@inproceedings{joy-etal-2023-banglaclickbert,
title = "{B}angla{C}lick{BERT}: {B}angla Clickbait Detection from News Headlines using Domain Adaptive {B}angla{BERT} and {MLP} Techniques",
author = "Joy, Saman Sarker and
Aishi, Tanusree Das and
Nodi, Naima Tahsin and
Rasel, Annajiat Alim",
editor = "Muresan, Smaranda and
Chen, Vivian and
Casey, Kennington and
David, Vandyke and
Nina, Dethlefs and
Koji, Inoue and
Erik, Ekstedt and
Stefan, Ultes",
booktitle = "Proceedings of the 21st Annual Workshop of the Australasian Language Technology Association",
month = nov,
year = "2023",
address = "Melbourne, Australia",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2023.alta-1.1",
pages = "1--10",
abstract = "News headlines or titles that deliberately persuade readers to view a particular online content are referred to as clickbait. There have been numerous studies focused on clickbait detection in English language, compared to that, there have been very few researches carried out that address clickbait detection in Bangla news headlines. In this study, we have experimented with several distinctive transformers models, namely BanglaBERT and XLM-RoBERTa. Additionally, we introduced a domain-adaptive pretrained model, BanglaClickBERT. We conducted a series of experiments to identify the most effective model. The dataset we used for this study contained 15,056 labeled and 65,406 unlabeled news headlines; in addition to that, we have collected more unlabeled Bangla news headlines by scraping clickbait-dense websites making a total of 1 million unlabeled news headlines in order to make our BanglaClickBERT. Our approach has successfully surpassed the performance of existing state-of-the-art technologies providing a more accurate and efficient solution for detecting clickbait in Bangla news headlines, with potential implications for improving online content quality and user experience.",
}
<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="joy-etal-2023-banglaclickbert">
<titleInfo>
<title>BanglaClickBERT: Bangla Clickbait Detection from News Headlines using Domain Adaptive BanglaBERT and MLP Techniques</title>
</titleInfo>
<name type="personal">
<namePart type="given">Saman</namePart>
<namePart type="given">Sarker</namePart>
<namePart type="family">Joy</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tanusree</namePart>
<namePart type="given">Das</namePart>
<namePart type="family">Aishi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Naima</namePart>
<namePart type="given">Tahsin</namePart>
<namePart type="family">Nodi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Annajiat</namePart>
<namePart type="given">Alim</namePart>
<namePart type="family">Rasel</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2023-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 21st Annual Workshop of the Australasian Language Technology Association</title>
</titleInfo>
<name type="personal">
<namePart type="given">Smaranda</namePart>
<namePart type="family">Muresan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vivian</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Kennington</namePart>
<namePart type="family">Casey</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Vandyke</namePart>
<namePart type="family">David</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Dethlefs</namePart>
<namePart type="family">Nina</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Inoue</namePart>
<namePart type="family">Koji</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ekstedt</namePart>
<namePart type="family">Erik</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ultes</namePart>
<namePart type="family">Stefan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Melbourne, Australia</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
</relatedItem>
<abstract>News headlines or titles that deliberately persuade readers to view a particular online content are referred to as clickbait. There have been numerous studies focused on clickbait detection in English language, compared to that, there have been very few researches carried out that address clickbait detection in Bangla news headlines. In this study, we have experimented with several distinctive transformers models, namely BanglaBERT and XLM-RoBERTa. Additionally, we introduced a domain-adaptive pretrained model, BanglaClickBERT. We conducted a series of experiments to identify the most effective model. The dataset we used for this study contained 15,056 labeled and 65,406 unlabeled news headlines; in addition to that, we have collected more unlabeled Bangla news headlines by scraping clickbait-dense websites making a total of 1 million unlabeled news headlines in order to make our BanglaClickBERT. Our approach has successfully surpassed the performance of existing state-of-the-art technologies providing a more accurate and efficient solution for detecting clickbait in Bangla news headlines, with potential implications for improving online content quality and user experience.</abstract>
<identifier type="citekey">joy-etal-2023-banglaclickbert</identifier>
<location>
<url>https://aclanthology.org/2023.alta-1.1</url>
</location>
<part>
<date>2023-11</date>
<extent unit="page">
<start>1</start>
<end>10</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T BanglaClickBERT: Bangla Clickbait Detection from News Headlines using Domain Adaptive BanglaBERT and MLP Techniques
%A Joy, Saman Sarker
%A Aishi, Tanusree Das
%A Nodi, Naima Tahsin
%A Rasel, Annajiat Alim
%Y Muresan, Smaranda
%Y Chen, Vivian
%Y Casey, Kennington
%Y David, Vandyke
%Y Nina, Dethlefs
%Y Koji, Inoue
%Y Erik, Ekstedt
%Y Stefan, Ultes
%S Proceedings of the 21st Annual Workshop of the Australasian Language Technology Association
%D 2023
%8 November
%I Association for Computational Linguistics
%C Melbourne, Australia
%F joy-etal-2023-banglaclickbert
%X News headlines or titles that deliberately persuade readers to view a particular online content are referred to as clickbait. There have been numerous studies focused on clickbait detection in English language, compared to that, there have been very few researches carried out that address clickbait detection in Bangla news headlines. In this study, we have experimented with several distinctive transformers models, namely BanglaBERT and XLM-RoBERTa. Additionally, we introduced a domain-adaptive pretrained model, BanglaClickBERT. We conducted a series of experiments to identify the most effective model. The dataset we used for this study contained 15,056 labeled and 65,406 unlabeled news headlines; in addition to that, we have collected more unlabeled Bangla news headlines by scraping clickbait-dense websites making a total of 1 million unlabeled news headlines in order to make our BanglaClickBERT. Our approach has successfully surpassed the performance of existing state-of-the-art technologies providing a more accurate and efficient solution for detecting clickbait in Bangla news headlines, with potential implications for improving online content quality and user experience.
%U https://aclanthology.org/2023.alta-1.1
%P 1-10
Markdown (Informal)
[BanglaClickBERT: Bangla Clickbait Detection from News Headlines using Domain Adaptive BanglaBERT and MLP Techniques](https://aclanthology.org/2023.alta-1.1) (Joy et al., ALTA 2023)
ACL