English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The sudden widespread menace created by the present global pandemic COVID-19has had an unprecedented effect on our lives. Man-kind is going throughhumongous fear and dependence on social media like never before. Fearinevitably leads to panic, speculations, and the spread of misinformation. Manygovernments have taken measures to curb the spread of such misinformation forpublic well being. Besides global measures, to have effective outreach, systemsfor demographically local languages have an important role to play in thiseffort. Towards this, we propose an approach to detect fake news about COVID-19early on from social media, such as tweets, for multiple Indic-Languagesbesides English. In addition, we also create an annotated dataset of Hindi andBengali tweet for fake news detection. We propose a BERT based model augmentedwith additional relevant features extracted from Twitter to identify faketweets. To expand our approach to multiple Indic languages, we resort to mBERTbased model which is fine-tuned over created dataset in Hindi and Bengali. Wealso propose a zero-shot learning approach to alleviate the data scarcity issuefor such low resource languages. Through rigorous experiments, we show that ourapproach reaches around 89% F-Score in fake tweet detection which supercedesthe state-of-the-art (SOTA) results. Moreover, we establish the first benchmarkfor two Indic-Languages, Hindi and Bengali. Using our annotated data, our modelachieves about 79% F-Score in Hindi and 81% F-Score for Bengali Tweets. Ourzero-shot model achieves about 81% F-Score in Hindi and 78% F-Score for BengaliTweets without any annotated data, which clearly indicates the efficacy of ourapproach.

No Rumours Please! A Multi-Indic-Lingual Approach for COVID Fake-Tweet Detection