首页|Research from American University of the Middle East in Machine Learning Provide s New Insights (Enhancing Fake News Detection with Word Embedding: A Machine Lea rning and Deep Learning Approach)
Research from American University of the Middle East in Machine Learning Provide s New Insights (Enhancing Fake News Detection with Word Embedding: A Machine Lea rning and Deep Learning Approach)
扫码查看
点击上方二维码区域,可以放大扫码查看
原文链接
NETL
NSTL
Investigators publish new report on ar tificial intelligence. According to news reporting from Egaila, Kuwait, by NewsR x journalists, research stated, "The widespread dissemination of fake news on so cial media has necessitated the development of more sophisticated detection meth ods to maintain information integrity." The news correspondents obtained a quote from the research from American Univers ity of the Middle East: "This research systematically investigates the effective ness of different word embedding techniques- TF-IDF, Word2Vec, and FastText-when applied to a variety of machine learning (ML) and deep learning (DL) models for fake news detection. Leveraging the TruthSeeker dataset, which includes a divers e set of labeled news articles and social media posts spanning over a decade, we evaluated the performance of classifiers such as Support Vector Machines (SVMs) , Multilayer Perceptrons (MLPs), and Convolutional Neural Networks (CNNs). Our a nalysis demonstrates that SVMs using TF-IDF embeddings and CNNs employing TF-IDF embeddings achieve the highest overall performance in terms of accuracy, precis ion, recall, and F1 score. These results suggest that TF-IDF, with its capacity to highlight discriminative features in text, enhances the performance of models like SVMs, which are adept at handling sparse data representations. Additionall y, CNNs benefit from TF-IDF by effectively capturing localized features and patt erns within the textual data. In contrast, while Word2Vec and FastText embedding s capture semantic and syntactic nuances, they introduce complexities that may n ot always benefit traditional ML models like MLPs or SVMs, which could explain t heir relatively lower performance in some cases."
American University of the Middle EastEgailaKuwaitCyborgsEmerging TechnologiesMachine Learning