@inproceedings{perez-melian-etal-2017-zipfs,
title = "{Z}ipf{'}s and {B}enford{'}s laws in {T}witter hashtags",
author = "P{\'e}rez Meli{\'a}n, Jos{\'e} Alberto and
Conejero, J. Alberto and
Ferri Ram{\'\i}rez, C{\`e}sar",
booktitle = "Proceedings of the Student Research Workshop at the 15th Conference of the {E}uropean Chapter of the Association for Computational Linguistics",
month = apr,
year = "2017",
address = "Valencia, Spain",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/E17-4009",
pages = "84--93",
abstract = "Social networks have transformed communication dramatically in recent years through the rise of new platforms and the development of a new language of communication. This landscape requires new forms to describe and predict the behaviour of users in networks. This paper presents an analysis of the frequency distribution of hashtag popularity in Twitter conversations. Our objective is to determine if these frequency distribution follow some well-known frequency distribution that many real-life sets of numerical data satisfy. In particular, we study the similarity of frequency distribution of hashtag popularity with respect to Zipf{'}s law, an empirical law referring to the phenomenon that many types of data in social sciences can be approximated with a Zipfian distribution. Additionally, we also analyse Benford{'}s law, is a special case of Zipf{'}s law, a common pattern about the frequency distribution of leading digits. In order to compute correctly the frequency distribution of hashtag popularity, we need to correct many spelling errors that Twitter{'}s users introduce. For this purpose we introduce a new filter to correct hashtag mistake based on string distances. The experiments obtained employing datasets of Twitter streams generated under controlled conditions show that Benford{'}s law and Zipf{'}s law can be used to model hashtag frequency distribution.",
}

<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="perez-melian-etal-2017-zipfs">
<titleInfo>
<title>Zipf’s and Benford’s laws in Twitter hashtags</title>
</titleInfo>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="given">Alberto</namePart>
<namePart type="family">Pérez Melián</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">J</namePart>
<namePart type="given">Alberto</namePart>
<namePart type="family">Conejero</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cèsar</namePart>
<namePart type="family">Ferri Ramírez</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2017-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Student Research Workshop at the 15th Conference of the European Chapter of the Association for Computational Linguistics</title>
</titleInfo>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Valencia, Spain</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Social networks have transformed communication dramatically in recent years through the rise of new platforms and the development of a new language of communication. This landscape requires new forms to describe and predict the behaviour of users in networks. This paper presents an analysis of the frequency distribution of hashtag popularity in Twitter conversations. Our objective is to determine if these frequency distribution follow some well-known frequency distribution that many real-life sets of numerical data satisfy. In particular, we study the similarity of frequency distribution of hashtag popularity with respect to Zipf’s law, an empirical law referring to the phenomenon that many types of data in social sciences can be approximated with a Zipfian distribution. Additionally, we also analyse Benford’s law, is a special case of Zipf’s law, a common pattern about the frequency distribution of leading digits. In order to compute correctly the frequency distribution of hashtag popularity, we need to correct many spelling errors that Twitter’s users introduce. For this purpose we introduce a new filter to correct hashtag mistake based on string distances. The experiments obtained employing datasets of Twitter streams generated under controlled conditions show that Benford’s law and Zipf’s law can be used to model hashtag frequency distribution.</abstract>
<identifier type="citekey">perez-melian-etal-2017-zipfs</identifier>
<location>
<url>https://aclanthology.org/E17-4009</url>
</location>
<part>
<date>2017-04</date>
<extent unit="page">
<start>84</start>
<end>93</end>
</extent>
</part>
</mods>
</modsCollection>

%0 Conference Proceedings
%T Zipf’s and Benford’s laws in Twitter hashtags
%A Pérez Melián, José Alberto
%A Conejero, J. Alberto
%A Ferri Ramírez, Cèsar
%S Proceedings of the Student Research Workshop at the 15th Conference of the European Chapter of the Association for Computational Linguistics
%D 2017
%8 April
%I Association for Computational Linguistics
%C Valencia, Spain
%F perez-melian-etal-2017-zipfs
%X Social networks have transformed communication dramatically in recent years through the rise of new platforms and the development of a new language of communication. This landscape requires new forms to describe and predict the behaviour of users in networks. This paper presents an analysis of the frequency distribution of hashtag popularity in Twitter conversations. Our objective is to determine if these frequency distribution follow some well-known frequency distribution that many real-life sets of numerical data satisfy. In particular, we study the similarity of frequency distribution of hashtag popularity with respect to Zipf’s law, an empirical law referring to the phenomenon that many types of data in social sciences can be approximated with a Zipfian distribution. Additionally, we also analyse Benford’s law, is a special case of Zipf’s law, a common pattern about the frequency distribution of leading digits. In order to compute correctly the frequency distribution of hashtag popularity, we need to correct many spelling errors that Twitter’s users introduce. For this purpose we introduce a new filter to correct hashtag mistake based on string distances. The experiments obtained employing datasets of Twitter streams generated under controlled conditions show that Benford’s law and Zipf’s law can be used to model hashtag frequency distribution.
%U https://aclanthology.org/E17-4009
%P 84-93

##### Markdown (Informal)

[Zipf’s and Benford’s laws in Twitter hashtags](https://aclanthology.org/E17-4009) (Pérez Melián et al., EACL 2017)

##### ACL

- José Alberto Pérez Melián, J. Alberto Conejero, and Cèsar Ferri Ramírez. 2017. Zipf’s and Benford’s laws in Twitter hashtags. In
*Proceedings of the Student Research Workshop at the 15th Conference of the European Chapter of the Association for Computational Linguistics*, pages 84–93, Valencia, Spain. Association for Computational Linguistics.