作者: Hyunmo Kang , L. Getoor , B. Shneiderman , M. Bilgic , L. Licamele
DOI: 10.1109/TVCG.2008.55
关键词:
摘要: Databases often contain uncertain and imprecise references to real-world entities. Entity resolution, the process of reconciling multiple underlying entities, is an important data cleaning required before accurate visualization or analysis possible. In many cases, in addition noisy describing there relationships among This relational during entity resolution process; it useful both for algorithms which determine likely database be resolved visual analytic tools support process. this paper, we introduce a novel user interface, D-Dupe, interactive data. D-Dupe effectively combines with network that enables users make use entity's context making decisions. Since decisions are interdependent, facilitates understanding complex through animations highlight combined inferences history mechanism allows inspect chains An empirical study 12 confirmed benefits on performance tasks terms time as well users' confidence satisfaction.