Sharing Economy, Platforms and Crowds
Loading...
Paper Type
Complete
Paper Number
2635
Description
The fake review problem, an enduring challenge faced by E-commerce platforms, has worsened in recent years. In this paper, we investigate the platform’s economic incentive to filter fake reviews. Using a game theoretical model, we analyze the sellers’ manipulation behavior and the platform’s optimal fake review control strategy. Our results show that a more accurate algorithm can lead to a lower platform’s payoff, and in the equilibrium, the platform would not increase the accuracy to the maximum value even it is costless to do so. Another interesting finding is that the high-quality seller can set higher manipulation level when competition is intense. Moreover, we find that the optimal algorithm accuracy increases when platform is more reputable and competition decrease. In addition, we find less intense competition can hurt the platform when its fake review control strategy is endogenized. Our findings send an important message to consumers and policy makers that they should not fully rely on the platform to tackle fake reviews.
Recommended Citation
Wang, Zhe; Kumar, Subodha; and Liu, Dengpan, "On Platform’s Incentive to Filter Fake Reviews: A Game-Theoretic Model" (2020). ICIS 2020 Proceedings. 20.
https://aisel.aisnet.org/icis2020/sharing_economy/sharing_economy/20
On Platform’s Incentive to Filter Fake Reviews: A Game-Theoretic Model
The fake review problem, an enduring challenge faced by E-commerce platforms, has worsened in recent years. In this paper, we investigate the platform’s economic incentive to filter fake reviews. Using a game theoretical model, we analyze the sellers’ manipulation behavior and the platform’s optimal fake review control strategy. Our results show that a more accurate algorithm can lead to a lower platform’s payoff, and in the equilibrium, the platform would not increase the accuracy to the maximum value even it is costless to do so. Another interesting finding is that the high-quality seller can set higher manipulation level when competition is intense. Moreover, we find that the optimal algorithm accuracy increases when platform is more reputable and competition decrease. In addition, we find less intense competition can hurt the platform when its fake review control strategy is endogenized. Our findings send an important message to consumers and policy makers that they should not fully rely on the platform to tackle fake reviews.
When commenting on articles, please be friendly, welcoming, respectful and abide by the AIS eLibrary Discussion Thread Code of Conduct posted here.