma de Mallorca (Spain)",
publisher = "ELRA Language Resources Association (ELRA)",
url = "https://aclanthology.org/2026.llms4ssh-1.13/",
doi = "10.63317/5h8po3qfcqa9",
pages = "126--138",
abstract = "In religion and theology studies, spirituality has garnered significant research attention for the reason that it not only transcends culture but offers unique experience to each individual. However, social scientists often rely on limited datasets, which are basically unavailable online. In this study, we collaborated with social scientists to develop a high-quality multimedia multi-modal datasets, \textbf{SACRED}, in which the faithfulness of classification is guaranteed. Using \textbf{SACRED}, we evaluated the performance of 13 popular LLMs as well as traditional rule-based and fine-tuned approaches. The result suggests DeepSeek-V3 model performs well in classifying such abstract concepts (i.e., 79.19{\%} accuracy in the Quora test set), and the GPT-4o-mini model surpassed the other models in the vision tasks (63.99{\%} F1 score). Purportedly, this is the first annotated multi-modal dataset from online spirituality communication. Our study also found a new type of connectedness which is valuable for communication science studies."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="guan-etal-2026-sacred">
<titleInfo>
<title>SACRED: A Faithful Annotated Multimedia Multimodal Multilingual Dataset for Classifying Connectedness Types in Online Spirituality</title>
</titleInfo>
<name type="personal">
<namePart type="given">Qinghao</namePart>
<namePart type="family">Guan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuchen</namePart>
<namePart type="family">Pan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Donghao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zishi</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiyang</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lu</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Flaminia</namePart>
<namePart type="family">Canu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emilia</namePart>
<namePart type="family">Volkart</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gerold</namePart>
<namePart type="family">Schneider</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of Shaping Multilingual, Multimodal AI for the Social Sciences and Humanities (LLMs4SSH) @ LREC 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Arturo</namePart>
<namePart type="family">Montejo-Raez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cristina</namePart>
<namePart type="family">Grisot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joanna</namePart>
<namePart type="family">Blochowiak</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nikola</namePart>
<namePart type="family">Ljubešić</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elena</namePart>
<namePart type="family">Battaner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">German</namePart>
<namePart type="family">Rigau</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA Language Resources Association (ELRA)</publisher>
<place>
<placeTerm type="text">Palma de Mallorca (Spain)</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In religion and theology studies, spirituality has garnered significant research attention for the reason that it not only transcends culture but offers unique experience to each individual. However, social scientists often rely on limited datasets, which are basically unavailable online. In this study, we collaborated with social scientists to develop a high-quality multimedia multi-modal datasets, SACRED, in which the faithfulness of classification is guaranteed. Using SACRED, we evaluated the performance of 13 popular LLMs as well as traditional rule-based and fine-tuned approaches. The result suggests DeepSeek-V3 model performs well in classifying such abstract concepts (i.e., 79.19% accuracy in the Quora test set), and the GPT-4o-mini model surpassed the other models in the vision tasks (63.99% F1 score). Purportedly, this is the first annotated multi-modal dataset from online spirituality communication. Our study also found a new type of connectedness which is valuable for communication science studies.</abstract>
<identifier type="citekey">guan-etal-2026-sacred</identifier>
<identifier type="doi">10.63317/5h8po3qfcqa9</identifier>
<location>
<url>https://aclanthology.org/2026.llms4ssh-1.13/</url>
</location>
<part>
<date>2026-05</date>
<extent unit="page">
<start>126</start>
<end>138</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T SACRED: A Faithful Annotated Multimedia Multimodal Multilingual Dataset for Classifying Connectedness Types in Online Spirituality
%A Guan, Qinghao
%A Pan, Yuchen
%A Li, Donghao
%A Zhang, Zishi
%A Chen, Yiyang
%A Li, Lu
%A Canu, Flaminia
%A Volkart, Emilia
%A Schneider, Gerold
%Y Montejo-Raez, Arturo
%Y Grisot, Cristina
%Y Blochowiak, Joanna
%Y Ljubešić, Nikola
%Y Battaner, Elena
%Y Rigau, German
%S Proceedings of Shaping Multilingual, Multimodal AI for the Social Sciences and Humanities (LLMs4SSH) @ LREC 2026
%D 2026
%8 May
%I ELRA Language Resources Association (ELRA)
%C Palma de Mallorca (Spain)
%F guan-etal-2026-sacred
%X In religion and theology studies, spirituality has garnered significant research attention for the reason that it not only transcends culture but offers unique experience to each individual. However, social scientists often rely on limited datasets, which are basically unavailable online. In this study, we collaborated with social scientists to develop a high-quality multimedia multi-modal datasets, SACRED, in which the faithfulness of classification is guaranteed. Using SACRED, we evaluated the performance of 13 popular LLMs as well as traditional rule-based and fine-tuned approaches. The result suggests DeepSeek-V3 model performs well in classifying such abstract concepts (i.e., 79.19% accuracy in the Quora test set), and the GPT-4o-mini model surpassed the other models in the vision tasks (63.99% F1 score). Purportedly, this is the first annotated multi-modal dataset from online spirituality communication. Our study also found a new type of connectedness which is valuable for communication science studies.
%R 10.63317/5h8po3qfcqa9
%U https://aclanthology.org/2026.llms4ssh-1.13/
%U https://doi.org/10.63317/5h8po3qfcqa9
%P 126-138
Markdown (Informal)
[SACRED: A Faithful Annotated Multimedia Multimodal Multilingual Dataset for Classifying Connectedness Types in Online Spirituality](https://aclanthology.org/2026.llms4ssh-1.13/) (Guan et al., LLMs4SSH 2026)
ACL
- Qinghao Guan, Yuchen Pan, Donghao Li, Zishi Zhang, Yiyang Chen, Lu Li, Flaminia Canu, Emilia Volkart, and Gerold Schneider. 2026. SACRED: A Faithful Annotated Multimedia Multimodal Multilingual Dataset for Classifying Connectedness Types in Online Spirituality. In Proceedings of Shaping Multilingual, Multimodal AI for the Social Sciences and Humanities (LLMs4SSH) @ LREC 2026, pages 126–138, Palma de Mallorca (Spain). ELRA Language Resources Association (ELRA).