@inproceedings{abbasi-etal-2021-constructing,
title = "Constructing a Psychometric Testbed for Fair Natural Language Processing",
author = "Abbasi, Ahmed and
Dobolyi, David and
Lalor, John P. and
Netemeyer, Richard G. and
Smith, Kendall and
Yang, Yi",
editor = "Moens, Marie-Francine and
Huang, Xuanjing and
Specia, Lucia and
Yih, Scott Wen-tau",
booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
month = nov,
year = "2021",
address = "Online and Punta Cana, Dominican Republic",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.emnlp-main.304/",
doi = "10.18653/v1/2021.emnlp-main.304",
pages = "3748--3758",
abstract = "Psychometric measures of ability, attitudes, perceptions, and beliefs are crucial for understanding user behavior in various contexts including health, security, e-commerce, and finance. Traditionally, psychometric dimensions have been measured and collected using survey-based methods. Inferring such constructs from user-generated text could allow timely, unobtrusive collection and analysis. In this paper we describe our efforts to construct a corpus for psychometric natural language processing (NLP) related to important dimensions such as trust, anxiety, numeracy, and literacy, in the health domain. We discuss our multi-step process to align user text with their survey-based response items and provide an overview of the resulting testbed which encompasses survey-based psychometric measures and accompanying user-generated text from 8,502 respondents. Our testbed also encompasses self-reported demographic information, including race, sex, age, income, and education - thereby affording opportunities for measuring bias and benchmarking fairness of text classification methods. We report preliminary results on use of the text to predict/categorize users' survey response labels - and on the fairness of these models. We also discuss the important implications of our work and resulting testbed for future NLP research on psychometrics and fairness."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="abbasi-etal-2021-constructing">
<titleInfo>
<title>Constructing a Psychometric Testbed for Fair Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ahmed</namePart>
<namePart type="family">Abbasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Dobolyi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">John</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Lalor</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Richard</namePart>
<namePart type="given">G</namePart>
<namePart type="family">Netemeyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kendall</namePart>
<namePart type="family">Smith</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing</title>
</titleInfo>
<name type="personal">
<namePart type="given">Marie-Francine</namePart>
<namePart type="family">Moens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuanjing</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lucia</namePart>
<namePart type="family">Specia</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Scott</namePart>
<namePart type="given">Wen-tau</namePart>
<namePart type="family">Yih</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online and Punta Cana, Dominican Republic</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Psychometric measures of ability, attitudes, perceptions, and beliefs are crucial for understanding user behavior in various contexts including health, security, e-commerce, and finance. Traditionally, psychometric dimensions have been measured and collected using survey-based methods. Inferring such constructs from user-generated text could allow timely, unobtrusive collection and analysis. In this paper we describe our efforts to construct a corpus for psychometric natural language processing (NLP) related to important dimensions such as trust, anxiety, numeracy, and literacy, in the health domain. We discuss our multi-step process to align user text with their survey-based response items and provide an overview of the resulting testbed which encompasses survey-based psychometric measures and accompanying user-generated text from 8,502 respondents. Our testbed also encompasses self-reported demographic information, including race, sex, age, income, and education - thereby affording opportunities for measuring bias and benchmarking fairness of text classification methods. We report preliminary results on use of the text to predict/categorize users’ survey response labels - and on the fairness of these models. We also discuss the important implications of our work and resulting testbed for future NLP research on psychometrics and fairness.</abstract>
<identifier type="citekey">abbasi-etal-2021-constructing</identifier>
<identifier type="doi">10.18653/v1/2021.emnlp-main.304</identifier>
<location>
<url>https://aclanthology.org/2021.emnlp-main.304/</url>
</location>
<part>
<date>2021-11</date>
<extent unit="page">
<start>3748</start>
<end>3758</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Constructing a Psychometric Testbed for Fair Natural Language Processing
%A Abbasi, Ahmed
%A Dobolyi, David
%A Lalor, John P.
%A Netemeyer, Richard G.
%A Smith, Kendall
%A Yang, Yi
%Y Moens, Marie-Francine
%Y Huang, Xuanjing
%Y Specia, Lucia
%Y Yih, Scott Wen-tau
%S Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing
%D 2021
%8 November
%I Association for Computational Linguistics
%C Online and Punta Cana, Dominican Republic
%F abbasi-etal-2021-constructing
%X Psychometric measures of ability, attitudes, perceptions, and beliefs are crucial for understanding user behavior in various contexts including health, security, e-commerce, and finance. Traditionally, psychometric dimensions have been measured and collected using survey-based methods. Inferring such constructs from user-generated text could allow timely, unobtrusive collection and analysis. In this paper we describe our efforts to construct a corpus for psychometric natural language processing (NLP) related to important dimensions such as trust, anxiety, numeracy, and literacy, in the health domain. We discuss our multi-step process to align user text with their survey-based response items and provide an overview of the resulting testbed which encompasses survey-based psychometric measures and accompanying user-generated text from 8,502 respondents. Our testbed also encompasses self-reported demographic information, including race, sex, age, income, and education - thereby affording opportunities for measuring bias and benchmarking fairness of text classification methods. We report preliminary results on use of the text to predict/categorize users’ survey response labels - and on the fairness of these models. We also discuss the important implications of our work and resulting testbed for future NLP research on psychometrics and fairness.
%R 10.18653/v1/2021.emnlp-main.304
%U https://aclanthology.org/2021.emnlp-main.304/
%U https://doi.org/10.18653/v1/2021.emnlp-main.304
%P 3748-3758
Markdown (Informal)
[Constructing a Psychometric Testbed for Fair Natural Language Processing](https://aclanthology.org/2021.emnlp-main.304/) (Abbasi et al., EMNLP 2021)
ACL
- Ahmed Abbasi, David Dobolyi, John P. Lalor, Richard G. Netemeyer, Kendall Smith, and Yi Yang. 2021. Constructing a Psychometric Testbed for Fair Natural Language Processing. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pages 3748–3758, Online and Punta Cana, Dominican Republic. Association for Computational Linguistics.