In the era of digital information, online platforms play a crucial role in shaping public opinion. However, the extensive spread of misinformation and fake news poses a significant challenge, largely fueled by non-credible users. Detecting user credibility is vital for ensuring the reliability of information on these platforms. This study employs supervised machine learning algorithms, leveraging key user features to enhance credibility detection. Feature selection methods, specifically SelectKBest and correlation-based algorithms, are explored for their impact on X-Platform user credibility detection. Utilizing various classifiers, including support vector machine, logistic regression, and XGBoost, experiments are conducted on the ArPFN dataset, which is a labeled, balanced, publicly available dataset. The evaluation includes measures like accuracy, precision, recall, and F1-score to assess efficiency. This research considers feature categories and selection methods with SML to detect their impact on the accuracy of X-Platform user credibility detection, making this research a reference for researchers and practitioners working in the field of SML, feature engineering, and social media analysis. We aim to advance the field’s understanding of effective strategies for mitigating the spread of fake news. The novelty of this study lies in the comprehensive exploration of feature selection methods and their influence on credibility detection, contributing valuable insights for future research in this domain.

Social media represent a vital actor in our lives, often serving as a primary source of information, surpassing traditional sources. Among these platforms, the X-Platform, which used to be called Twitter, has emerged as a leading space for the exchange of opinions and emotions. In this study, we introduced a supervised machine learning system designed to detect user credibility in this influential platform. User credibility detection depends largely on the features of the users on the platform. Feature weighting plays a pivotal role in identifying the significance of each feature in a dataset. It can indicate irrelevant features, which can lead to better performance in classification problems. This study aims to highlight the impact of weighted features on the accuracy of X-Platform User Credibility Detection (XUCD) using supervised machine learning methods, such as Principal Component Analysis (PCA) and correlation-coefficient algorithms, and tree-based methods, such as (ExtraTressClarifier) to extract new weighted features in the dataset and then use them to train our model to discover their impact on the accuracy of user credibility detection issues. As a result, we measured the effectiveness of different feature-weighting methods on different dataset categories to determine which obtained the best detection accuracy. Experiments were conducted on real user profiles, and statistical and emotional information was extracted from a publicly available dataset called (ArPFN). The improvement in XUCD accuracy using different weighting methods was dependent on the method and dataset category used.