@inproceedings{sawhney-etal-2021-empirical,
title = "An Empirical Investigation of Bias in the Multimodal Analysis of Financial Earnings Calls",
author = "Sawhney, Ramit and
Aggarwal, Arshiya and
Shah, Rajiv Ratn",
editor = "Toutanova, Kristina and
Rumshisky, Anna and
Zettlemoyer, Luke and
Hakkani-Tur, Dilek and
Beltagy, Iz and
Bethard, Steven and
Cotterell, Ryan and
Chakraborty, Tanmoy and
Zhou, Yichao",
booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
month = jun,
year = "2021",
address = "Online",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.naacl-main.294",
doi = "10.18653/v1/2021.naacl-main.294",
pages = "3751--3757",
abstract = "Volatility prediction is complex due to the stock market{'}s stochastic nature. Existing research focuses on the textual elements of financial disclosures like earnings calls transcripts to forecast stock volatility and risk, but ignores the rich acoustic features in the company executives{'} speech. Recently, new multimodal approaches that leverage the verbal and vocal cues of speakers in financial disclosures significantly outperform previous state-of-the-art approaches demonstrating the benefits of multimodality and speech. However, the financial realm is still plagued with a severe underrepresentation of various communities spanning diverse demographics, gender, and native speech. While multimodal models are better risk forecasters, it is imperative to also investigate the potential bias that these models may learn from the speech signals of company executives. In this work, we present the first study to discover the gender bias in multimodal volatility prediction due to gender-sensitive audio features and fewer female executives in earnings calls of one of the world{'}s biggest stock indexes, the S{\&}P 500 index. We quantitatively analyze bias as error disparity and investigate the sources of this bias. Our results suggest that multimodal neural financial models accentuate gender-based stereotypes.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sawhney-etal-2021-empirical">
<titleInfo>
<title>An Empirical Investigation of Bias in the Multimodal Analysis of Financial Earnings Calls</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ramit</namePart>
<namePart type="family">Sawhney</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Arshiya</namePart>
<namePart type="family">Aggarwal</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Rajiv</namePart>
<namePart type="given">Ratn</namePart>
<namePart type="family">Shah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies</title>
</titleInfo>
<name type="personal">
<namePart type="given">Kristina</namePart>
<namePart type="family">Toutanova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anna</namePart>
<namePart type="family">Rumshisky</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luke</namePart>
<namePart type="family">Zettlemoyer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dilek</namePart>
<namePart type="family">Hakkani-Tur</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Iz</namePart>
<namePart type="family">Beltagy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Steven</namePart>
<namePart type="family">Bethard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ryan</namePart>
<namePart type="family">Cotterell</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanmoy</namePart>
<namePart type="family">Chakraborty</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yichao</namePart>
<namePart type="family">Zhou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Online</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Volatility prediction is complex due to the stock market’s stochastic nature. Existing research focuses on the textual elements of financial disclosures like earnings calls transcripts to forecast stock volatility and risk, but ignores the rich acoustic features in the company executives’ speech. Recently, new multimodal approaches that leverage the verbal and vocal cues of speakers in financial disclosures significantly outperform previous state-of-the-art approaches demonstrating the benefits of multimodality and speech. However, the financial realm is still plagued with a severe underrepresentation of various communities spanning diverse demographics, gender, and native speech. While multimodal models are better risk forecasters, it is imperative to also investigate the potential bias that these models may learn from the speech signals of company executives. In this work, we present the first study to discover the gender bias in multimodal volatility prediction due to gender-sensitive audio features and fewer female executives in earnings calls of one of the world’s biggest stock indexes, the S&P 500 index. We quantitatively analyze bias as error disparity and investigate the sources of this bias. Our results suggest that multimodal neural financial models accentuate gender-based stereotypes.</abstract>
<identifier type="citekey">sawhney-etal-2021-empirical</identifier>
<identifier type="doi">10.18653/v1/2021.naacl-main.294</identifier>
<location>
<url>https://aclanthology.org/2021.naacl-main.294</url>
</location>
<part>
<date>2021-06</date>
<extent unit="page">
<start>3751</start>
<end>3757</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T An Empirical Investigation of Bias in the Multimodal Analysis of Financial Earnings Calls
%A Sawhney, Ramit
%A Aggarwal, Arshiya
%A Shah, Rajiv Ratn
%Y Toutanova, Kristina
%Y Rumshisky, Anna
%Y Zettlemoyer, Luke
%Y Hakkani-Tur, Dilek
%Y Beltagy, Iz
%Y Bethard, Steven
%Y Cotterell, Ryan
%Y Chakraborty, Tanmoy
%Y Zhou, Yichao
%S Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies
%D 2021
%8 June
%I Association for Computational Linguistics
%C Online
%F sawhney-etal-2021-empirical
%X Volatility prediction is complex due to the stock market’s stochastic nature. Existing research focuses on the textual elements of financial disclosures like earnings calls transcripts to forecast stock volatility and risk, but ignores the rich acoustic features in the company executives’ speech. Recently, new multimodal approaches that leverage the verbal and vocal cues of speakers in financial disclosures significantly outperform previous state-of-the-art approaches demonstrating the benefits of multimodality and speech. However, the financial realm is still plagued with a severe underrepresentation of various communities spanning diverse demographics, gender, and native speech. While multimodal models are better risk forecasters, it is imperative to also investigate the potential bias that these models may learn from the speech signals of company executives. In this work, we present the first study to discover the gender bias in multimodal volatility prediction due to gender-sensitive audio features and fewer female executives in earnings calls of one of the world’s biggest stock indexes, the S&P 500 index. We quantitatively analyze bias as error disparity and investigate the sources of this bias. Our results suggest that multimodal neural financial models accentuate gender-based stereotypes.
%R 10.18653/v1/2021.naacl-main.294
%U https://aclanthology.org/2021.naacl-main.294
%U https://doi.org/10.18653/v1/2021.naacl-main.294
%P 3751-3757
Markdown (Informal)
[An Empirical Investigation of Bias in the Multimodal Analysis of Financial Earnings Calls](https://aclanthology.org/2021.naacl-main.294) (Sawhney et al., NAACL 2021)
ACL