Implementation of Personality Detection and Accuracy Prediction for identification of fake and true news using Decision Tree and Random Forest Algorithms

Abstract

This project aims to innovatively classify and evaluate constructive proactive personality data in order to predict fake and true news on social media. There are 25000 entities and five attributes in the proactive personality knowledge dataset that was used for training and testing. By using the Decision Tree (DT) and Random forest (RF) algorithms, a methodology for predicting fake news and true news in the proactive personality was developed. The investigation of classification model comprises DT sieves fake and true news with an accuracy of 96% and the RF classifier predicted the fake news at an accuracy of 93%. The significance value is (P<0.05). The experimental results demonstrated the capability of DT and RF classifier models based on their prediction of relevant information of input data. It is found that the DT model performs better compared to the RF model in terms of accuracy and precision.