Please use this identifier to cite or link to this item:
Title: Comments summarization
Authors: Adilkhanov, Bauyrzhan
Keywords: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Document and text processing
Issue Date: 2014
Abstract: The abundance of social media platforms and other traditional types of websites allowing their users to communicate via comments as well as the availability and spread of various comment hosting services resulted in a lot of information being generated every day in a form of comments. Comments are generally short written remarks expressing someone’s opinions or reactions on a particular topic. When considered in large amounts, comments often prove to contain very useful information for both platform users as well as variety of organizations. However, as appealing the data contained in comments might be, it is not very easy to see the overall picture of the topics discussed in the numerous comments of such a typical nowadays news or blog article. Although many websites provide some kind of comments filtering functionality, none of those filters provide a way to get an overview or summary of all discussions occurring in the comments. Therefore, the objective of this project is to solve the aforementioned problem by designing and implementing a software that given an article from a particular website (Yahoo! News in this case) and its associated comments, would generate a summary of these comments taking into account all of the important topics discussed in the article itself as well as in its comments. Through the use of Natural Language Processing and Information Retrieval techniques, the program is implemented in this project that solves the problem mentioned.
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 
FYP Report.pdf
  Restricted Access
4.65 MBAdobe PDFView/Open

Google ScholarTM


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