@inproceedings{bianchi-etal-2022-twitter,
title = "{T}witter-Demographer: A Flow-based Tool to Enrich {T}witter Data",
author = "Bianchi, Federico and
Cutrona, Vincenzo and
Hovy, Dirk",
editor = "Che, Wanxiang and
Shutova, Ekaterina",
booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations",
month = dec,
year = "2022",
address = "Abu Dhabi, UAE",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.emnlp-demos.29",
doi = "10.18653/v1/2022.emnlp-demos.29",
pages = "289--297",
abstract = "Twitter data have become essential to Natural Language Processing (NLP) and social science research, driving various scientific discoveries in recent years. However, the textual data alone are often not enough to conduct studies: especially, social scientists need more variables to perform their analysis and control for various factors. How we augment this information, such as users{'} location, age, or tweet sentiment, has ramifications for anonymity and reproducibility, and requires dedicated effort. This paper describes Twitter-Demographer, a simple, flow-based tool to enrich Twitter data with additional information about tweets and users. {\textbackslash}tool is aimed at NLP practitioners, psycho-linguists, and (computational) social scientists who want to enrich their datasets with aggregated information, facilitating reproducibility, and providing algorithmic privacy-by-design measures for pseudo-anonymity. We discuss our design choices, inspired by the flow-based programming paradigm, to use black-box components that can easily be chained together and extended. We also analyze the ethical issues related to the use of this tool, and the built-in measures to facilitate pseudo-anonymity.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bianchi-etal-2022-twitter">
<titleInfo>
<title>Twitter-Demographer: A Flow-based Tool to Enrich Twitter Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Federico</namePart>
<namePart type="family">Bianchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vincenzo</namePart>
<namePart type="family">Cutrona</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dirk</namePart>
<namePart type="family">Hovy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2022-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations</title>
</titleInfo>
<name type="personal">
<namePart type="given">Wanxiang</namePart>
<namePart type="family">Che</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekaterina</namePart>
<namePart type="family">Shutova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Abu Dhabi, UAE</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Twitter data have become essential to Natural Language Processing (NLP) and social science research, driving various scientific discoveries in recent years. However, the textual data alone are often not enough to conduct studies: especially, social scientists need more variables to perform their analysis and control for various factors. How we augment this information, such as users’ location, age, or tweet sentiment, has ramifications for anonymity and reproducibility, and requires dedicated effort. This paper describes Twitter-Demographer, a simple, flow-based tool to enrich Twitter data with additional information about tweets and users. \textbackslashtool is aimed at NLP practitioners, psycho-linguists, and (computational) social scientists who want to enrich their datasets with aggregated information, facilitating reproducibility, and providing algorithmic privacy-by-design measures for pseudo-anonymity. We discuss our design choices, inspired by the flow-based programming paradigm, to use black-box components that can easily be chained together and extended. We also analyze the ethical issues related to the use of this tool, and the built-in measures to facilitate pseudo-anonymity.</abstract>
<identifier type="citekey">bianchi-etal-2022-twitter</identifier>
<identifier type="doi">10.18653/v1/2022.emnlp-demos.29</identifier>
<location>
<url>https://aclanthology.org/2022.emnlp-demos.29</url>
</location>
<part>
<date>2022-12</date>
<extent unit="page">
<start>289</start>
<end>297</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Twitter-Demographer: A Flow-based Tool to Enrich Twitter Data
%A Bianchi, Federico
%A Cutrona, Vincenzo
%A Hovy, Dirk
%Y Che, Wanxiang
%Y Shutova, Ekaterina
%S Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations
%D 2022
%8 December
%I Association for Computational Linguistics
%C Abu Dhabi, UAE
%F bianchi-etal-2022-twitter
%X Twitter data have become essential to Natural Language Processing (NLP) and social science research, driving various scientific discoveries in recent years. However, the textual data alone are often not enough to conduct studies: especially, social scientists need more variables to perform their analysis and control for various factors. How we augment this information, such as users’ location, age, or tweet sentiment, has ramifications for anonymity and reproducibility, and requires dedicated effort. This paper describes Twitter-Demographer, a simple, flow-based tool to enrich Twitter data with additional information about tweets and users. \textbackslashtool is aimed at NLP practitioners, psycho-linguists, and (computational) social scientists who want to enrich their datasets with aggregated information, facilitating reproducibility, and providing algorithmic privacy-by-design measures for pseudo-anonymity. We discuss our design choices, inspired by the flow-based programming paradigm, to use black-box components that can easily be chained together and extended. We also analyze the ethical issues related to the use of this tool, and the built-in measures to facilitate pseudo-anonymity.
%R 10.18653/v1/2022.emnlp-demos.29
%U https://aclanthology.org/2022.emnlp-demos.29
%U https://doi.org/10.18653/v1/2022.emnlp-demos.29
%P 289-297
Markdown (Informal)
[Twitter-Demographer: A Flow-based Tool to Enrich Twitter Data](https://aclanthology.org/2022.emnlp-demos.29) (Bianchi et al., EMNLP 2022)
ACL
- Federico Bianchi, Vincenzo Cutrona, and Dirk Hovy. 2022. Twitter-Demographer: A Flow-based Tool to Enrich Twitter Data. In Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, pages 289–297, Abu Dhabi, UAE. Association for Computational Linguistics.