Emergent semantics from game-induced folksonomies
KDD '12: The 18th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining Beijing China August, 2012(2012)
摘要
We describe the GiveALink Slider, an experimental social tagging game designed with the purpose of generating meaningful and useful annotations to improve upon the drawbacks of existing folksonomies. Knowledge, in the form of reliable annotations, is validated and accumulated through the implicit interactions among multiple players. In this paper we explore the hypothesis that such a game can improve both the quality and quantity of social annotation data. Our evaluation of game-induced annotations shows that games may improve on the semantic structure of existing folksonomies from several perspectives, including searchability, novelty, and coherence. Games can therefore play a valuable role in the collection of helpful annotations, by leveraging human power and specific game design features.
更多查看译文
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络