@inproceedings{hossain-etal-2021-nlp,
title = "{NLP}-{CUET}@{D}ravidian{L}ang{T}ech-{EACL}2021: Investigating Visual and Textual Features to Identify Trolls from Multimodal Social Media Memes",
author = "Hossain, Eftekhar and
Sharif, Omar and
Hoque, Mohammed Moshiul",
editor = "Chakravarthi, Bharathi Raja and
Priyadharshini, Ruba and
Kumar M, Anand and
Krishnamurthy, Parameswari and
Sherly, Elizabeth",
booktitle = "Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages",
month = apr,
year = "2021",
address = "Kyiv",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2021.dravidianlangtech-1.43",
pages = "300--306",
abstract = "In the past few years, the meme has become a new way of communication on the Internet. As memes are in images forms with embedded text, it can quickly spread hate, offence and violence. Classifying memes are very challenging because of their multimodal nature and region-specific interpretation. A shared task is organized to develop models that can identify trolls from multimodal social media memes. This work presents a computational model that we developed as part of our participation in the task. Training data comes in two forms: an image with embedded Tamil code-mixed text and an associated caption. We investigated the visual and textual features using CNN, VGG16, Inception, m-BERT, XLM-R, XLNet algorithms. Multimodal features are extracted by combining image (CNN, ResNet50, Inception) and text (Bi-LSTM) features via early fusion approach. Results indicate that the textual approach with XLNet achieved the highest weighted f{\_}1-score of 0.58, which enable our model to secure 3rd rank in this task.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hossain-etal-2021-nlp">
<titleInfo>
<title>NLP-CUET@DravidianLangTech-EACL2021: Investigating Visual and Textual Features to Identify Trolls from Multimodal Social Media Memes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Eftekhar</namePart>
<namePart type="family">Hossain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Omar</namePart>
<namePart type="family">Sharif</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammed</namePart>
<namePart type="given">Moshiul</namePart>
<namePart type="family">Hoque</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2021-04</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages</title>
</titleInfo>
<name type="personal">
<namePart type="given">Bharathi</namePart>
<namePart type="given">Raja</namePart>
<namePart type="family">Chakravarthi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruba</namePart>
<namePart type="family">Priyadharshini</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Anand</namePart>
<namePart type="family">Kumar M</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Parameswari</namePart>
<namePart type="family">Krishnamurthy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Elizabeth</namePart>
<namePart type="family">Sherly</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Kyiv</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>In the past few years, the meme has become a new way of communication on the Internet. As memes are in images forms with embedded text, it can quickly spread hate, offence and violence. Classifying memes are very challenging because of their multimodal nature and region-specific interpretation. A shared task is organized to develop models that can identify trolls from multimodal social media memes. This work presents a computational model that we developed as part of our participation in the task. Training data comes in two forms: an image with embedded Tamil code-mixed text and an associated caption. We investigated the visual and textual features using CNN, VGG16, Inception, m-BERT, XLM-R, XLNet algorithms. Multimodal features are extracted by combining image (CNN, ResNet50, Inception) and text (Bi-LSTM) features via early fusion approach. Results indicate that the textual approach with XLNet achieved the highest weighted f_1-score of 0.58, which enable our model to secure 3rd rank in this task.</abstract>
<identifier type="citekey">hossain-etal-2021-nlp</identifier>
<location>
<url>https://aclanthology.org/2021.dravidianlangtech-1.43</url>
</location>
<part>
<date>2021-04</date>
<extent unit="page">
<start>300</start>
<end>306</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T NLP-CUET@DravidianLangTech-EACL2021: Investigating Visual and Textual Features to Identify Trolls from Multimodal Social Media Memes
%A Hossain, Eftekhar
%A Sharif, Omar
%A Hoque, Mohammed Moshiul
%Y Chakravarthi, Bharathi Raja
%Y Priyadharshini, Ruba
%Y Kumar M, Anand
%Y Krishnamurthy, Parameswari
%Y Sherly, Elizabeth
%S Proceedings of the First Workshop on Speech and Language Technologies for Dravidian Languages
%D 2021
%8 April
%I Association for Computational Linguistics
%C Kyiv
%F hossain-etal-2021-nlp
%X In the past few years, the meme has become a new way of communication on the Internet. As memes are in images forms with embedded text, it can quickly spread hate, offence and violence. Classifying memes are very challenging because of their multimodal nature and region-specific interpretation. A shared task is organized to develop models that can identify trolls from multimodal social media memes. This work presents a computational model that we developed as part of our participation in the task. Training data comes in two forms: an image with embedded Tamil code-mixed text and an associated caption. We investigated the visual and textual features using CNN, VGG16, Inception, m-BERT, XLM-R, XLNet algorithms. Multimodal features are extracted by combining image (CNN, ResNet50, Inception) and text (Bi-LSTM) features via early fusion approach. Results indicate that the textual approach with XLNet achieved the highest weighted f_1-score of 0.58, which enable our model to secure 3rd rank in this task.
%U https://aclanthology.org/2021.dravidianlangtech-1.43
%P 300-306
Markdown (Informal)
[NLP-CUET@DravidianLangTech-EACL2021: Investigating Visual and Textual Features to Identify Trolls from Multimodal Social Media Memes](https://aclanthology.org/2021.dravidianlangtech-1.43) (Hossain et al., DravidianLangTech 2021)
ACL