Please use this identifier to cite or link to this item:
Title: Review/opinion search engine (ROSE)
Authors: Zhang, Qichuan
Keywords: DRNTU::Engineering::Computer science and engineering::Information systems::Information storage and retrieval
Issue Date: 2009
Abstract: Before purchasing a product, wouldn't it be nice if you can instantly get product rankings, user reviews and opinions, all from just one website, without wasting time looking through the reviews from many websites. ROSE does this for you! ROSE requires minimal human effort; a sentiment classifier automatically process and analyze the huge amount of review data extracted from various online review websites. The ROSE front-end presents the analyzed result in a well-organized manner. ROSE is currently focused on Chinese reviews, and will join the Chinese Internet community soon. This report focuses on two main aspects. 1.ROSE Control Panel development, how Rich Internet Application paradigm can be applied to implement the control panel such that, user experience can be similar to desktop application, as well as increase in information transmission efficiency. 2.Semantic sentiment classification, the machine learning magic behind ROSE, which is responsible for classifying reviews into POSTIVE, NEGATIVE or NEUTRAL categories.
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:SCSE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
  Restricted Access
1.65 MBAdobe PDFView/Open

Google ScholarTM


Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.