Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/73008
Title: User-level twitter polarity classification using a hybrid approach
Authors: Chong, Kah Weng
Keywords: DRNTU::Engineering::Electrical and electronic engineering
Issue Date: 2017
Abstract: Sentiment analysis often bring information and prediction about opinions. For a large corpus of opinions data on Twitter, it is always not simple to analyze due to different personal expression and the grammar level they use. Moreover, Emoji and slangs, abbreviation bring tougher challenge. Today, having a sentiment analysis tools for Twitter data mining is usefulness in terms of business survey, detection of terrorist mind sets, and for better understanding of particular user. Although the analytic result might not be 100% true and accurate, it create a compare platform that consumer can choose between different brands when comes to choice. On the other hand, detection of terrorist mind sets is always a play-safe strategy especially in current world which more and more terrorist attacked was launched unexpectedly. Lastly, to study a person behavior and properties, sentiment analysis bring great achievement. This program use hybrid approach to cover the brevity, lack of context, same word used to express different sentiments by different users.
URI: http://hdl.handle.net/10356/73008
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
EEE FYP Chong Kah Weng 13DEC2017.pdf
  Restricted Access
Project Report2.23 MBAdobe PDFView/Open

Page view(s) 50

98
checked on Oct 1, 2020

Download(s) 50

18
checked on Oct 1, 2020

Google ScholarTM

Check

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