A Survey on Visual Text Analytics

PhD Qualifying Examination


Title: "A Survey on Visual Text Analytics"

by

Mr. Siwei FU


Abstract:

With the development of web technologies, especially the advent of social 
media, a wide variety of textual data, such as online news, forum data and 
Twitter data, have been generated and become available. This is providing 
opportunities for individuals and corporations to find insightful patterns and 
make better decisions. Text analytical techniques are frequently employed to 
help users investigate large volumes of unstructured or semi-structured text 
data. However, complex analytical results cannot easily be interpreted by users 
lacking a comprehensive computer science background. On the other hand, visual 
text analytics, which combines text visualization with text analytical 
techniques, has become increasingly popular in recent years.

In this survey, we provide an overview of visual text analytics to guide our 
further research. We first present the taxonomy of text data, and then 
summarize text analytical techniques in five categories (i.e., information 
extraction, text summarization, sentiment analysis, text clustering, and text 
classification). After that, we introduce major visualization representations 
for text data,  followed by a description of visual text analytics systems used 
in different domains. In the end of the survey, we discuss the remaining 
challenges and suggest future research directions.


Date:  			Wednesday, 14 October 2015

Time:                  	2:00pm - 4:00pm

Venue:                  Room CYTG002
                         CYT Building

Committee Members:	Prof. Huamin Qu (Supervisor)
 			Prof. Chiew-Lan Tai (Chairperson)
 			Prof. Chi-Keung Tang
 			Prof. Nevin Zhang


**** ALL are Welcome ****