Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/71028
Title: Fine-grained sentiment classification of social media data
Authors: She, Yanyao
Keywords: DRNTU::Engineering::Electrical and electronic engineering
Issue Date: 2017
Abstract: Social media offers a rich source of information, such as critiques, feedbacks, and other opinions posted online by internet users. Such information may reflect attitudes and sentiments of users towards certain topics, products, or services. The need to interpret the huge amount of data available on social media has accelerated the emergence of sentiment analysis. By definition, Sentiment analysis, or opinion mining, is a set of techniques under Natural Language Processing (NLP) that helps to identify users’ sentiments mainly by investigating, extracting and analysing subjective texts. In this project, the student is required to conduct research on academic literature as well as existing applications with an objective of improving the performance of SentiMo, a proprietary sentiment analysis engine developed by IHPC. This report consists of two parts. The first part includes the findings of a holistic research on sentiment analysis and existing applications in the market, as well as four improvement recommendations proposed for SentiMo as a result. Afterwards, the second part of the report is focused on the field of sarcasm detection for social media data, which aims at identifying sarcasm in users’ posts. A multidimensional analysis of sarcasm on social media and a comprehensive rule-based sarcasm detection framework are presented.
URI: http://hdl.handle.net/10356/71028
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 
Fine-Grained Sentiment Classification Of Social Media Data.pdf
  Restricted Access
1.13 MBAdobe PDFView/Open

Page view(s)

115
Updated on May 7, 2021

Download(s) 50

18
Updated on May 7, 2021

Google ScholarTM

Check

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