DETECTION OF DECEPTIVE OPINION SPAM USING MACHINE LEARNING APPROACH

Deceptive reviews detection has attracted significant attention from both business and research communities. The problem remains to be highly challenging due to the difficulty of human labeling needed for supervised learning. Deceptive reviews are those deliberately mislead readers by giving undeserving positive reviews to some target objects in order to promote the objects, or by giving unjust negative reviews to some target objects in order to damage their reputation. Detecting opinion spam is a very challenging problem since opinions expressed in the Web are typically short texts, written by unknown people using different styles and for different purposes. Opinion spam has many forms, e.g., fake reviews, fake comments, fake blogs, fake social net-work postings and deceptive texts.