An agent-based modeling analysis of helpful vote on online product reviews

Helpful vote is a common feature on many websites that utilizes the 'wisdom of the crowd' to vote on whether a piece of information posted on the website (e.g., A product review) is helpful. Recent studies show that under certain conditions, aggregated judgment may lead to inaccurate information. Motivated by these studies, we argue that the aggregated helpful votes may not reflect the underlying quality of a review because of (1) people's selective attention (i.e., Consumers often select reviews to vote based on existing helpful vote) and (2) social influence (i.e., The existing helpful vote affects future helpful vote). We develop computational models to simulate reviews, consumers, and their helpful votes. The model results well represent real-world helpful vote collected longitudinally from Amazon.com. The results also show that the aggregated helpful vote may not reflect the true quality of the reviews.