@inproceedings{petti-korhonen-2024-losst,
title = "{L}o{SST}-{AD}: A Longitudinal Corpus for Tracking {A}lzheimer{'}s Disease Related Changes in Spontaneous Speech",
author = "Petti, Ulla and
Korhonen, Anna",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.944",
pages = "10813--10821",
abstract = "Language-based biomarkers have shown promising results in differentiating those with Alzheimer{'}s disease (AD) diagnosis from healthy individuals, but the earliest changes in language are thought to start years or even decades before the diagnosis. Detecting these changes is critical to allow early interventions, but research into the earliest signs is challenging, as it requires large longitudinal datasets that are time-consuming and expensive to collect. There is a need for alternative methods for tracking longitudinal language change, including Natural Language Processing (NLP) and speech recognition technologies. We present a novel corpus that can enable this: a corpus of transcripts of public interviews with 20 famous figures, half of whom will eventually be diagnosed with AD, recorded over several decades. We evaluate the corpus by validating patterns of vocabulary richness changes known from literature, such as decline in noun frequency, word length, and several other features. We show that public data could be used to collect longitudinal datasets without causing extra stress for the participant, and that these data can adequately reflect longitudinal AD-related changes in vocabulary richness. Our corpus can provide a valuable starting point for the development of early detection tools and enhance our understanding of how AD affects language over time.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="petti-korhonen-2024-losst">
<titleInfo>
<title>LoSST-AD: A Longitudinal Corpus for Tracking Alzheimer’s Disease Related Changes in Spontaneous Speech</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ulla</namePart>
<namePart type="family">Petti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Korhonen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Language-based biomarkers have shown promising results in differentiating those with Alzheimer’s disease (AD) diagnosis from healthy individuals, but the earliest changes in language are thought to start years or even decades before the diagnosis. Detecting these changes is critical to allow early interventions, but research into the earliest signs is challenging, as it requires large longitudinal datasets that are time-consuming and expensive to collect. There is a need for alternative methods for tracking longitudinal language change, including Natural Language Processing (NLP) and speech recognition technologies. We present a novel corpus that can enable this: a corpus of transcripts of public interviews with 20 famous figures, half of whom will eventually be diagnosed with AD, recorded over several decades. We evaluate the corpus by validating patterns of vocabulary richness changes known from literature, such as decline in noun frequency, word length, and several other features. We show that public data could be used to collect longitudinal datasets without causing extra stress for the participant, and that these data can adequately reflect longitudinal AD-related changes in vocabulary richness. Our corpus can provide a valuable starting point for the development of early detection tools and enhance our understanding of how AD affects language over time.</abstract>
<identifier type="citekey">petti-korhonen-2024-losst</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.944</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>10813</start>
<end>10821</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T LoSST-AD: A Longitudinal Corpus for Tracking Alzheimer’s Disease Related Changes in Spontaneous Speech
%A Petti, Ulla
%A Korhonen, Anna
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F petti-korhonen-2024-losst
%X Language-based biomarkers have shown promising results in differentiating those with Alzheimer’s disease (AD) diagnosis from healthy individuals, but the earliest changes in language are thought to start years or even decades before the diagnosis. Detecting these changes is critical to allow early interventions, but research into the earliest signs is challenging, as it requires large longitudinal datasets that are time-consuming and expensive to collect. There is a need for alternative methods for tracking longitudinal language change, including Natural Language Processing (NLP) and speech recognition technologies. We present a novel corpus that can enable this: a corpus of transcripts of public interviews with 20 famous figures, half of whom will eventually be diagnosed with AD, recorded over several decades. We evaluate the corpus by validating patterns of vocabulary richness changes known from literature, such as decline in noun frequency, word length, and several other features. We show that public data could be used to collect longitudinal datasets without causing extra stress for the participant, and that these data can adequately reflect longitudinal AD-related changes in vocabulary richness. Our corpus can provide a valuable starting point for the development of early detection tools and enhance our understanding of how AD affects language over time.
%U https://aclanthology.org/2024.lrec-main.944
%P 10813-10821
Markdown (Informal)
[LoSST-AD: A Longitudinal Corpus for Tracking Alzheimer’s Disease Related Changes in Spontaneous Speech](https://aclanthology.org/2024.lrec-main.944) (Petti & Korhonen, LREC-COLING 2024)
ACL