@inproceedings{van-boven-etal-2022-intersection,
title = "At the Intersection of {NLP} and Sustainable Development: Exploring the Impact of Demographic-Aware Text Representations in Modeling Value on a Corpus of Interviews",
author = "van Boven, Goya and
Hirmer, Stephanie and
Conforti, Costanza",
editor = "Calzolari, Nicoletta and
B{\'e}chet, Fr{\'e}d{\'e}ric and
Blache, Philippe and
Choukri, Khalid and
Cieri, Christopher and
Declerck, Thierry and
Goggi, Sara and
Isahara, Hitoshi and
Maegaard, Bente and
Mariani, Joseph and
Mazo, H{\'e}l{\`e}ne and
Odijk, Jan and
Piperidis, Stelios",
booktitle = "Proceedings of the Thirteenth Language Resources and Evaluation Conference",
month = jun,
year = "2022",
address = "Marseille, France",
publisher = "European Language Resources Association",
url = "https://aclanthology.org/2022.lrec-1.216",
pages = "2007--2021",
abstract = "This research explores automated text classification using data from Low{--} and Middle{--}Income Countries (LMICs). In particular, we explore enhancing text representations with demographic information of speakers in a privacy-preserving manner. We introduce the Demographic-Rich Qualitative UPV-Interviews Dataset (DR-QI), a rich dataset of qualitative interviews from rural communities in India and Uganda. The interviews were conducted following the latest standards for respectful interactions with illiterate speakers (Hirmer et al., 2021a). The interviews were later sentence-annotated for Automated User-Perceived Value (UPV) Classification (Conforti et al., 2020), a schema that classifies values expressed by speakers, resulting in a dataset of 5,333 sentences. We perform the UPV classification task, which consists of predicting which values are expressed in a given sentence, on the new DR-QI dataset. We implement a classification model using DistilBERT (Sanh et al., 2019), which we extend with demographic information. In order to preserve the privacy of speakers, we investigate encoding demographic information using autoencoders. We find that adding demographic information improves performance, even if such information is encoded. In addition, we find that the performance per UPV is linked to the number of occurrences of that value in our data.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="van-boven-etal-2022-intersection">
<titleInfo>
<title>At the Intersection of NLP and Sustainable Development: Exploring the Impact of Demographic-Aware Text Representations in Modeling Value on a Corpus of Interviews</title>
</titleInfo>
<name type="personal">
<namePart type="given">Goya</namePart>
<namePart type="family">van Boven</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stephanie</namePart>
<namePart type="family">Hirmer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Costanza</namePart>
<namePart type="family">Conforti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Thirteenth Language Resources and Evaluation Conference</title>
</titleInfo>
<name type="personal">
<namePart type="given">Nicoletta</namePart>
<namePart type="family">Calzolari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Frédéric</namePart>
<namePart type="family">Béchet</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Philippe</namePart>
<namePart type="family">Blache</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Khalid</namePart>
<namePart type="family">Choukri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Christopher</namePart>
<namePart type="family">Cieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Thierry</namePart>
<namePart type="family">Declerck</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sara</namePart>
<namePart type="family">Goggi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hitoshi</namePart>
<namePart type="family">Isahara</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bente</namePart>
<namePart type="family">Maegaard</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Joseph</namePart>
<namePart type="family">Mariani</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hélène</namePart>
<namePart type="family">Mazo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jan</namePart>
<namePart type="family">Odijk</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Stelios</namePart>
<namePart type="family">Piperidis</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>European Language Resources Association</publisher>
<place>
<placeTerm type="text">Marseille, France</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This research explores automated text classification using data from Low– and Middle–Income Countries (LMICs). In particular, we explore enhancing text representations with demographic information of speakers in a privacy-preserving manner. We introduce the Demographic-Rich Qualitative UPV-Interviews Dataset (DR-QI), a rich dataset of qualitative interviews from rural communities in India and Uganda. The interviews were conducted following the latest standards for respectful interactions with illiterate speakers (Hirmer et al., 2021a). The interviews were later sentence-annotated for Automated User-Perceived Value (UPV) Classification (Conforti et al., 2020), a schema that classifies values expressed by speakers, resulting in a dataset of 5,333 sentences. We perform the UPV classification task, which consists of predicting which values are expressed in a given sentence, on the new DR-QI dataset. We implement a classification model using DistilBERT (Sanh et al., 2019), which we extend with demographic information. In order to preserve the privacy of speakers, we investigate encoding demographic information using autoencoders. We find that adding demographic information improves performance, even if such information is encoded. In addition, we find that the performance per UPV is linked to the number of occurrences of that value in our data.</abstract>
<identifier type="citekey">van-boven-etal-2022-intersection</identifier>
<location>
<url>https://aclanthology.org/2022.lrec-1.216</url>
</location>
<part>
<date>2022-06</date>
<extent unit="page">
<start>2007</start>
<end>2021</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T At the Intersection of NLP and Sustainable Development: Exploring the Impact of Demographic-Aware Text Representations in Modeling Value on a Corpus of Interviews
%A van Boven, Goya
%A Hirmer, Stephanie
%A Conforti, Costanza
%Y Calzolari, Nicoletta
%Y Béchet, Frédéric
%Y Blache, Philippe
%Y Choukri, Khalid
%Y Cieri, Christopher
%Y Declerck, Thierry
%Y Goggi, Sara
%Y Isahara, Hitoshi
%Y Maegaard, Bente
%Y Mariani, Joseph
%Y Mazo, Hélène
%Y Odijk, Jan
%Y Piperidis, Stelios
%S Proceedings of the Thirteenth Language Resources and Evaluation Conference
%D 2022
%8 June
%I European Language Resources Association
%C Marseille, France
%F van-boven-etal-2022-intersection
%X This research explores automated text classification using data from Low– and Middle–Income Countries (LMICs). In particular, we explore enhancing text representations with demographic information of speakers in a privacy-preserving manner. We introduce the Demographic-Rich Qualitative UPV-Interviews Dataset (DR-QI), a rich dataset of qualitative interviews from rural communities in India and Uganda. The interviews were conducted following the latest standards for respectful interactions with illiterate speakers (Hirmer et al., 2021a). The interviews were later sentence-annotated for Automated User-Perceived Value (UPV) Classification (Conforti et al., 2020), a schema that classifies values expressed by speakers, resulting in a dataset of 5,333 sentences. We perform the UPV classification task, which consists of predicting which values are expressed in a given sentence, on the new DR-QI dataset. We implement a classification model using DistilBERT (Sanh et al., 2019), which we extend with demographic information. In order to preserve the privacy of speakers, we investigate encoding demographic information using autoencoders. We find that adding demographic information improves performance, even if such information is encoded. In addition, we find that the performance per UPV is linked to the number of occurrences of that value in our data.
%U https://aclanthology.org/2022.lrec-1.216
%P 2007-2021
Markdown (Informal)
[At the Intersection of NLP and Sustainable Development: Exploring the Impact of Demographic-Aware Text Representations in Modeling Value on a Corpus of Interviews](https://aclanthology.org/2022.lrec-1.216) (van Boven et al., LREC 2022)
ACL