Authors :
Islam D. S. Aabdalla; Dr. D. Vasumathi
Volume/Issue :
Volume 8 - 2023, Issue 11 - November
Google Scholar :
https://tinyurl.com/5n8chu28
Scribd :
https://tinyurl.com/3duwdtcv
DOI :
https://doi.org/10.5281/zenodo.10319990
Abstract :
Fake news exerts a pervasive and urgent
influence, causing mental harm to readers.
Differentiating between fake and genuine news is
increasingly tricky, impacting countless lives. This
proliferation of falsehoods spreads harm and
misinformation and erodes trust in global information
sources, affecting individuals, organizations, and nations.
It requires immediate attention. To address this issue, we
conducted a comprehensive study utilizing advanced
techniques such as TF-IDF and feature engineering to
detect fake news. WWe proposed Machine Learning
Techniques (MLT), including Naïve Bayes (NB),
Decision trees (DT), Support Vector Machines (SVM),
Random Forest (RF), and Logistic Regression (LR) to
classify news articles. Our studies involved analyzing
word patterns from diverse news sources to identify
unreliable news. We calculated the likelihood of an
article being fake or genuine based on the extracted
features and evaluated algorithm accuracy using a
carefully crafted training dataset. The analysis revealed
that the decision tree algorithm exhibited the highest
accuracy, detecting fake news with an impressive 99.68%
rate. While the remaining algorithms performed well,
none surpassed the accuracy of the decision tree. TThis
study highlights the immense potential of machine
learning techniques in combating the pervasive menace
of leaks. Our research presents a reliable and efficient
method to identify and classify unreliable information,
Safeguarding the integrity of news sources and
protecting individuals and societies from the harmful
effects of misinformation.
Keywords :
Machine Learning, TF-IDF, Feature Extraction, Fake News Detection, social media.
Fake news exerts a pervasive and urgent
influence, causing mental harm to readers.
Differentiating between fake and genuine news is
increasingly tricky, impacting countless lives. This
proliferation of falsehoods spreads harm and
misinformation and erodes trust in global information
sources, affecting individuals, organizations, and nations.
It requires immediate attention. To address this issue, we
conducted a comprehensive study utilizing advanced
techniques such as TF-IDF and feature engineering to
detect fake news. WWe proposed Machine Learning
Techniques (MLT), including Naïve Bayes (NB),
Decision trees (DT), Support Vector Machines (SVM),
Random Forest (RF), and Logistic Regression (LR) to
classify news articles. Our studies involved analyzing
word patterns from diverse news sources to identify
unreliable news. We calculated the likelihood of an
article being fake or genuine based on the extracted
features and evaluated algorithm accuracy using a
carefully crafted training dataset. The analysis revealed
that the decision tree algorithm exhibited the highest
accuracy, detecting fake news with an impressive 99.68%
rate. While the remaining algorithms performed well,
none surpassed the accuracy of the decision tree. TThis
study highlights the immense potential of machine
learning techniques in combating the pervasive menace
of leaks. Our research presents a reliable and efficient
method to identify and classify unreliable information,
Safeguarding the integrity of news sources and
protecting individuals and societies from the harmful
effects of misinformation.
Keywords :
Machine Learning, TF-IDF, Feature Extraction, Fake News Detection, social media.