Spatial-temporal community emotion estimation through social media text sentiment analysis

Pao Yue-kong Library Electronic Theses Database

Spatial-temporal community emotion estimation through social media text sentiment analysis

 

Author: Lee, Hung Fai
Title: Spatial-temporal community emotion estimation through social media text sentiment analysis
Degree: M.Sc.
Year: 2017
Subject: Social media -- Social aspects.
Social media -- Social aspects -- China -- Hong Kong.
Online social networks -- Social aspects.
Online social networks -- Social aspects -- China -- Hong Kong.
Public opinion -- Data processing.
Computational linguistics.
Hong Kong Polytechnic University -- Dissertations
Department: Dept. of Computing
Pages: vii, 50, 3 pages : color illustrations
Language: English
InnoPac Record: http://library.polyu.edu.hk/record=b2950013
URI: http://theses.lib.polyu.edu.hk/handle/200/8856
Abstract: Community sentiment status awareness is beneficial to individual emotion regulation [10]. Strong emotional content spread over wide geographical area with fast speed [29]. Community emotion status can be quickly reflected on social media. Therefore, a spatial-temporal community emotion status awareness system can be built by collecting text content from social media for sentiment analysis. Data was collected from social media Twitter by using Twitter provided API, the replied message marked with user's location and issuing date. The system scan through 14 districts in Hong Kong to collect the post between end of August to the end of October. 1-gram tf-idf technique were adopted to extract emotion feature from the text. Emotion classifier was built by using SVM-rbf kernel machine learning model. Non-local online corpus dataset was adopted as training set. The post from corpus which contain certain number of top 200 most frequent appear terms in local collected dataset was picked for training. This can refine the online corpus dataset as consist with local collected post as possible. The experiment result shows training with higher term consistency dataset has better accuracy while classifying local collected tweets. Collective emotion visualized in different region and different time. Analyzing those spatial-temporal data found that emotion in Southern and Shatin district has more obvious downward trends during data collection period. In district Wan Chai, Central Western and Yau Tsim Mong have higher tendency with good mood on Friday, Saturday and Sunday.

Files in this item

Files Size Format
b29500138.pdf 2.178Mb PDF
Copyright Undertaking
As a bona fide Library user, I declare that:
  1. I will abide by the rules and legal ordinances governing copyright regarding the use of the Database.
  2. I will use the Database for the purpose of my research or private study only and not for circulation or further reproduction or any other purpose.
  3. I agree to indemnify and hold the University harmless from and against any loss, damage, cost, liability or expenses arising from copyright infringement or unauthorized usage.
By downloading any item(s) listed above, you acknowledge that you have read and understood the copyright undertaking as stated above, and agree to be bound by all of its terms.

     

Quick Search

Browse

More Information