@inproceedings{fiorentini-etal-2024-towards,
title = "Towards the {W}h{AP} Corpus: A Resource for the Study of {I}talian on {W}hats{A}pp",
author = "Fiorentini, Ilaria and
Forlano, Marco and
Nese, Nicholas",
editor = "Calzolari, Nicoletta and
Kan, Min-Yen and
Hoste, Veronique and
Lenci, Alessandro and
Sakti, Sakriani and
Xue, Nianwen",
booktitle = "Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)",
month = may,
year = "2024",
address = "Torino, Italia",
publisher = "ELRA and ICCL",
url = "https://aclanthology.org/2024.lrec-main.1448/",
pages = "16659--16663",
abstract = "Over the past two decades, the rise of new technologies and social networks has significantly shaped written language, imbuing it with characteristics akin to the spoken language. This study reports on the ongoing initiative to build the WhAP corpus, a resource featuring WhatsApp conversations in Italian, encompassing both written and spoken messages and totaling at present more than 400.000 tokens, 89 conversations, and 194 participants from diverse age groups and geographical regions of Italy. More specifically, this paper focuses on the practical steps involved in the construction of the resource. Once publicly accessible, the WhAP Corpus will enable in-depth linguistic research on the language used on WhatsApp, which shows unique features such as the blending of written and spoken elements."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fiorentini-etal-2024-towards">
<titleInfo>
<title>Towards the WhAP Corpus: A Resource for the Study of Italian on WhatsApp</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ilaria</namePart>
<namePart type="family">Fiorentini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marco</namePart>
<namePart type="family">Forlano</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nicholas</namePart>
<namePart type="family">Nese</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2024-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)</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">Min-Yen</namePart>
<namePart type="family">Kan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Veronique</namePart>
<namePart type="family">Hoste</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alessandro</namePart>
<namePart type="family">Lenci</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sakriani</namePart>
<namePart type="family">Sakti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nianwen</namePart>
<namePart type="family">Xue</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>ELRA and ICCL</publisher>
<place>
<placeTerm type="text">Torino, Italia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Over the past two decades, the rise of new technologies and social networks has significantly shaped written language, imbuing it with characteristics akin to the spoken language. This study reports on the ongoing initiative to build the WhAP corpus, a resource featuring WhatsApp conversations in Italian, encompassing both written and spoken messages and totaling at present more than 400.000 tokens, 89 conversations, and 194 participants from diverse age groups and geographical regions of Italy. More specifically, this paper focuses on the practical steps involved in the construction of the resource. Once publicly accessible, the WhAP Corpus will enable in-depth linguistic research on the language used on WhatsApp, which shows unique features such as the blending of written and spoken elements.</abstract>
<identifier type="citekey">fiorentini-etal-2024-towards</identifier>
<location>
<url>https://aclanthology.org/2024.lrec-main.1448/</url>
</location>
<part>
<date>2024-05</date>
<extent unit="page">
<start>16659</start>
<end>16663</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards the WhAP Corpus: A Resource for the Study of Italian on WhatsApp
%A Fiorentini, Ilaria
%A Forlano, Marco
%A Nese, Nicholas
%Y Calzolari, Nicoletta
%Y Kan, Min-Yen
%Y Hoste, Veronique
%Y Lenci, Alessandro
%Y Sakti, Sakriani
%Y Xue, Nianwen
%S Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
%D 2024
%8 May
%I ELRA and ICCL
%C Torino, Italia
%F fiorentini-etal-2024-towards
%X Over the past two decades, the rise of new technologies and social networks has significantly shaped written language, imbuing it with characteristics akin to the spoken language. This study reports on the ongoing initiative to build the WhAP corpus, a resource featuring WhatsApp conversations in Italian, encompassing both written and spoken messages and totaling at present more than 400.000 tokens, 89 conversations, and 194 participants from diverse age groups and geographical regions of Italy. More specifically, this paper focuses on the practical steps involved in the construction of the resource. Once publicly accessible, the WhAP Corpus will enable in-depth linguistic research on the language used on WhatsApp, which shows unique features such as the blending of written and spoken elements.
%U https://aclanthology.org/2024.lrec-main.1448/
%P 16659-16663
Markdown (Informal)
[Towards the WhAP Corpus: A Resource for the Study of Italian on WhatsApp](https://aclanthology.org/2024.lrec-main.1448/) (Fiorentini et al., LREC-COLING 2024)
ACL