Fake News Detection System using Web-Extension

Investigating the Performance of the GPT-3.5 Model in Fake News Detection: An Experimental Analysis

“…Scope Use GPT GPT Version Different approaches have been proposed to detect fake news and improve news credibility. Some studies employed deep learning techniques, such as Long Short-Term Memory (LSTM) and GPT-2 models [Khivasara et al 2020], whereas others explored the Transformer architecture to leverage news information and social contexts [Raza and Ding 2022]. With respect to [Khivasara et al 2020], the GPT-2 model was utilized to determine whether the content of purported fake news originated from an Artificial Intelligence (AI) generator, rather than employing it to verify the authenticity of the news itself.…”

“…Some studies employed deep learning techniques, such as Long Short-Term Memory (LSTM) and GPT-2 models [Khivasara et al 2020], whereas others explored the Transformer architecture to leverage news information and social contexts [Raza and Ding 2022]. With respect to [Khivasara et al 2020], the GPT-2 model was utilized to determine whether the content of purported fake news originated from an Artificial Intelligence (AI) generator, rather than employing it to verify the authenticity of the news itself. Also, some studies utilized machine learning techniques, such as Term Frequency -Inverse Document Frequency (TF-IDF) and Support Vector Machine (SVM), to extract relevant features and classify texts as fake or genuine [Baarir and Djeffal 2021].…”

“…In this context, ChatGPT -a language model trained by OpenAI that became popular recently -is capable of providing responses and information in text, addressing various areas of knowledge based on its training. Therefore, it has the potential to be used in the analysis of false texts [Khivasara et al 2020].…”