Microblogs Deception Detection using BERT and Multiscale CNNs
- Publisher:
- IEEE
- Publication Type:
- Conference Proceeding
- Citation:
- 2021 2nd Global Conference for Advancement in Technology (GCAT), 2021, 00, pp. 1-6
- Issue Date:
- 2021-11-13
Closed Access
Filename | Description | Size | |||
---|---|---|---|---|---|
Microblogs_Deception_Detection_using_BERT_and_Multiscale_CNNs.pdf | Published version | 784.02 kB |
Copyright Clearance Process
- Recently Added
- In Progress
- Closed Access
This item is closed access and not available.
Online news consumption has rapidly increased, and so has the proliferation of false information. People worldwide have mainly become dependent on social media networks to intake news about the happenings around them. Also, the data is profoundly contaminated with wrong information that harms society in uncountable ways. It is of huge importance to be able to identify a false message. The research society is contributing to solving the problem by developing machine learning and deep learning algorithms. With misinformation spreading ubiquitously, various data modalities have emerged that become carriers of such false news. Research trend is advancing towards multi-modal fake news detection to authenticate text, images, and videos on the web. Existing studies have elaborated on the successful use of RNNs and CNNs. Being a new NLP technique, BERT has been used by a limited number of studies, while multiscale CNNs have not been explored yet to apply fake news detection. This research proposes a novel framework using BERT and multiscale CNNs to perform multi-modal fake news classification and achieve results higher than the existing state-of-the-art techniques.
Please use this identifier to cite or link to this item: