A NOVEL LEARNING VECTOR QUANTIZATION WITH HAMMING DISTANCE MEASURE FOR EFFECTIVE PREDICTION OF FAKE NEWS

Abstract

The main aim of the study is to improve the prediction rate in fake news detection. A novel Learning Vector Quantization (LVQ) with hamming distance is proposed for effective prediction of fake news. The sample size is calculated as N=10 for multi group analysis using the G-Power calculator. ISOT dataset is used for the study and the proposed learning vector quantization algorithm is executed and compared with three existing algorithms: Passive Aggressive classifier, LSTM and LS-SVM algorithm.