@inproceedings{pandey-etal-2026-automatic,
title = "Automatic Annotation of Mental Health Recovery Narratives: A Benchmark Study",
author = "Pandey, Shrankhla and
Murray, Graham and
Laws, Ben and
Rennick-Egglestone, Stefan and
Slade, Mike and
Morgan, Sarah",
editor = "Zirikly, Aya and
Bar, Kfir and
MacAvaney, Sean and
Ireland, Molly and
Ophir, Yaakov and
Atzil-Slonim, Dana and
Varadarajan, Vasudha and
Bedrick, Steven and
Desmet, Bart",
booktitle = "Proceedings of the 10th Workshop on Computational Linguistics and Clinical Psychology ({CLP}sych 2026)",
month = jul,
year = "2026",
address = "San Diego, California, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.clpsych-1.8/",
pages = "100--118",
ISBN = "979-8-89176-421-7",
abstract = "Manual annotation of mental health recovery narratives is slow and emotionally demanding, which limits the scalability of the digital mental health resource. A framework exists to characterise such narratives, called INCRESE, but there are currently no methods to automatically annotate the characteristics defined in INCRESE. We benchmarked the ability of support vector classifiers to annotate INCRESE characteristics when trained with three families of text representations: bag of words, GloVe static embeddings, and BERT contextual embeddings, using a dataset of 355 mental health recovery narratives. Characteristics related to diagnosis and turning points achieved a balanced accuracy greater than 0.67. Characteristics related to content warnings achieved a balanced accuracy of 0.72 but showed poor recall, which may be harmful for readers because it could lead to unsolicited exposure to sensitive content such as abuse or sexual violence. The lived-experience advisors endorsed the project objectives and addressed challenges of characteristic prioritization, adding insights not visible from quantitative metrics alone."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="pandey-etal-2026-automatic">
<titleInfo>
<title>Automatic Annotation of Mental Health Recovery Narratives: A Benchmark Study</title>
</titleInfo>
<name type="personal">
<namePart type="given">Shrankhla</namePart>
<namePart type="family">Pandey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Graham</namePart>
<namePart type="family">Murray</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ben</namePart>
<namePart type="family">Laws</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stefan</namePart>
<namePart type="family">Rennick-Egglestone</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mike</namePart>
<namePart type="family">Slade</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sarah</namePart>
<namePart type="family">Morgan</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 10th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2026)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Aya</namePart>
<namePart type="family">Zirikly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kfir</namePart>
<namePart type="family">Bar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sean</namePart>
<namePart type="family">MacAvaney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Molly</namePart>
<namePart type="family">Ireland</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaakov</namePart>
<namePart type="family">Ophir</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dana</namePart>
<namePart type="family">Atzil-Slonim</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vasudha</namePart>
<namePart type="family">Varadarajan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bedrick</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bart</namePart>
<namePart type="family">Desmet</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">979-8-89176-421-7</identifier>
</relatedItem>
<abstract>Manual annotation of mental health recovery narratives is slow and emotionally demanding, which limits the scalability of the digital mental health resource. A framework exists to characterise such narratives, called INCRESE, but there are currently no methods to automatically annotate the characteristics defined in INCRESE. We benchmarked the ability of support vector classifiers to annotate INCRESE characteristics when trained with three families of text representations: bag of words, GloVe static embeddings, and BERT contextual embeddings, using a dataset of 355 mental health recovery narratives. Characteristics related to diagnosis and turning points achieved a balanced accuracy greater than 0.67. Characteristics related to content warnings achieved a balanced accuracy of 0.72 but showed poor recall, which may be harmful for readers because it could lead to unsolicited exposure to sensitive content such as abuse or sexual violence. The lived-experience advisors endorsed the project objectives and addressed challenges of characteristic prioritization, adding insights not visible from quantitative metrics alone.</abstract>
<identifier type="citekey">pandey-etal-2026-automatic</identifier>
<location>
<url>https://aclanthology.org/2026.clpsych-1.8/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>100</start>
<end>118</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Automatic Annotation of Mental Health Recovery Narratives: A Benchmark Study
%A Pandey, Shrankhla
%A Murray, Graham
%A Laws, Ben
%A Rennick-Egglestone, Stefan
%A Slade, Mike
%A Morgan, Sarah
%Y Zirikly, Aya
%Y Bar, Kfir
%Y MacAvaney, Sean
%Y Ireland, Molly
%Y Ophir, Yaakov
%Y Atzil-Slonim, Dana
%Y Varadarajan, Vasudha
%Y Bedrick, Steven
%Y Desmet, Bart
%S Proceedings of the 10th Workshop on Computational Linguistics and Clinical Psychology (CLPsych 2026)
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, USA
%@ 979-8-89176-421-7
%F pandey-etal-2026-automatic
%X Manual annotation of mental health recovery narratives is slow and emotionally demanding, which limits the scalability of the digital mental health resource. A framework exists to characterise such narratives, called INCRESE, but there are currently no methods to automatically annotate the characteristics defined in INCRESE. We benchmarked the ability of support vector classifiers to annotate INCRESE characteristics when trained with three families of text representations: bag of words, GloVe static embeddings, and BERT contextual embeddings, using a dataset of 355 mental health recovery narratives. Characteristics related to diagnosis and turning points achieved a balanced accuracy greater than 0.67. Characteristics related to content warnings achieved a balanced accuracy of 0.72 but showed poor recall, which may be harmful for readers because it could lead to unsolicited exposure to sensitive content such as abuse or sexual violence. The lived-experience advisors endorsed the project objectives and addressed challenges of characteristic prioritization, adding insights not visible from quantitative metrics alone.
%U https://aclanthology.org/2026.clpsych-1.8/
%P 100-118
Markdown (Informal)
[Automatic Annotation of Mental Health Recovery Narratives: A Benchmark Study](https://aclanthology.org/2026.clpsych-1.8/) (Pandey et al., CLPsych 2026)
ACL