@inproceedings{ameer-etal-2019-cic,
title = "{CIC} at {S}em{E}val-2019 Task 5: Simple Yet Very Efficient Approach to Hate Speech Detection, Aggressive Behavior Detection, and Target Classification in {T}witter",
author = "Ameer, Iqra and
Siddiqui, Muhammad Hammad Fahim and
Sidorov, Grigori and
Gelbukh, Alexander",
editor = "May, Jonathan and
Shutova, Ekaterina and
Herbelot, Aurelie and
Zhu, Xiaodan and
Apidianaki, Marianna and
Mohammad, Saif M.",
booktitle = "Proceedings of the 13th International Workshop on Semantic Evaluation",
month = jun,
year = "2019",
address = "Minneapolis, Minnesota, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/S19-2067",
doi = "10.18653/v1/S19-2067",
pages = "382--386",
abstract = "In recent years, the use of social media has in-creased incredibly. Social media permits Inter-net users a friendly platform to express their views and opinions. Along with these nice and distinct communication chances, it also allows bad things like usage of hate speech. Online automatic hate speech detection in various aspects is a significant scientific problem. This paper presents the Instituto Polit{\'e}cnico Nacional (Mexico) approach for the Semeval 2019 Task-5 [Hateval 2019] (Basile et al., 2019) competition for Multilingual Detection of Hate Speech on Twitter. The goal of this paper is to detect (A) Hate speech against immigrants and women, (B) Aggressive behavior and target classification, both for English and Spanish. In the proposed approach, we used a bag of words model with preprocessing (stem-ming and stop words removal). We submitted two different systems with names: (i) CIC-1 and (ii) CIC-2 for Hateval 2019 shared task. We used TF values in the first system and TF-IDF for the second system. The first system, CIC-1 got 2nd rank in subtask B for both English and Spanish languages with EMR score of 0.568 for English and 0.675 for Spanish. The second system, CIC-2 was ranked 4th in sub-task A and 1st in subtask B for Spanish language with a macro-F1 score of 0.727 and EMR score of 0.705 respectively.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="ameer-etal-2019-cic">
<titleInfo>
<title>CIC at SemEval-2019 Task 5: Simple Yet Very Efficient Approach to Hate Speech Detection, Aggressive Behavior Detection, and Target Classification in Twitter</title>
</titleInfo>
<name type="personal">
<namePart type="given">Iqra</namePart>
<namePart type="family">Ameer</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Muhammad</namePart>
<namePart type="given">Hammad</namePart>
<namePart type="given">Fahim</namePart>
<namePart type="family">Siddiqui</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Grigori</namePart>
<namePart type="family">Sidorov</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Alexander</namePart>
<namePart type="family">Gelbukh</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2019-06</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 13th International Workshop on Semantic Evaluation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jonathan</namePart>
<namePart type="family">May</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>
<name type="personal">
<namePart type="given">Aurelie</namePart>
<namePart type="family">Herbelot</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiaodan</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Marianna</namePart>
<namePart type="family">Apidianaki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Saif</namePart>
<namePart type="given">M</namePart>
<namePart type="family">Mohammad</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Minneapolis, Minnesota, USA</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In recent years, the use of social media has in-creased incredibly. Social media permits Inter-net users a friendly platform to express their views and opinions. Along with these nice and distinct communication chances, it also allows bad things like usage of hate speech. Online automatic hate speech detection in various aspects is a significant scientific problem. This paper presents the Instituto Politécnico Nacional (Mexico) approach for the Semeval 2019 Task-5 [Hateval 2019] (Basile et al., 2019) competition for Multilingual Detection of Hate Speech on Twitter. The goal of this paper is to detect (A) Hate speech against immigrants and women, (B) Aggressive behavior and target classification, both for English and Spanish. In the proposed approach, we used a bag of words model with preprocessing (stem-ming and stop words removal). We submitted two different systems with names: (i) CIC-1 and (ii) CIC-2 for Hateval 2019 shared task. We used TF values in the first system and TF-IDF for the second system. The first system, CIC-1 got 2nd rank in subtask B for both English and Spanish languages with EMR score of 0.568 for English and 0.675 for Spanish. The second system, CIC-2 was ranked 4th in sub-task A and 1st in subtask B for Spanish language with a macro-F1 score of 0.727 and EMR score of 0.705 respectively.</abstract>
<identifier type="citekey">ameer-etal-2019-cic</identifier>
<identifier type="doi">10.18653/v1/S19-2067</identifier>
<location>
<url>https://aclanthology.org/S19-2067</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>382</start>
<end>386</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CIC at SemEval-2019 Task 5: Simple Yet Very Efficient Approach to Hate Speech Detection, Aggressive Behavior Detection, and Target Classification in Twitter
%A Ameer, Iqra
%A Siddiqui, Muhammad Hammad Fahim
%A Sidorov, Grigori
%A Gelbukh, Alexander
%Y May, Jonathan
%Y Shutova, Ekaterina
%Y Herbelot, Aurelie
%Y Zhu, Xiaodan
%Y Apidianaki, Marianna
%Y Mohammad, Saif M.
%S Proceedings of the 13th International Workshop on Semantic Evaluation
%D 2019
%8 June
%I Association for Computational Linguistics
%C Minneapolis, Minnesota, USA
%F ameer-etal-2019-cic
%X In recent years, the use of social media has in-creased incredibly. Social media permits Inter-net users a friendly platform to express their views and opinions. Along with these nice and distinct communication chances, it also allows bad things like usage of hate speech. Online automatic hate speech detection in various aspects is a significant scientific problem. This paper presents the Instituto Politécnico Nacional (Mexico) approach for the Semeval 2019 Task-5 [Hateval 2019] (Basile et al., 2019) competition for Multilingual Detection of Hate Speech on Twitter. The goal of this paper is to detect (A) Hate speech against immigrants and women, (B) Aggressive behavior and target classification, both for English and Spanish. In the proposed approach, we used a bag of words model with preprocessing (stem-ming and stop words removal). We submitted two different systems with names: (i) CIC-1 and (ii) CIC-2 for Hateval 2019 shared task. We used TF values in the first system and TF-IDF for the second system. The first system, CIC-1 got 2nd rank in subtask B for both English and Spanish languages with EMR score of 0.568 for English and 0.675 for Spanish. The second system, CIC-2 was ranked 4th in sub-task A and 1st in subtask B for Spanish language with a macro-F1 score of 0.727 and EMR score of 0.705 respectively.
%R 10.18653/v1/S19-2067
%U https://aclanthology.org/S19-2067
%U https://doi.org/10.18653/v1/S19-2067
%P 382-386
Markdown (Informal)
[CIC at SemEval-2019 Task 5: Simple Yet Very Efficient Approach to Hate Speech Detection, Aggressive Behavior Detection, and Target Classification in Twitter](https://aclanthology.org/S19-2067) (Ameer et al., SemEval 2019)
ACL