@inproceedings{matveyenko-etal-2026-development,
title = "Development and Benchmarking of a Blended Human-{AI} Qualitative Research Assistant",
author = "Matveyenko, Joseph and
Liu, James and
Parsons, John David and
Brown, Ryan and
Palimaru, Alina I. and
Gupta, Vipul and
Puri, Prateek",
editor = "Li, Yunyao and
Rehm, Georg and
Tu, Mei",
booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics ({ACL} 2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.acl-industry.131/",
pages = "1917--1932",
ISBN = "979-8-89176-394-4",
abstract = "Qualitative research emphasizes constructing meaning through iterative engagement with textual data. Traditionally, this human-driven process requires navigating coder fatigue and interpretive drift, thus posing challenges when scaling analysis to larger, more complex datasets. Computational approaches to augment qualitative research have been met with skepticism, partly due to their inability to replicate the nuance, context-awareness, and sophistication of human analysis. LLMs, however, present new opportunities to automate aspects of qualitative analysis while upholding rigor and research quality. In this work, we present and benchmark Muse, an interactive qualitative research system that allows researchers to identify themes and annotate datasets, achieving an inter-rater reliability between Muse and humans of Cohen{'}s $\kappa = 0.7$ for well-specified codes."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="matveyenko-etal-2026-development">
<titleInfo>
<title>Development and Benchmarking of a Blended Human-AI Qualitative Research Assistant</title>
</titleInfo>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Matveyenko</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">James</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">David</namePart>
<namePart type="family">Parsons</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Brown</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alina</namePart>
<namePart type="given">I</namePart>
<namePart type="family">Palimaru</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vipul</namePart>
<namePart type="family">Gupta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Prateek</namePart>
<namePart type="family">Puri</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>Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mei</namePart>
<namePart type="family">Tu</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, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-394-4</identifier>
</relatedItem>
<abstract>Qualitative research emphasizes constructing meaning through iterative engagement with textual data. Traditionally, this human-driven process requires navigating coder fatigue and interpretive drift, thus posing challenges when scaling analysis to larger, more complex datasets. Computational approaches to augment qualitative research have been met with skepticism, partly due to their inability to replicate the nuance, context-awareness, and sophistication of human analysis. LLMs, however, present new opportunities to automate aspects of qualitative analysis while upholding rigor and research quality. In this work, we present and benchmark Muse, an interactive qualitative research system that allows researchers to identify themes and annotate datasets, achieving an inter-rater reliability between Muse and humans of Cohen’s ąppa = 0.7 for well-specified codes.</abstract>
<identifier type="citekey">matveyenko-etal-2026-development</identifier>
<location>
<url>https://aclanthology.org/2026.acl-industry.131/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>1917</start>
<end>1932</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Development and Benchmarking of a Blended Human-AI Qualitative Research Assistant
%A Matveyenko, Joseph
%A Liu, James
%A Parsons, John David
%A Brown, Ryan
%A Palimaru, Alina I.
%A Gupta, Vipul
%A Puri, Prateek
%Y Li, Yunyao
%Y Rehm, Georg
%Y Tu, Mei
%S Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-394-4
%F matveyenko-etal-2026-development
%X Qualitative research emphasizes constructing meaning through iterative engagement with textual data. Traditionally, this human-driven process requires navigating coder fatigue and interpretive drift, thus posing challenges when scaling analysis to larger, more complex datasets. Computational approaches to augment qualitative research have been met with skepticism, partly due to their inability to replicate the nuance, context-awareness, and sophistication of human analysis. LLMs, however, present new opportunities to automate aspects of qualitative analysis while upholding rigor and research quality. In this work, we present and benchmark Muse, an interactive qualitative research system that allows researchers to identify themes and annotate datasets, achieving an inter-rater reliability between Muse and humans of Cohen’s ąppa = 0.7 for well-specified codes.
%U https://aclanthology.org/2026.acl-industry.131/
%P 1917-1932
Markdown (Informal)
[Development and Benchmarking of a Blended Human-AI Qualitative Research Assistant](https://aclanthology.org/2026.acl-industry.131/) (Matveyenko et al., ACL 2026)
ACL
- Joseph Matveyenko, James Liu, John David Parsons, Ryan Brown, Alina I. Palimaru, Vipul Gupta, and Prateek Puri. 2026. Development and Benchmarking of a Blended Human-AI Qualitative Research Assistant. In Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (ACL 2026), pages 1917–1932, San Diego, California, USA. Association for Computational Linguistics.