@inproceedings{hasan-etal-2022-cuet,
title = "{CUET}-{NLP}@{D}ravidian{L}ang{T}ech-{ACL}2022: Investigating Deep Learning Techniques to Detect Multimodal Troll Memes",
author = "Hasan, Md and
Jannat, Nusratul and
Hossain, Eftekhar and
Sharif, Omar and
Hoque, Mohammed Moshiul",
editor = "Chakravarthi, Bharathi Raja and
Priyadharshini, Ruba and
Madasamy, Anand Kumar and
Krishnamurthy, Parameswari and
Sherly, Elizabeth and
Mahesan, Sinnathamby",
booktitle = "Proceedings of the Second Workshop on Speech and Language Technologies for Dravidian Languages",
month = may,
year = "2022",
address = "Dublin, Ireland",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2022.dravidianlangtech-1.27/",
doi = "10.18653/v1/2022.dravidianlangtech-1.27",
pages = "170--176",
abstract = "With the substantial rise of internet usage, social media has become a powerful communication medium to convey information, opinions, and feelings on various issues. Recently, memes have become a popular way of sharing information on social media. Usually, memes are visuals with text incorporated into them and quickly disseminate hatred and offensive content. Detecting or classifying memes is challenging due to their region-specific interpretation and multimodal nature. This work presents a meme classification technique in Tamil developed by the CUET NLP team under the shared task (DravidianLangTech-ACL2022). Several computational models have been investigated to perform the classification task. This work also explored visual and textual features using VGG16, ResNet50, VGG19, CNN and CNN+LSTM models. Multimodal features are extracted by combining image (VGG16) and text (CNN, LSTM+CNN) characteristics. Results demonstrate that the textual strategy with CNN+LSTM achieved the highest weighted $f_1$-score (0.52) and recall (0.57). Moreover, the CNN-Text+VGG16 outperformed the other models concerning the multimodal memes detection by achieving the highest $f_1$-score of 0.49, but the LSTM+CNN model allowed the team to achieve $4^{th}$ place in the shared task."
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="hasan-etal-2022-cuet">
<titleInfo>
<title>CUET-NLP@DravidianLangTech-ACL2022: Investigating Deep Learning Techniques to Detect Multimodal Troll Memes</title>
</titleInfo>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="family">Hasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nusratul</namePart>
<namePart type="family">Jannat</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<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>2022-05</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the Second 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="given">Kumar</namePart>
<namePart type="family">Madasamy</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>
<name type="personal">
<namePart type="given">Sinnathamby</namePart>
<namePart type="family">Mahesan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Dublin, Ireland</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>With the substantial rise of internet usage, social media has become a powerful communication medium to convey information, opinions, and feelings on various issues. Recently, memes have become a popular way of sharing information on social media. Usually, memes are visuals with text incorporated into them and quickly disseminate hatred and offensive content. Detecting or classifying memes is challenging due to their region-specific interpretation and multimodal nature. This work presents a meme classification technique in Tamil developed by the CUET NLP team under the shared task (DravidianLangTech-ACL2022). Several computational models have been investigated to perform the classification task. This work also explored visual and textual features using VGG16, ResNet50, VGG19, CNN and CNN+LSTM models. Multimodal features are extracted by combining image (VGG16) and text (CNN, LSTM+CNN) characteristics. Results demonstrate that the textual strategy with CNN+LSTM achieved the highest weighted f₁-score (0.52) and recall (0.57). Moreover, the CNN-Text+VGG16 outperformed the other models concerning the multimodal memes detection by achieving the highest f₁-score of 0.49, but the LSTM+CNN model allowed the team to achieve 4^th place in the shared task.</abstract>
<identifier type="citekey">hasan-etal-2022-cuet</identifier>
<identifier type="doi">10.18653/v1/2022.dravidianlangtech-1.27</identifier>
<location>
<url>https://aclanthology.org/2022.dravidianlangtech-1.27/</url>
</location>
<part>
<date>2022-05</date>
<extent unit="page">
<start>170</start>
<end>176</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CUET-NLP@DravidianLangTech-ACL2022: Investigating Deep Learning Techniques to Detect Multimodal Troll Memes
%A Hasan, Md
%A Jannat, Nusratul
%A Hossain, Eftekhar
%A Sharif, Omar
%A Hoque, Mohammed Moshiul
%Y Chakravarthi, Bharathi Raja
%Y Priyadharshini, Ruba
%Y Madasamy, Anand Kumar
%Y Krishnamurthy, Parameswari
%Y Sherly, Elizabeth
%Y Mahesan, Sinnathamby
%S Proceedings of the Second Workshop on Speech and Language Technologies for Dravidian Languages
%D 2022
%8 May
%I Association for Computational Linguistics
%C Dublin, Ireland
%F hasan-etal-2022-cuet
%X With the substantial rise of internet usage, social media has become a powerful communication medium to convey information, opinions, and feelings on various issues. Recently, memes have become a popular way of sharing information on social media. Usually, memes are visuals with text incorporated into them and quickly disseminate hatred and offensive content. Detecting or classifying memes is challenging due to their region-specific interpretation and multimodal nature. This work presents a meme classification technique in Tamil developed by the CUET NLP team under the shared task (DravidianLangTech-ACL2022). Several computational models have been investigated to perform the classification task. This work also explored visual and textual features using VGG16, ResNet50, VGG19, CNN and CNN+LSTM models. Multimodal features are extracted by combining image (VGG16) and text (CNN, LSTM+CNN) characteristics. Results demonstrate that the textual strategy with CNN+LSTM achieved the highest weighted f₁-score (0.52) and recall (0.57). Moreover, the CNN-Text+VGG16 outperformed the other models concerning the multimodal memes detection by achieving the highest f₁-score of 0.49, but the LSTM+CNN model allowed the team to achieve 4^th place in the shared task.
%R 10.18653/v1/2022.dravidianlangtech-1.27
%U https://aclanthology.org/2022.dravidianlangtech-1.27/
%U https://doi.org/10.18653/v1/2022.dravidianlangtech-1.27
%P 170-176
Markdown (Informal)
[CUET-NLP@DravidianLangTech-ACL2022: Investigating Deep Learning Techniques to Detect Multimodal Troll Memes](https://aclanthology.org/2022.dravidianlangtech-1.27/) (Hasan et al., DravidianLangTech 2022)
ACL