| Summary, etc |
In today's digital era the growing quantity of misinformation has emerged as a prominent issue, given its potential to undermine the spread of precise information and erode the trustworthiness of news outlets. This research aims to construct a model utilizing machine learning methods for the identification of inauthentic news articles.To achieve the aims and objectives identified for this study a comprehensive data collection on political news was collected from an online repository Kaggle and preprocessed. The effectiveness of various machine learning algorithms, such as K Nearest Neighbour Algorithm, Decision Tree, SVC <br/>Classifier, Xgboost, Naïve Bayes Algorithm, Random Forest Algorithm, Logistic Regression and Passive Aggressive Algorithm. in detecting false news was evaluated. The most precise and effective algorithm SVC Classifier was selected as the basis for the final <br/>model through performance evaluation. The model was simulated using Google Colaboratory in Python Programming Language. Using metrics such as accuracy, precision, recall, and F1-score, the model's performance was evaluated to ensure its <br/>reliability and efficacy in distinguishing between Fake news and True news.This study seeks to contribute to the field of detecting fake news by developing a robust machine learning-based model specifically tailored for political news. This research's findings can <br/>be used to improve media literacy, prevent the spread of false information, and cultivate a more informed society.Keywords: Digital era, Fake news detection, machine learning algorithms, political news, media literacy |
