Detecting User Credibility on Twitter using a Hybrid Machine Learning Model of Features’ Selection and Weighting

With the pervasive and rapidly growing presence of the internet and social media, creating untrustworthy accounts has become effortless, allowing fake news to be spread for personal or private interests. As a result, it is crucial in this era to investigate the credibility of users on social networking platforms such as Twitter. In this research, we aim to integrate existing solutions from previous research to create a hybrid model. Our approach is based on selecting and weighting features using supervised machine learning methods such as ExtraTressClarifier, correlation-based algorithm methods, and SelectKBest to extract new ranked and 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. The research objective is to combine feature selection and weighting methods with Supervised Machine Learning to evaluate their impact on the accuracy of user credibility detection on Twitter. In addition, we measure the effectiveness of different feature categories on this detection. Experiments are conducted on one of the online available datasets. We seek to employ extracted features from a user's profile and statistical and emotional information. Then, the experimental results are compared to discover the effectiveness of the proposed solution. This study focuses on revealing the credibility of Twitter (or X-platform as recently renamed) accounts, which may result in the need for some adjustments to the generalization of Twitter’s outputs to other social media accounts such as LinkedIn, Facebook, and others.

@article{Abid-Althaqafi2024,
  title     = {Detecting User Credibility on Twitter using a Hybrid Machine Learning Model of Features’ Selection and Weighting},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {15},
  number    = {5},
  year      = {2024},
  publisher = {The Science and Information Organization},
  author    = {Nahid R. Abid-Althaqafi and Hessah A. Alsalamah},
  doi       = {10.14569/IJACSA.2024.0150513},
  url       = {https://doi.org/10.14569/IJACSA.2024.0150513}
}