@inproceedings{belainine-etal-2016-named,
title = "Named Entity Recognition and Hashtag Decomposition to Improve the Classification of Tweets",
author = "Belainine, Billal and
Fonseca, Alexsandro and
Sadat, Fatiha",
editor = "Han, Bo and
Ritter, Alan and
Derczynski, Leon and
Xu, Wei and
Baldwin, Tim",
booktitle = "Proceedings of the 2nd Workshop on Noisy User-generated Text ({WNUT})",
month = dec,
year = "2016",
address = "Osaka, Japan",
publisher = "The COLING 2016 Organizing Committee",
url = "https://aclanthology.org/W16-3915",
pages = "102--111",
abstract = "In social networks services like Twitter, users are overwhelmed with huge amount of social data, most of which are short, unstructured and highly noisy. Identifying accurate information from this huge amount of data is indeed a hard task. Classification of tweets into organized form will help the user to easily access these required information. Our first contribution relates to filtering parts of speech and preprocessing this kind of highly noisy and short data. Our second contribution concerns the named entity recognition (NER) in tweets. Thus, the adaptation of existing language tools for natural languages, noisy and not accurate language tweets, is necessary. Our third contribution involves segmentation of hashtags and a semantic enrichment using a combination of relations from WordNet, which helps the performance of our classification system, including disambiguation of named entities, abbreviations and acronyms. Graph theory is used to cluster the words extracted from WordNet and tweets, based on the idea of connected components. We test our automatic classification system with four categories: politics, economy, sports and the medical field. We evaluate and compare several automatic classification systems using part or all of the items described in our contributions and found that filtering by part of speech and named entity recognition dramatically increase the classification precision to 77.3 {\%}. Moreover, a classification system incorporating segmentation of hashtags and semantic enrichment by two relations from WordNet, synonymy and hyperonymy, increase classification precision up to 83.4 {\%}.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="belainine-etal-2016-named">
<titleInfo>
<title>Named Entity Recognition and Hashtag Decomposition to Improve the Classification of Tweets</title>
</titleInfo>
<name type="personal">
<namePart type="given">Billal</namePart>
<namePart type="family">Belainine</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexsandro</namePart>
<namePart type="family">Fonseca</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Fatiha</namePart>
<namePart type="family">Sadat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2016-12</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bo</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alan</namePart>
<namePart type="family">Ritter</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Leon</namePart>
<namePart type="family">Derczynski</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Wei</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tim</namePart>
<namePart type="family">Baldwin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>The COLING 2016 Organizing Committee</publisher>
<place>
<placeTerm type="text">Osaka, Japan</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In social networks services like Twitter, users are overwhelmed with huge amount of social data, most of which are short, unstructured and highly noisy. Identifying accurate information from this huge amount of data is indeed a hard task. Classification of tweets into organized form will help the user to easily access these required information. Our first contribution relates to filtering parts of speech and preprocessing this kind of highly noisy and short data. Our second contribution concerns the named entity recognition (NER) in tweets. Thus, the adaptation of existing language tools for natural languages, noisy and not accurate language tweets, is necessary. Our third contribution involves segmentation of hashtags and a semantic enrichment using a combination of relations from WordNet, which helps the performance of our classification system, including disambiguation of named entities, abbreviations and acronyms. Graph theory is used to cluster the words extracted from WordNet and tweets, based on the idea of connected components. We test our automatic classification system with four categories: politics, economy, sports and the medical field. We evaluate and compare several automatic classification systems using part or all of the items described in our contributions and found that filtering by part of speech and named entity recognition dramatically increase the classification precision to 77.3 %. Moreover, a classification system incorporating segmentation of hashtags and semantic enrichment by two relations from WordNet, synonymy and hyperonymy, increase classification precision up to 83.4 %.</abstract>
<identifier type="citekey">belainine-etal-2016-named</identifier>
<location>
<url>https://aclanthology.org/W16-3915</url>
</location>
<part>
<date>2016-12</date>
<extent unit="page">
<start>102</start>
<end>111</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Named Entity Recognition and Hashtag Decomposition to Improve the Classification of Tweets
%A Belainine, Billal
%A Fonseca, Alexsandro
%A Sadat, Fatiha
%Y Han, Bo
%Y Ritter, Alan
%Y Derczynski, Leon
%Y Xu, Wei
%Y Baldwin, Tim
%S Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT)
%D 2016
%8 December
%I The COLING 2016 Organizing Committee
%C Osaka, Japan
%F belainine-etal-2016-named
%X In social networks services like Twitter, users are overwhelmed with huge amount of social data, most of which are short, unstructured and highly noisy. Identifying accurate information from this huge amount of data is indeed a hard task. Classification of tweets into organized form will help the user to easily access these required information. Our first contribution relates to filtering parts of speech and preprocessing this kind of highly noisy and short data. Our second contribution concerns the named entity recognition (NER) in tweets. Thus, the adaptation of existing language tools for natural languages, noisy and not accurate language tweets, is necessary. Our third contribution involves segmentation of hashtags and a semantic enrichment using a combination of relations from WordNet, which helps the performance of our classification system, including disambiguation of named entities, abbreviations and acronyms. Graph theory is used to cluster the words extracted from WordNet and tweets, based on the idea of connected components. We test our automatic classification system with four categories: politics, economy, sports and the medical field. We evaluate and compare several automatic classification systems using part or all of the items described in our contributions and found that filtering by part of speech and named entity recognition dramatically increase the classification precision to 77.3 %. Moreover, a classification system incorporating segmentation of hashtags and semantic enrichment by two relations from WordNet, synonymy and hyperonymy, increase classification precision up to 83.4 %.
%U https://aclanthology.org/W16-3915
%P 102-111
Markdown (Informal)
[Named Entity Recognition and Hashtag Decomposition to Improve the Classification of Tweets](https://aclanthology.org/W16-3915) (Belainine et al., WNUT 2016)
ACL