Comments summarization

• Main Author: Adilkhanov, Bauyrzhan
• Other Authors: Sun Aixin
• Format: Final Year Project
• Language: English
• Published: 2014
• Subjects: DRNTU::Engineering::Computer science and engineering::Computing methodologies::Document and text processing
• Online Access: http://hdl.handle.net/10356/59257
• Institution: Nanyang Technological University

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.