@inproceedings{castro-etal-2018-crowd,
title = "A Crowd-Annotated {S}panish Corpus for Humor Analysis",
author = "Castro, Santiago and
Chiruzzo, Luis and
Ros{\'a}, Aiala and
Garat, Diego and
Moncecchi, Guillermo",
editor = "Ku, Lun-Wei and
Li, Cheng-Te",
booktitle = "Proceedings of the Sixth International Workshop on Natural Language Processing for Social Media",
month = jul,
year = "2018",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-3502",
doi = "10.18653/v1/W18-3502",
pages = "7--11",
abstract = "Computational Humor involves several tasks, such as humor recognition, humor generation, and humor scoring, for which it is useful to have human-curated data. In this work we present a corpus of 27,000 tweets written in Spanish and crowd-annotated by their humor value and funniness score, with about four annotations per tweet, tagged by 1,300 people over the Internet. It is equally divided between tweets coming from humorous and non-humorous accounts. The inter-annotator agreement Krippendorff{'}s alpha value is 0.5710. The dataset is available for general usage and can serve as a basis for humor detection and as a first step to tackle subjectivity.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="castro-etal-2018-crowd">
<titleInfo>
<title>A Crowd-Annotated Spanish Corpus for Humor Analysis</title>
</titleInfo>
<name type="personal">
<namePart type="given">Santiago</namePart>
<namePart type="family">Castro</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luis</namePart>
<namePart type="family">Chiruzzo</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Aiala</namePart>
<namePart type="family">Rosá</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Diego</namePart>
<namePart type="family">Garat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guillermo</namePart>
<namePart type="family">Moncecchi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Sixth International Workshop on Natural Language Processing for Social Media</title>
</titleInfo>
<name type="personal">
<namePart type="given">Lun-Wei</namePart>
<namePart type="family">Ku</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Cheng-Te</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>Computational Humor involves several tasks, such as humor recognition, humor generation, and humor scoring, for which it is useful to have human-curated data. In this work we present a corpus of 27,000 tweets written in Spanish and crowd-annotated by their humor value and funniness score, with about four annotations per tweet, tagged by 1,300 people over the Internet. It is equally divided between tweets coming from humorous and non-humorous accounts. The inter-annotator agreement Krippendorff’s alpha value is 0.5710. The dataset is available for general usage and can serve as a basis for humor detection and as a first step to tackle subjectivity.</abstract>
<identifier type="citekey">castro-etal-2018-crowd</identifier>
<identifier type="doi">10.18653/v1/W18-3502</identifier>
<location>
<url>https://aclanthology.org/W18-3502</url>
</location>
<part>
<date>2018-07</date>
<extent unit="page">
<start>7</start>
<end>11</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T A Crowd-Annotated Spanish Corpus for Humor Analysis
%A Castro, Santiago
%A Chiruzzo, Luis
%A Rosá, Aiala
%A Garat, Diego
%A Moncecchi, Guillermo
%Y Ku, Lun-Wei
%Y Li, Cheng-Te
%S Proceedings of the Sixth International Workshop on Natural Language Processing for Social Media
%D 2018
%8 July
%I Association for Computational Linguistics
%C Melbourne, Australia
%F castro-etal-2018-crowd
%X Computational Humor involves several tasks, such as humor recognition, humor generation, and humor scoring, for which it is useful to have human-curated data. In this work we present a corpus of 27,000 tweets written in Spanish and crowd-annotated by their humor value and funniness score, with about four annotations per tweet, tagged by 1,300 people over the Internet. It is equally divided between tweets coming from humorous and non-humorous accounts. The inter-annotator agreement Krippendorff’s alpha value is 0.5710. The dataset is available for general usage and can serve as a basis for humor detection and as a first step to tackle subjectivity.
%R 10.18653/v1/W18-3502
%U https://aclanthology.org/W18-3502
%U https://doi.org/10.18653/v1/W18-3502
%P 7-11
Markdown (Informal)
[A Crowd-Annotated Spanish Corpus for Humor Analysis](https://aclanthology.org/W18-3502) (Castro et al., SocialNLP 2018)
ACL
- Santiago Castro, Luis Chiruzzo, Aiala Rosá, Diego Garat, and Guillermo Moncecchi. 2018. A Crowd-Annotated Spanish Corpus for Humor Analysis. In Proceedings of the Sixth International Workshop on Natural Language Processing for Social Media, pages 7–11, Melbourne, Australia. Association for Computational Linguistics.