@inproceedings{reuel-etal-2022-measuring,
title = "Measuring the Language of Self-Disclosure across Corpora",
author = "Reuel, Ann-Katrin and
Peralta, Sebastian and
Sedoc, Jo{\~a}o and
Sherman, Garrick and
Ungar, Lyle",
editor = "Muresan, Smaranda and
Nakov, Preslav and
Villavicencio, Aline",
booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.findings-acl.83",
doi = "10.18653/v1/2022.findings-acl.83",
pages = "1035--1047",
abstract = "Being able to reliably estimate self-disclosure {--} a key component of friendship and intimacy {--} from language is important for many psychology studies. We build single-task models on five self-disclosure corpora, but find that these models generalize poorly; the within-domain accuracy of predicted message-level self-disclosure of the best-performing model (mean Pearson{'}s r=0.69) is much higher than the respective across data set accuracy (mean Pearson{'}s r=0.32), due to both variations in the corpora (e.g., medical vs. general topics) and labeling instructions (target variables: self-disclosure, emotional disclosure, intimacy). However, some lexical features, such as expression of negative emotions and use of first person personal pronouns such as {`}I{'} reliably predict self-disclosure across corpora. We develop a multi-task model that yields better results, with an average Pearson{'}s r of 0.37 for out-of-corpora prediction.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="reuel-etal-2022-measuring">
<titleInfo>
<title>Measuring the Language of Self-Disclosure across Corpora</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ann-Katrin</namePart>
<namePart type="family">Reuel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sebastian</namePart>
<namePart type="family">Peralta</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Garrick</namePart>
<namePart type="family">Sherman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lyle</namePart>
<namePart type="family">Ungar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2022</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Preslav</namePart>
<namePart type="family">Nakov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aline</namePart>
<namePart type="family">Villavicencio</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Being able to reliably estimate self-disclosure – a key component of friendship and intimacy – from language is important for many psychology studies. We build single-task models on five self-disclosure corpora, but find that these models generalize poorly; the within-domain accuracy of predicted message-level self-disclosure of the best-performing model (mean Pearson’s r=0.69) is much higher than the respective across data set accuracy (mean Pearson’s r=0.32), due to both variations in the corpora (e.g., medical vs. general topics) and labeling instructions (target variables: self-disclosure, emotional disclosure, intimacy). However, some lexical features, such as expression of negative emotions and use of first person personal pronouns such as ‘I’ reliably predict self-disclosure across corpora. We develop a multi-task model that yields better results, with an average Pearson’s r of 0.37 for out-of-corpora prediction.</abstract>
<identifier type="citekey">reuel-etal-2022-measuring</identifier>
<identifier type="doi">10.18653/v1/2022.findings-acl.83</identifier>
<location>
<url>https://aclanthology.org/2022.findings-acl.83</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>1035</start>
<end>1047</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Measuring the Language of Self-Disclosure across Corpora
%A Reuel, Ann-Katrin
%A Peralta, Sebastian
%A Sedoc, João
%A Sherman, Garrick
%A Ungar, Lyle
%Y Muresan, Smaranda
%Y Nakov, Preslav
%Y Villavicencio, Aline
%S Findings of the Association for Computational Linguistics: ACL 2022
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F reuel-etal-2022-measuring
%X Being able to reliably estimate self-disclosure – a key component of friendship and intimacy – from language is important for many psychology studies. We build single-task models on five self-disclosure corpora, but find that these models generalize poorly; the within-domain accuracy of predicted message-level self-disclosure of the best-performing model (mean Pearson’s r=0.69) is much higher than the respective across data set accuracy (mean Pearson’s r=0.32), due to both variations in the corpora (e.g., medical vs. general topics) and labeling instructions (target variables: self-disclosure, emotional disclosure, intimacy). However, some lexical features, such as expression of negative emotions and use of first person personal pronouns such as ‘I’ reliably predict self-disclosure across corpora. We develop a multi-task model that yields better results, with an average Pearson’s r of 0.37 for out-of-corpora prediction.
%R 10.18653/v1/2022.findings-acl.83
%U https://aclanthology.org/2022.findings-acl.83
%U https://doi.org/10.18653/v1/2022.findings-acl.83
%P 1035-1047
Markdown (Informal)
[Measuring the Language of Self-Disclosure across Corpora](https://aclanthology.org/2022.findings-acl.83) (Reuel et al., Findings 2022)
ACL
- Ann-Katrin Reuel, Sebastian Peralta, João Sedoc, Garrick Sherman, and Lyle Ungar. 2022. Measuring the Language of Self-Disclosure across Corpora. In Findings of the Association for Computational Linguistics: ACL 2022, pages 1035–1047, Dublin, Ireland. Association for Computational Linguistics.