作者: John Riedl , Shilad Wieland Sen
DOI:
关键词: Flexibility (engineering) 、 Computer science 、 Encyclopedia 、 Upload 、 World Wide Web 、 Data science 、 Automation 、 Quality (business) 、 MovieLens 、 Recommender system 、 User interface
摘要: Member contributions power many online communities. Users have uploaded billions of images to flickr, bookmarked millions pages on del.icio.us, and authored encyclopedia articles at Wikipedia. Tags—member contributed words or phrases that describe items—have emerged as a powerful method for searching, organizing, making sense of, these vast corpora. In this thesis we explore the dynamics, challenges, possibilities tagging systems. We study way in which factors influencing an individual user's choice tags can affect evolution community whole. Like other community-maintained systems, systems suffer from low quality contributions. interfaces algorithms differentiate between high tags. Finally, tagommenders, tag-based recommendation combine flexibility with automation recommender systems. We base our explorations activity MovieLens movie system. analyze behavior, user studies, surveys, 97,000 3,600 users. Our results provide insight into dynamics existing communities, suggest mechanisms address challenges extensions to,