Deep Ensemble Approach for COVID-19 Fake News Detection from Social Media
8th International Conference on Signal Processing and Integrated Networks, SPIN 2021
; : 396-401, 2021.
Article
in English
| Scopus | ID: covidwho-1752437
ABSTRACT
Social media networks such as Facebook and Twitter are overwhelmed with COVID-19-related posts during the outbreak. People have also posted several fake news among the massive COVID-19-related social media posts. Fake news has the potential to create public fear, weaken government credibility, and pose a serious threat to social order. This paper provides a deep ensemble-based method for detecting COVID-19 fake news. An ensemble classifier is made up of three different classifiers Support Vector Machine, Dense Neural Network, and Convolutional Neural Network. The extensive experiments with the proposed ensemble model and eight different conventional machine learning classifiers are carried out using the character and word n-gram TF-IDF features. The results of the experiments show that character n-gram features outperform word n-gram features. The proposed deep ensemble classifier performed better, with a weighted Fl -score of 0.97 in contrast to numerous conventional machine learning classifiers and deep learning classifiers. © 2021 IEEE
Deep Learning; Ensemble classifier; Fake news; Machine Learning; Twitter; Convolutional neural networks; Fake detection; Support vector machines; Conventional machines; Ensemble approaches; Ensemble-classifier; Facebook; Machine-learning; Social media; Social media networks; Word n-grams; Social networking (online)
Full text:
Available
Collection:
Databases of international organizations
Database:
Scopus
Language:
English
Journal:
8th International Conference on Signal Processing and Integrated Networks, SPIN 2021
Year:
2021
Document Type:
Article
Similar
MEDLINE
...
LILACS
LIS