Topic hierarchy construction from heterogeneous evidence

Existing studies on hierarchy constructionmainly focus on text corpora and indiscriminately mix numerous topics, thus increasing the possibility of knowledge acquisition bottlenecks and misconceptions. To address these problems and provide a comprehensive and in-depth representation of domain specific topics, we propose a novel topic hierarchy construction method with real-time update. This method combines heterogeneous evidence from multiple sources including folksonomy and encyclopedia, separately in both initial topic hierarchy construction and topic hierarchy improvement. Results of comprehensive experiments indicate that the proposed method significantly outperforms state-of-theart methods (t-test, p-value < 0.000 1); recall has particularly improved by 20.4% to 38.7%.