In today's digital age, consumers increasingly rely on online reviews to make informed decisions about products. However, this reliance on reviews has led to an increase in opinion spam - fake reviews written to sound authentic. While previous research has focused on identifying manual instances of opinion spam, the researchers of this study took a different approach. They studied deceptive opinion spam, which refers to reviews that are not only fake but also intentionally crafted to deceive readers.
To detect deceptive opinion spam, the researchers used a combination of psychology and computational linguistics. They developed and tested three different approaches and ultimately created a classifier that is 90% accurate in identifying deceptive reviews. The researchers also made a theoretical contribution by revealing a relationship between deceptive opinions and imaginative writing.
Read the research: Finding Deceptive Opinion Spam by Any Stretch of the Imagination
