@inproceedings{vente-etal-2026-corpuslens,
title = "{C}orpus{L}ens: {LLM}s as Data Analysis Facilitators in the Social, Humanistic, and Language Sciences",
author = "Vente, Blake and
Deas, Nicholas and
Patton, Desmond U. and
Kleiner, Shana and
Grieser, Jessica A and
McKeown, Kathleen",
editor = "Agrawal, Sweta and
Abad, Alberto",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-demos.62/",
pages = "651--663",
ISBN = "979-8-89176-461-3",
abstract = "In our interdisciplinary, collaborative research, we have found that humanities and social science researchers would like to analyze data underlying LLMs as well as study how language tools (e.g., emotion detection) work on their data. Existing tools are often unintuitive for such researchers and do not provide them enough agency. In this paper, we introduce CorpusLens, an LLM-based tool to aid social, humanistic, and language science researchers in exploratory textual data analysis. We present the design of CorpusLens as well as a user study showing that researchers found CorpusLens to be more helpful than prior tools they had used, while also rating it as intuitive, easy to use, transparent and enabling."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="vente-etal-2026-corpuslens">
<titleInfo>
<title>CorpusLens: LLMs as Data Analysis Facilitators in the Social, Humanistic, and Language Sciences</title>
</titleInfo>
<name type="personal">
<namePart type="given">Blake</namePart>
<namePart type="family">Vente</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="family">Deas</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="given">U</namePart>
<namePart type="family">Patton</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shana</namePart>
<namePart type="family">Kleiner</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessica</namePart>
<namePart type="given">A</namePart>
<namePart type="family">Grieser</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kathleen</namePart>
<namePart type="family">McKeown</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Sweta</namePart>
<namePart type="family">Agrawal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alberto</namePart>
<namePart type="family">Abad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-461-3</identifier>
</relatedItem>
<abstract>In our interdisciplinary, collaborative research, we have found that humanities and social science researchers would like to analyze data underlying LLMs as well as study how language tools (e.g., emotion detection) work on their data. Existing tools are often unintuitive for such researchers and do not provide them enough agency. In this paper, we introduce CorpusLens, an LLM-based tool to aid social, humanistic, and language science researchers in exploratory textual data analysis. We present the design of CorpusLens as well as a user study showing that researchers found CorpusLens to be more helpful than prior tools they had used, while also rating it as intuitive, easy to use, transparent and enabling.</abstract>
<identifier type="citekey">vente-etal-2026-corpuslens</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-demos.62/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>651</start>
<end>663</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CorpusLens: LLMs as Data Analysis Facilitators in the Social, Humanistic, and Language Sciences
%A Vente, Blake
%A Deas, Nicholas
%A Patton, Desmond U.
%A Kleiner, Shana
%A Grieser, Jessica A.
%A McKeown, Kathleen
%Y Agrawal, Sweta
%Y Abad, Alberto
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-461-3
%F vente-etal-2026-corpuslens
%X In our interdisciplinary, collaborative research, we have found that humanities and social science researchers would like to analyze data underlying LLMs as well as study how language tools (e.g., emotion detection) work on their data. Existing tools are often unintuitive for such researchers and do not provide them enough agency. In this paper, we introduce CorpusLens, an LLM-based tool to aid social, humanistic, and language science researchers in exploratory textual data analysis. We present the design of CorpusLens as well as a user study showing that researchers found CorpusLens to be more helpful than prior tools they had used, while also rating it as intuitive, easy to use, transparent and enabling.
%U https://aclanthology.org/2026.emnlp-demos.62/
%P 651-663
Markdown (Informal)
[CorpusLens: LLMs as Data Analysis Facilitators in the Social, Humanistic, and Language Sciences](https://aclanthology.org/2026.emnlp-demos.62/) (Vente et al., EMNLP 2026)
ACL
- Blake Vente, Nicholas Deas, Desmond U. Patton, Shana Kleiner, Jessica A Grieser, and Kathleen McKeown. 2026. CorpusLens: LLMs as Data Analysis Facilitators in the Social, Humanistic, and Language Sciences. In Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 651–663, Budapest, Hungary. Association for Computational Linguistics.