@inproceedings{kreuter-etal-2022-items,
title = "Items from Psychometric Tests as Training Data for Personality Profiling Models of {T}witter Users",
author = "Kreuter, Anne and
Sassenberg, Kai and
Klinger, Roman",
editor = "Barnes, Jeremy and
De Clercq, Orph{\'e}e and
Barriere, Valentin and
Tafreshi, Shabnam and
Alqahtani, Sawsan and
Sedoc, Jo{\~a}o and
Klinger, Roman and
Balahur, Alexandra",
booktitle = "Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment {\&} Social Media Analysis",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.wassa-1.35/",
doi = "10.18653/v1/2022.wassa-1.35",
pages = "315--323",
abstract = "Machine-learned models for author profiling in social media often rely on data acquired via self-reporting-based psychometric tests (questionnaires) filled out by social media users. This is an expensive but accurate data collection strategy. Another, less costly alternative, which leads to potentially more noisy and biased data, is to rely on labels inferred from publicly available information in the profiles of the users, for instance self-reported diagnoses or test results. In this paper, we explore a third strategy, namely to directly use a corpus of items from validated psychometric tests as training data. Items from psychometric tests often consist of sentences from an I-perspective (e.g., {\textquoteleft}I make friends easily.'). Such corpora of test items constitute {\textquoteleft}small data', but their availability for many concepts is a rich resource. We investigate this approach for personality profiling, and evaluate BERT classifiers fine-tuned on such psychometric test items for the big five personality traits (openness, conscientiousness, extraversion, agreeableness, neuroticism) and analyze various augmentation strategies regarding their potential to address the challenges coming with such a small corpus. Our evaluation on a publicly available Twitter corpus shows a comparable performance to in-domain training for 4/5 personality traits with T5-based data augmentation."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="kreuter-etal-2022-items">
<titleInfo>
<title>Items from Psychometric Tests as Training Data for Personality Profiling Models of Twitter Users</title>
</titleInfo>
<name type="personal">
<namePart type="given">Anne</namePart>
<namePart type="family">Kreuter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kai</namePart>
<namePart type="family">Sassenberg</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Klinger</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>Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jeremy</namePart>
<namePart type="family">Barnes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Orphée</namePart>
<namePart type="family">De Clercq</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Valentin</namePart>
<namePart type="family">Barriere</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shabnam</namePart>
<namePart type="family">Tafreshi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sawsan</namePart>
<namePart type="family">Alqahtani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">João</namePart>
<namePart type="family">Sedoc</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Roman</namePart>
<namePart type="family">Klinger</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexandra</namePart>
<namePart type="family">Balahur</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>Machine-learned models for author profiling in social media often rely on data acquired via self-reporting-based psychometric tests (questionnaires) filled out by social media users. This is an expensive but accurate data collection strategy. Another, less costly alternative, which leads to potentially more noisy and biased data, is to rely on labels inferred from publicly available information in the profiles of the users, for instance self-reported diagnoses or test results. In this paper, we explore a third strategy, namely to directly use a corpus of items from validated psychometric tests as training data. Items from psychometric tests often consist of sentences from an I-perspective (e.g., ‘I make friends easily.’). Such corpora of test items constitute ‘small data’, but their availability for many concepts is a rich resource. We investigate this approach for personality profiling, and evaluate BERT classifiers fine-tuned on such psychometric test items for the big five personality traits (openness, conscientiousness, extraversion, agreeableness, neuroticism) and analyze various augmentation strategies regarding their potential to address the challenges coming with such a small corpus. Our evaluation on a publicly available Twitter corpus shows a comparable performance to in-domain training for 4/5 personality traits with T5-based data augmentation.</abstract>
<identifier type="citekey">kreuter-etal-2022-items</identifier>
<identifier type="doi">10.18653/v1/2022.wassa-1.35</identifier>
<location>
<url>https://aclanthology.org/2022.wassa-1.35/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>315</start>
<end>323</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Items from Psychometric Tests as Training Data for Personality Profiling Models of Twitter Users
%A Kreuter, Anne
%A Sassenberg, Kai
%A Klinger, Roman
%Y Barnes, Jeremy
%Y De Clercq, Orphée
%Y Barriere, Valentin
%Y Tafreshi, Shabnam
%Y Alqahtani, Sawsan
%Y Sedoc, João
%Y Klinger, Roman
%Y Balahur, Alexandra
%S Proceedings of the 12th Workshop on Computational Approaches to Subjectivity, Sentiment & Social Media Analysis
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F kreuter-etal-2022-items
%X Machine-learned models for author profiling in social media often rely on data acquired via self-reporting-based psychometric tests (questionnaires) filled out by social media users. This is an expensive but accurate data collection strategy. Another, less costly alternative, which leads to potentially more noisy and biased data, is to rely on labels inferred from publicly available information in the profiles of the users, for instance self-reported diagnoses or test results. In this paper, we explore a third strategy, namely to directly use a corpus of items from validated psychometric tests as training data. Items from psychometric tests often consist of sentences from an I-perspective (e.g., ‘I make friends easily.’). Such corpora of test items constitute ‘small data’, but their availability for many concepts is a rich resource. We investigate this approach for personality profiling, and evaluate BERT classifiers fine-tuned on such psychometric test items for the big five personality traits (openness, conscientiousness, extraversion, agreeableness, neuroticism) and analyze various augmentation strategies regarding their potential to address the challenges coming with such a small corpus. Our evaluation on a publicly available Twitter corpus shows a comparable performance to in-domain training for 4/5 personality traits with T5-based data augmentation.
%R 10.18653/v1/2022.wassa-1.35
%U https://aclanthology.org/2022.wassa-1.35/
%U https://doi.org/10.18653/v1/2022.wassa-1.35
%P 315-323
Markdown (Informal)
[Items from Psychometric Tests as Training Data for Personality Profiling Models of Twitter Users](https://aclanthology.org/2022.wassa-1.35/) (Kreuter et al., WASSA 2022)
ACL