@inproceedings{meyer-etal-2024-exploring,
title = "Exploring the Challenges of Behaviour Change Language Classification: A Study on Semi-Supervised Learning and the Impact of Pseudo-Labelled Data",
author = "Meyer, Selina and
Fernandez-Pichel, Marcos and
Elsweiler, David and
Losada, David E.",
editor = "Demner-Fushman, Dina and
Ananiadou, Sophia and
Thompson, Paul and
Ondov, Brian",
booktitle = "Proceedings of the First Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC-COLING 2024",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.cl4health-1.28",
pages = "229--239",
abstract = "Automatic classification of behaviour change language can enhance conversational agents{'} capabilities to adjust their behaviour based on users{'} current situations and to encourage individuals to make positive changes. However, the lack of annotated language data of change-seekers hampers the performance of existing classifiers. In this study, we investigate the use of semi-supervised learning (SSL) to classify highly imbalanced texts around behaviour change. We assess the impact of including pseudo-labelled data from various sources and examine the balance between the amount of added pseudo-labelled data and the strictness of the inclusion criteria. Our findings indicate that while adding pseudo-labelled samples to the training data has limited classification impact, it does not significantly reduce performance regardless of the source of these new samples. This reinforces previous findings on the feasibility of applying classifiers trained on behaviour change language to diverse contexts.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="meyer-etal-2024-exploring">
<titleInfo>
<title>Exploring the Challenges of Behaviour Change Language Classification: A Study on Semi-Supervised Learning and the Impact of Pseudo-Labelled Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Selina</namePart>
<namePart type="family">Meyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Fernandez-Pichel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Elsweiler</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Losada</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 First Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC-COLING 2024</title>
</titleInfo>
<name type="personal">
<namePart type="given">Dina</namePart>
<namePart type="family">Demner-Fushman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sophia</namePart>
<namePart type="family">Ananiadou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Paul</namePart>
<namePart type="family">Thompson</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Brian</namePart>
<namePart type="family">Ondov</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>Automatic classification of behaviour change language can enhance conversational agents’ capabilities to adjust their behaviour based on users’ current situations and to encourage individuals to make positive changes. However, the lack of annotated language data of change-seekers hampers the performance of existing classifiers. In this study, we investigate the use of semi-supervised learning (SSL) to classify highly imbalanced texts around behaviour change. We assess the impact of including pseudo-labelled data from various sources and examine the balance between the amount of added pseudo-labelled data and the strictness of the inclusion criteria. Our findings indicate that while adding pseudo-labelled samples to the training data has limited classification impact, it does not significantly reduce performance regardless of the source of these new samples. This reinforces previous findings on the feasibility of applying classifiers trained on behaviour change language to diverse contexts.</abstract>
<identifier type="citekey">meyer-etal-2024-exploring</identifier>
<location>
<url>https://aclanthology.org/2024.cl4health-1.28</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>229</start>
<end>239</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring the Challenges of Behaviour Change Language Classification: A Study on Semi-Supervised Learning and the Impact of Pseudo-Labelled Data
%A Meyer, Selina
%A Fernandez-Pichel, Marcos
%A Elsweiler, David
%A Losada, David E.
%Y Demner-Fushman, Dina
%Y Ananiadou, Sophia
%Y Thompson, Paul
%Y Ondov, Brian
%S Proceedings of the First Workshop on Patient-Oriented Language Processing (CL4Health) @ LREC-COLING 2024
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F meyer-etal-2024-exploring
%X Automatic classification of behaviour change language can enhance conversational agents’ capabilities to adjust their behaviour based on users’ current situations and to encourage individuals to make positive changes. However, the lack of annotated language data of change-seekers hampers the performance of existing classifiers. In this study, we investigate the use of semi-supervised learning (SSL) to classify highly imbalanced texts around behaviour change. We assess the impact of including pseudo-labelled data from various sources and examine the balance between the amount of added pseudo-labelled data and the strictness of the inclusion criteria. Our findings indicate that while adding pseudo-labelled samples to the training data has limited classification impact, it does not significantly reduce performance regardless of the source of these new samples. This reinforces previous findings on the feasibility of applying classifiers trained on behaviour change language to diverse contexts.
%U https://aclanthology.org/2024.cl4health-1.28
%P 229-239
Markdown (Informal)
[Exploring the Challenges of Behaviour Change Language Classification: A Study on Semi-Supervised Learning and the Impact of Pseudo-Labelled Data](https://aclanthology.org/2024.cl4health-1.28) (Meyer et al., CL4Health-WS 2024)
ACL