CrowdStart: Warming up cold-start items using crowdsourcing
作者：
Highlights：
• A new framework is proposed to adopt crowdsourcing to the cold-start item problem.
• Sophisticated user interfaces for crowdsourcing is designed.
• Human-machine collaboration is used to address the cold-start item problem.
• Real-world evaluation is conducted with about 400 workers on Amazon Mechanical Turk.
• The proposed framework is effective at improving the cold-start item recommendations.
摘要
•A new framework is proposed to adopt crowdsourcing to the cold-start item problem.•Sophisticated user interfaces for crowdsourcing is designed.•Human-machine collaboration is used to address the cold-start item problem.•Real-world evaluation is conducted with about 400 workers on Amazon Mechanical Turk.•The proposed framework is effective at improving the cold-start item recommendations.
论文关键词：Collaborative filtering,New item recommendation,Crowdsourcing
论文评审过程：Received 18 July 2018, Revised 6 June 2019, Accepted 12 July 2019, Available online 15 July 2019, Version of Record 22 July 2019.
论文官网地址：https://doi.org/10.1016/j.eswa.2019.07.030
