To provide personalized online shopping suggestions, recommendation systems play an increasingly important role in “closing a transaction”. Some leading online movie sales platforms, such as Netflix and Rotten Tomatoes, have exploited content-based recommendation approaches. However, the issue of insufficient information about features in item profiles may lead to less accurate recommendations. In this paper, we propose a recommendation method known as Collective Intelligence Social Tagging (CIST), which combines a content-based recommendation approach with a social tagging function based on crowd-sourcing. We used an online movie sales platform as a use-case of how a CIST approach could increase the accuracy of recommended results and the overall user experience. In order t0 understand the feasibility and satisfaction level for CIST, we conducted fifteen design interviews to first determine user-developer perspectives on CIST, and then collected their overall design input.
Wang, Yixiao and Sharma, Ravi S., "Design of Front-End for Recommendation Systems: Towards a Hybrid Architecture" (2018). ICEB 2018 Proceedings. 80.