Open AccessMachine Learning Based Detection of Deceptive Tweets on Covid-19
Author(s) -
Amisha Sinha,
Mohnish Raval,
S. Sindhu
Publication year - 2021
Publication title -
international journal of engineering and advanced technology
Language(s) - English
Resource type - Journals
ISSN - 2249-8958
DOI - 10.35940/ijeat.e2831.0610521
Subject(s) - computer science , lexical analysis , preprocessor , support vector machine , artificial intelligence , social media , machine learning , random forest , stop words , process (computing) , set (abstract data type) , population , natural language processing , world wide web , demography , sociology , programming language , operating system
Social media plays a vital role in connecting peoplearound world and developing relationships. Social Media has ahuge potential audience and the circulation of any information doesimpact a huge population. With the surge of Covid-19, we can see alot offake news and tweets circulating about remedies, medicine,and general information related to pandemics. In this paper, we setout machine learning-based detection of deceptive informationaround Covid-19. With this paper, we have described our projectwhich could detect whether a tweet is fake or real automatically.The labeled dataset is used in the process which is extracted fromthe arXiv repository. Dataset has tweets, upon which variousmethods are applied for cleaning, training, and testing. Preprocessing, Classification, tokenization, and stemming/removal ofstop words are performed to extract the most relevant informationfrom the dataset and to achieve better accuracy in comparison withthe existing system. For classification, we have used twoclassification techniques- Tf-Idf and Bags of words. To achievebetter accuracy, we have used two other methodology-SVM andRandom Forest and have achieved an F1-score of 0.94 using SVM.