Fake texts have become prevalent in current digital era. These are utilized by businesses and individuals to tarnish brand reputation of their competitors and enhance own revenues, and market shares. Due to rise and acceptance of social media, fake text detection is receiving impetus by academicians and practitioners. Fake news is made of text, images and/or URLs. We focus on identifying fake news using textual information. Many writers/bots are hired by organizations for writing fake text to invoke negative sentiments among population. The key objective is to evaluate effectiveness of fake text detection while progressing from statistical to deep learning models. In this work, we propose hybrid model using deep neural network based techniques for text classification. The text mining process was applied then multiple classification methods were implemented to categorize text as fake or real. Multiple experiments on three real-world datasets were executed to show viability of our approach.
Sarin, Gaurav and Kumar, Pradeep, "ConvGRUText: A Deep Learning Method for Fake Text Detection on Online Social Media" (2020). PACIS 2020 Proceedings. 60.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.