@inproceedings{goel-sharma-2019-usf,
title = "{USF} at {S}em{E}val-2019 Task 6: Offensive Language Detection Using {LSTM} With Word Embeddings",
author = "Goel, Bharti and
Sharma, Ravi",
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/S19-2139/",
doi = "10.18653/v1/S19-2139",
pages = "796--800",
abstract = "In this paper, we present a system description for the SemEval-2019 Task 6 submitted by our team. For the task, our system takes tweet as an input and determine if the tweet is offensive or non-offensive (Sub-task A). In case a tweet is offensive, our system identifies if a tweet is targeted (insult or threat) or non-targeted like swearing (Sub-task B). In targeted tweets, our system identifies the target as an individual or group (Sub-task C). We used data pre-processing techniques like splitting hashtags into words, removing special characters, stop-word removal, stemming, lemmatization, capitalization, and offensive word dictionary. Later, we used keras tokenizer and word embeddings for feature extraction. For classification, we used the LSTM (Long short-term memory) model of keras framework. Our accuracy scores for Sub-task A, B and C are \textit{0.8128}, \textit{0.8167} and \textit{0.3662} respectively. Our results indicate that fine-grained classification to identify offense target was difficult for the system. Lastly, in the future scope section, we will discuss the ways to improve system performance."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="goel-sharma-2019-usf">
<titleInfo>
<title>USF at SemEval-2019 Task 6: Offensive Language Detection Using LSTM With Word Embeddings</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharti</namePart>
<namePart type="family">Goel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ravi</namePart>
<namePart type="family">Sharma</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 this paper, we present a system description for the SemEval-2019 Task 6 submitted by our team. For the task, our system takes tweet as an input and determine if the tweet is offensive or non-offensive (Sub-task A). In case a tweet is offensive, our system identifies if a tweet is targeted (insult or threat) or non-targeted like swearing (Sub-task B). In targeted tweets, our system identifies the target as an individual or group (Sub-task C). We used data pre-processing techniques like splitting hashtags into words, removing special characters, stop-word removal, stemming, lemmatization, capitalization, and offensive word dictionary. Later, we used keras tokenizer and word embeddings for feature extraction. For classification, we used the LSTM (Long short-term memory) model of keras framework. Our accuracy scores for Sub-task A, B and C are 0.8128, 0.8167 and 0.3662 respectively. Our results indicate that fine-grained classification to identify offense target was difficult for the system. Lastly, in the future scope section, we will discuss the ways to improve system performance.</abstract>
<identifier type="citekey">goel-sharma-2019-usf</identifier>
<identifier type="doi">10.18653/v1/S19-2139</identifier>
<location>
<url>https://aclanthology.org/S19-2139/</url>
</location>
<part>
<date>2019-06</date>
<extent unit="page">
<start>796</start>
<end>800</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T USF at SemEval-2019 Task 6: Offensive Language Detection Using LSTM With Word Embeddings
%A Goel, Bharti
%A Sharma, Ravi
%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 goel-sharma-2019-usf
%X In this paper, we present a system description for the SemEval-2019 Task 6 submitted by our team. For the task, our system takes tweet as an input and determine if the tweet is offensive or non-offensive (Sub-task A). In case a tweet is offensive, our system identifies if a tweet is targeted (insult or threat) or non-targeted like swearing (Sub-task B). In targeted tweets, our system identifies the target as an individual or group (Sub-task C). We used data pre-processing techniques like splitting hashtags into words, removing special characters, stop-word removal, stemming, lemmatization, capitalization, and offensive word dictionary. Later, we used keras tokenizer and word embeddings for feature extraction. For classification, we used the LSTM (Long short-term memory) model of keras framework. Our accuracy scores for Sub-task A, B and C are 0.8128, 0.8167 and 0.3662 respectively. Our results indicate that fine-grained classification to identify offense target was difficult for the system. Lastly, in the future scope section, we will discuss the ways to improve system performance.
%R 10.18653/v1/S19-2139
%U https://aclanthology.org/S19-2139/
%U https://doi.org/10.18653/v1/S19-2139
%P 796-800
Markdown (Informal)
[USF at SemEval-2019 Task 6: Offensive Language Detection Using LSTM With Word Embeddings](https://aclanthology.org/S19-2139/) (Goel & Sharma, SemEval 2019)
ACL