@inproceedings{fortuna-etal-2018-merging,
title = "Merging Datasets for Aggressive Text Identification",
author = "Fortuna, Paula and
Ferreira, Jos{\'e} and
Pires, Luiz and
Routar, Guilherme and
Nunes, S{\'e}rgio",
editor = "Kumar, Ritesh and
Ojha, Atul Kr. and
Zampieri, Marcos and
Malmasi, Shervin",
booktitle = "Proceedings of the First Workshop on Trolling, Aggression and Cyberbullying ({TRAC}-2018)",
month = aug,
year = "2018",
address = "Santa Fe, New Mexico, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/W18-4416",
pages = "128--139",
abstract = "This paper presents the approach of the team {``}groutar{''} to the shared task on Aggression Identification, considering the test sets in English, both from Facebook and general Social Media. This experiment aims to test the effect of merging new datasets in the performance of classification models. We followed a standard machine learning approach with training, validation, and testing phases, and considered features such as part-of-speech, frequencies of insults, punctuation, sentiment, and capitalization. In terms of algorithms, we experimented with Boosted Logistic Regression, Multi-Layer Perceptron, Parallel Random Forest and eXtreme Gradient Boosting. One question appearing was how to merge datasets using different classification systems (e.g. aggression vs. toxicity). Other issue concerns the possibility to generalize models and apply them to data from different social networks. Regarding these, we merged two datasets, and the results showed that training with similar data is an advantage in the classification of social networks data. However, adding data from different platforms, allowed slightly better results in both Facebook and Social Media, indicating that more generalized models can be an advantage.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fortuna-etal-2018-merging">
<titleInfo>
<title>Merging Datasets for Aggressive Text Identification</title>
</titleInfo>
<name type="personal">
<namePart type="given">Paula</namePart>
<namePart type="family">Fortuna</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">José</namePart>
<namePart type="family">Ferreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Luiz</namePart>
<namePart type="family">Pires</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guilherme</namePart>
<namePart type="family">Routar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sérgio</namePart>
<namePart type="family">Nunes</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2018-08</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Trolling, Aggression and Cyberbullying (TRAC-2018)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Ritesh</namePart>
<namePart type="family">Kumar</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Atul</namePart>
<namePart type="given">Kr.</namePart>
<namePart type="family">Ojha</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marcos</namePart>
<namePart type="family">Zampieri</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shervin</namePart>
<namePart type="family">Malmasi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Santa Fe, New Mexico, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>This paper presents the approach of the team “groutar” to the shared task on Aggression Identification, considering the test sets in English, both from Facebook and general Social Media. This experiment aims to test the effect of merging new datasets in the performance of classification models. We followed a standard machine learning approach with training, validation, and testing phases, and considered features such as part-of-speech, frequencies of insults, punctuation, sentiment, and capitalization. In terms of algorithms, we experimented with Boosted Logistic Regression, Multi-Layer Perceptron, Parallel Random Forest and eXtreme Gradient Boosting. One question appearing was how to merge datasets using different classification systems (e.g. aggression vs. toxicity). Other issue concerns the possibility to generalize models and apply them to data from different social networks. Regarding these, we merged two datasets, and the results showed that training with similar data is an advantage in the classification of social networks data. However, adding data from different platforms, allowed slightly better results in both Facebook and Social Media, indicating that more generalized models can be an advantage.</abstract>
<identifier type="citekey">fortuna-etal-2018-merging</identifier>
<location>
<url>https://aclanthology.org/W18-4416</url>
</location>
<part>
<date>2018-08</date>
<extent unit="page">
<start>128</start>
<end>139</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Merging Datasets for Aggressive Text Identification
%A Fortuna, Paula
%A Ferreira, José
%A Pires, Luiz
%A Routar, Guilherme
%A Nunes, Sérgio
%Y Kumar, Ritesh
%Y Ojha, Atul Kr.
%Y Zampieri, Marcos
%Y Malmasi, Shervin
%S Proceedings of the First Workshop on Trolling, Aggression and Cyberbullying (TRAC-2018)
%D 2018
%8 August
%I Association for Computational Linguistics
%C Santa Fe, New Mexico, USA
%F fortuna-etal-2018-merging
%X This paper presents the approach of the team “groutar” to the shared task on Aggression Identification, considering the test sets in English, both from Facebook and general Social Media. This experiment aims to test the effect of merging new datasets in the performance of classification models. We followed a standard machine learning approach with training, validation, and testing phases, and considered features such as part-of-speech, frequencies of insults, punctuation, sentiment, and capitalization. In terms of algorithms, we experimented with Boosted Logistic Regression, Multi-Layer Perceptron, Parallel Random Forest and eXtreme Gradient Boosting. One question appearing was how to merge datasets using different classification systems (e.g. aggression vs. toxicity). Other issue concerns the possibility to generalize models and apply them to data from different social networks. Regarding these, we merged two datasets, and the results showed that training with similar data is an advantage in the classification of social networks data. However, adding data from different platforms, allowed slightly better results in both Facebook and Social Media, indicating that more generalized models can be an advantage.
%U https://aclanthology.org/W18-4416
%P 128-139
Markdown (Informal)
[Merging Datasets for Aggressive Text Identification](https://aclanthology.org/W18-4416) (Fortuna et al., TRAC 2018)
ACL
- Paula Fortuna, José Ferreira, Luiz Pires, Guilherme Routar, and Sérgio Nunes. 2018. Merging Datasets for Aggressive Text Identification. In Proceedings of the First Workshop on Trolling, Aggression and Cyberbullying (TRAC-2018), pages 128–139, Santa Fe, New Mexico, USA. Association for Computational Linguistics.