@inproceedings{li-etal-2024-social,
title = "Social Intelligence Data Infrastructure: Structuring the Present and Navigating the Future",
author = "Li, Minzhi and
Shi, Weiyan and
Ziems, Caleb and
Yang, Diyi",
editor = "Ku, Lun-Wei and
Martins, Andre and
Srikumar, Vivek",
booktitle = "Findings of the Association for Computational Linguistics ACL 2024",
month = aug,
year = "2024",
address = "Bangkok, Thailand and virtual meeting",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-acl.163",
pages = "2789--2805",
abstract = "As Natural Language Processing (NLP) systems become increasingly integrated into human social life, these technologies will need to increasingly rely on social intelligence. Although there are many valuable datasets that benchmark isolated dimensions of social intelligence, there does not yet exist any body of work to join these threads into a cohesive subfield in which researchers can quickly identify research gaps and future directions. Towards this goal, we build a Social AI Data Infrastructure, which consists of a comprehensive social AI taxonomy and a data library of 480 NLP datasets. Our infrastructure allows us to analyze existing dataset efforts, and also evaluate language models{'} performance in different social intelligence aspects. Our analyses demonstrate its utility in enabling a thorough understanding of current data landscape and providing a holistic perspective on potential directions for future dataset development. We show there is a need for multifaceted datasets, increased diversity in language and culture, more long-tailed social situations, and more interactive data in future social intelligence data efforts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="li-etal-2024-social">
<titleInfo>
<title>Social Intelligence Data Infrastructure: Structuring the Present and Navigating the Future</title>
</titleInfo>
<name type="personal">
<namePart type="given">Minzhi</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiyan</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Caleb</namePart>
<namePart type="family">Ziems</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diyi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics ACL 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Andre</namePart>
<namePart type="family">Martins</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivek</namePart>
<namePart type="family">Srikumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Bangkok, Thailand and virtual meeting</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>As Natural Language Processing (NLP) systems become increasingly integrated into human social life, these technologies will need to increasingly rely on social intelligence. Although there are many valuable datasets that benchmark isolated dimensions of social intelligence, there does not yet exist any body of work to join these threads into a cohesive subfield in which researchers can quickly identify research gaps and future directions. Towards this goal, we build a Social AI Data Infrastructure, which consists of a comprehensive social AI taxonomy and a data library of 480 NLP datasets. Our infrastructure allows us to analyze existing dataset efforts, and also evaluate language models’ performance in different social intelligence aspects. Our analyses demonstrate its utility in enabling a thorough understanding of current data landscape and providing a holistic perspective on potential directions for future dataset development. We show there is a need for multifaceted datasets, increased diversity in language and culture, more long-tailed social situations, and more interactive data in future social intelligence data efforts.</abstract>
<identifier type="citekey">li-etal-2024-social</identifier>
<location>
<url>https://aclanthology.org/2024.findings-acl.163</url>
</location>
<part>
<date>2024-08</date>
<extent unit="page">
<start>2789</start>
<end>2805</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Social Intelligence Data Infrastructure: Structuring the Present and Navigating the Future
%A Li, Minzhi
%A Shi, Weiyan
%A Ziems, Caleb
%A Yang, Diyi
%Y Ku, Lun-Wei
%Y Martins, Andre
%Y Srikumar, Vivek
%S Findings of the Association for Computational Linguistics ACL 2024
%D 2024
%8 August
%I Association for Computational Linguistics
%C Bangkok, Thailand and virtual meeting
%F li-etal-2024-social
%X As Natural Language Processing (NLP) systems become increasingly integrated into human social life, these technologies will need to increasingly rely on social intelligence. Although there are many valuable datasets that benchmark isolated dimensions of social intelligence, there does not yet exist any body of work to join these threads into a cohesive subfield in which researchers can quickly identify research gaps and future directions. Towards this goal, we build a Social AI Data Infrastructure, which consists of a comprehensive social AI taxonomy and a data library of 480 NLP datasets. Our infrastructure allows us to analyze existing dataset efforts, and also evaluate language models’ performance in different social intelligence aspects. Our analyses demonstrate its utility in enabling a thorough understanding of current data landscape and providing a holistic perspective on potential directions for future dataset development. We show there is a need for multifaceted datasets, increased diversity in language and culture, more long-tailed social situations, and more interactive data in future social intelligence data efforts.
%U https://aclanthology.org/2024.findings-acl.163
%P 2789-2805
Markdown (Informal)
[Social Intelligence Data Infrastructure: Structuring the Present and Navigating the Future](https://aclanthology.org/2024.findings-acl.163) (Li et al., Findings 2024)
ACL