User-level twitter polarity classification with a hybrid approach

With the objective of extracting useful information from the vast amount of opinion-rich data on Twitter, both supervised learning-based and unsupervised lexicon-based methods for sentiment analysis on Twitter corpus are studied in recent years. However, the unique characteristics of tweets such as...

Full description

Saved in:
Bibliographic Details
Main Author: Liu, Fan
Other Authors: Er Meng Joo
Format: Final Year Project
Language:English
Published: 2016
Subjects:
Online Access:http://hdl.handle.net/10356/67830
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Nanyang Technological University
Language: English
id sg-ntu-dr.10356-67830
record_format dspace
spelling sg-ntu-dr.10356-678302023-07-07T16:43:18Z User-level twitter polarity classification with a hybrid approach Liu, Fan Er Meng Joo School of Electrical and Electronic Engineering DRNTU::Engineering With the objective of extracting useful information from the vast amount of opinion-rich data on Twitter, both supervised learning-based and unsupervised lexicon-based methods for sentiment analysis on Twitter corpus are studied in recent years. However, the unique characteristics of tweets such as the lack of labels and frequent usage of emoticons in tweets poses challenges to most of the existing learning-based and lexicon-based methods. In addition, studies on Twitter sentiment analysis nowadays mainly focus on domain specific tweets while a larger amount of tweets are about personal feelings and comments on daily life events. Therefore, in this project, a hybrid approach combining augmented lexicon-based and learning-based method is designed to handle the distinctive characteristics of tweets and perform sentiment analysis on a user-level, providing us information of specific Twitter users’ typing habits and their online sentiment fluctuations. Our model is capable of achieving an overall accuracy of 83.3%, largely outperforming current baseline lexicon-based and learning-based models on user-level tweets classification. Bachelor of Engineering 2016-05-21T06:49:18Z 2016-05-21T06:49:18Z 2016 Final Year Project (FYP) http://hdl.handle.net/10356/67830 en Nanyang Technological University 55 p. application/pdf
institution Nanyang Technological University
building NTU Library
continent Asia
country Singapore
Singapore
content_provider NTU Library
collection DR-NTU
language English
topic DRNTU::Engineering
spellingShingle DRNTU::Engineering
Liu, Fan
User-level twitter polarity classification with a hybrid approach
description With the objective of extracting useful information from the vast amount of opinion-rich data on Twitter, both supervised learning-based and unsupervised lexicon-based methods for sentiment analysis on Twitter corpus are studied in recent years. However, the unique characteristics of tweets such as the lack of labels and frequent usage of emoticons in tweets poses challenges to most of the existing learning-based and lexicon-based methods. In addition, studies on Twitter sentiment analysis nowadays mainly focus on domain specific tweets while a larger amount of tweets are about personal feelings and comments on daily life events. Therefore, in this project, a hybrid approach combining augmented lexicon-based and learning-based method is designed to handle the distinctive characteristics of tweets and perform sentiment analysis on a user-level, providing us information of specific Twitter users’ typing habits and their online sentiment fluctuations. Our model is capable of achieving an overall accuracy of 83.3%, largely outperforming current baseline lexicon-based and learning-based models on user-level tweets classification.
author2 Er Meng Joo
author_facet Er Meng Joo
Liu, Fan
format Final Year Project
author Liu, Fan
author_sort Liu, Fan
title User-level twitter polarity classification with a hybrid approach
title_short User-level twitter polarity classification with a hybrid approach
title_full User-level twitter polarity classification with a hybrid approach
title_fullStr User-level twitter polarity classification with a hybrid approach
title_full_unstemmed User-level twitter polarity classification with a hybrid approach
title_sort user-level twitter polarity classification with a hybrid approach
publishDate 2016
url http://hdl.handle.net/10356/67830
_version_ 1772826169909968896