Graduate Seminar Series

The objective of this research is to examine the efficacy of deep learning models in identifying deceit in written comments pertaining to controversial topics. The performance of different machine learning models was subsequently compared. The performance of conventional methods, namely Support Vector Machines (SVM) and Naive Bayes, was surpassed by more advanced approaches including Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU), and Convolutional Neural Network (CNN).