Visual analytics for supporting entity relationship discovery on text data

• Main Authors: DAI, Hanbo, LIM, Ee Peng, LAUW, Hady W., PANG, Hwee Hwa
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2008
• Subjects: Information seeking; Interestingness measures; visual analytics; content analysis; text data; Databases and Information Systems; Numerical Analysis and Scientific Computing
• Online Access: https://ink.library.smu.edu.sg/sis_research/292; https://ink.library.smu.edu.sg/context/sis_research/article/1291/viewcontent/Visual_Analytics_for_Supporting_Entity_Relationship_Discovery_on_Text__edited_.pdf
• Institution: Singapore Management University

To conduct content analysis over text data, one may look out for important named objects and entities that refer to real world instances, synthesizing them into knowledge relevant to a given information seeking task. In this paper, we introduce a visual analytics tool called ER-Explorer to support such an analysis task. ER-Explorer consists of a data model known as TUBE and a set of data manipulation operations specially designed for examining entities and relationships in text. As part of TUBE, a set of interestingness measures is defined to help exploring entities and their relationships. We illustrate the use of ER-Explorer in performing the task of finding associations between two given entities over a text data collection.