Teaching citizen scientists to categorize glitches using machine learning guided training
作者：
Highlights：
• Peer production communities must provide training to teach individuals how to become high-performing contributors.
• Scaffolded training is advantageous; however, selection of training materials and continuous assessment is a challenge.
• A scaffolded machine learning guided training (MLGT) program that teaches volunteers to classify glitches is evaluated.
• The MLGT was evaluated in an online field experiment, and results show the MLGT increases performance and retention.
摘要
•Peer production communities must provide training to teach individuals how to become high-performing contributors.•Scaffolded training is advantageous; however, selection of training materials and continuous assessment is a challenge.•A scaffolded machine learning guided training (MLGT) program that teaches volunteers to classify glitches is evaluated.•The MLGT was evaluated in an online field experiment, and results show the MLGT increases performance and retention.
论文关键词：Citizen science,Experiment,Training,Online communities,Zooniverse,User studies,Scaffolding,Learning
论文评审过程：Received 18 February 2019, Revised 26 October 2019, Accepted 15 November 2019, Available online 18 November 2019, Version of Record 26 November 2019.
论文官网地址：https://doi.org/10.1016/j.chb.2019.106198
