@inproceedings{bhandarkar-etal-2025-psytex,
title = "{P}sy{TE}x: A Knowledge-Guided Approach to Refining Text for Psychological Analysis",
author = "Bhandarkar, Avanti and
Wilson, Ronald and
Swarup, Anushka and
Webster, Gregory and
Woodard, Damon",
editor = {H{\"a}m{\"a}l{\"a}inen, Mika and
{\"O}hman, Emily and
Bizzoni, Yuri and
Miyagawa, So and
Alnajjar, Khalid},
booktitle = "Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities",
month = may,
year = "2025",
address = "Albuquerque, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.nlp4dh-1.14/",
doi = "10.18653/v1/2025.nlp4dh-1.14",
pages = "151--178",
ISBN = "979-8-89176-234-3",
abstract = "LLMs are increasingly applied for tasks requiring deep interpretive abilities and psychological insights, such as identity profiling, mental health diagnostics, personalized content curation, and human resource management. However, their performance in these tasks remains inconsistent, as these characteristics are not explicitly perceptible in the text. To address this challenge, this paper introduces a novel protocol called the ``Psychological Text Extraction and Refinement Framework (PsyTEx)'' that leverages LLMs to isolate and amplify psychologically informative segments and evaluate LLM proficiency in interpreting complex psychological constructs from text. Using personality recognition as a case study, our extensive evaluation of five SOTA LLMs across two personality models (Big Five and Dark Triad) and two assessment levels (detection and prediction) highlights significant limitations in LLM{'}s ability to accurately interpret psychological traits. However, our findings show that LLMs, when used within the PsyTEx protocol, can effectively extract relevant information that closely aligns with psychological expectations, offering a structured approach to support future advancements in modeling, taxonomy construction, and text-based psychological evaluations."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bhandarkar-etal-2025-psytex">
<titleInfo>
<title>PsyTEx: A Knowledge-Guided Approach to Refining Text for Psychological Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Avanti</namePart>
<namePart type="family">Bhandarkar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ronald</namePart>
<namePart type="family">Wilson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anushka</namePart>
<namePart type="family">Swarup</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gregory</namePart>
<namePart type="family">Webster</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Damon</namePart>
<namePart type="family">Woodard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities</title>
</titleInfo>
<name type="personal">
<namePart type="given">Mika</namePart>
<namePart type="family">Hämäläinen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Emily</namePart>
<namePart type="family">Öhman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuri</namePart>
<namePart type="family">Bizzoni</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">So</namePart>
<namePart type="family">Miyagawa</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Alnajjar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Albuquerque, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-234-3</identifier>
</relatedItem>
<abstract>LLMs are increasingly applied for tasks requiring deep interpretive abilities and psychological insights, such as identity profiling, mental health diagnostics, personalized content curation, and human resource management. However, their performance in these tasks remains inconsistent, as these characteristics are not explicitly perceptible in the text. To address this challenge, this paper introduces a novel protocol called the “Psychological Text Extraction and Refinement Framework (PsyTEx)” that leverages LLMs to isolate and amplify psychologically informative segments and evaluate LLM proficiency in interpreting complex psychological constructs from text. Using personality recognition as a case study, our extensive evaluation of five SOTA LLMs across two personality models (Big Five and Dark Triad) and two assessment levels (detection and prediction) highlights significant limitations in LLM’s ability to accurately interpret psychological traits. However, our findings show that LLMs, when used within the PsyTEx protocol, can effectively extract relevant information that closely aligns with psychological expectations, offering a structured approach to support future advancements in modeling, taxonomy construction, and text-based psychological evaluations.</abstract>
<identifier type="citekey">bhandarkar-etal-2025-psytex</identifier>
<identifier type="doi">10.18653/v1/2025.nlp4dh-1.14</identifier>
<location>
<url>https://aclanthology.org/2025.nlp4dh-1.14/</url>
</location>
<part>
<date>2025-05</date>
<extent unit="page">
<start>151</start>
<end>178</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T PsyTEx: A Knowledge-Guided Approach to Refining Text for Psychological Analysis
%A Bhandarkar, Avanti
%A Wilson, Ronald
%A Swarup, Anushka
%A Webster, Gregory
%A Woodard, Damon
%Y Hämäläinen, Mika
%Y Öhman, Emily
%Y Bizzoni, Yuri
%Y Miyagawa, So
%Y Alnajjar, Khalid
%S Proceedings of the 5th International Conference on Natural Language Processing for Digital Humanities
%D 2025
%8 May
%I Association for Computational Linguistics
%C Albuquerque, USA
%@ 979-8-89176-234-3
%F bhandarkar-etal-2025-psytex
%X LLMs are increasingly applied for tasks requiring deep interpretive abilities and psychological insights, such as identity profiling, mental health diagnostics, personalized content curation, and human resource management. However, their performance in these tasks remains inconsistent, as these characteristics are not explicitly perceptible in the text. To address this challenge, this paper introduces a novel protocol called the “Psychological Text Extraction and Refinement Framework (PsyTEx)” that leverages LLMs to isolate and amplify psychologically informative segments and evaluate LLM proficiency in interpreting complex psychological constructs from text. Using personality recognition as a case study, our extensive evaluation of five SOTA LLMs across two personality models (Big Five and Dark Triad) and two assessment levels (detection and prediction) highlights significant limitations in LLM’s ability to accurately interpret psychological traits. However, our findings show that LLMs, when used within the PsyTEx protocol, can effectively extract relevant information that closely aligns with psychological expectations, offering a structured approach to support future advancements in modeling, taxonomy construction, and text-based psychological evaluations.
%R 10.18653/v1/2025.nlp4dh-1.14
%U https://aclanthology.org/2025.nlp4dh-1.14/
%U https://doi.org/10.18653/v1/2025.nlp4dh-1.14
%P 151-178
Markdown (Informal)
[PsyTEx: A Knowledge-Guided Approach to Refining Text for Psychological Analysis](https://aclanthology.org/2025.nlp4dh-1.14/) (Bhandarkar et al., NLP4DH 2025)
ACL