GR Semicolon EN

Show simple item record

dc.contributor.author
Karyofyllidis, Karyofyllis
en
dc.date.accessioned
2019-04-08T08:53:20Z
dc.date.available
2019-04-09T00:00:22Z
dc.date.issued
2019-04-08
dc.identifier.uri
https://repository.ihu.edu.gr//xmlui/handle/11544/29302
dc.rights
Default License
dc.subject
Social Media
en
dc.subject
Data Mining
en
dc.subject
Sentiment Analysis
en
dc.subject
Big Data Analytics
en
dc.title
Sentiment Analysis for Twitter Users of America
en
heal.type
masterThesis
en_US
heal.creatorID.email
lex_kari@yahoo.com
heal.generalDescription
The target of this dissertation is to use one of the most famous social media platforms (Twitter) to extract sentiment information (happiness) about the users, performing text mining techniques on tweets. We will focus on sentiment analysis of users for the states of America. After the classification, data analysis will be produced using Business Intel-ligence tools to query them using various dimensions trying to justify the results and probably identify factors that influence this emotional state.
en
heal.classification
Computer Science
en
heal.classificationURI.MSC
Mobile and Web Computing
heal.language
en
en_US
heal.access
free
en_US
heal.license
http://creativecommons.org/licenses/by-nc/4.0
en_US
heal.recordProvider
School of Science and Technology, MSc in Mobile and Web Computing
en_US
heal.publicationDate
2019-04-01
heal.abstract
This dissertation was written as a part of the MSc in “Mobile and Web Computing” at the International Hellenic University, Thessaloniki, Greece. Nowadays, social media has noted as a type of online communication where people and organizations connect online to share information , thoughts and ideas . Be cause of its speed and reach , ease of use, social media influence various topics that range from the politics and environment to entertainment and the technology industry. Examples include Facebook , Twitter, LinkedIn etc . An important part of our information - gathering behavior has always been to find out what other people think, thus as mentioned above with the growing availability and popularity of social Media, people now can make use of information technologies techniques to seek out and understand the opinions of others through their posts . Techniques like Data Mining, Machine Learning, Sentiment Analysis will be introduced for the purpose of this thesis to classify opinions into sentiment states. Sentiment is a plain concept, simple to understand. It’s just a feeling or emotion, an attitude or opinion. On social media, the sentiment can be seen in the tone or emotion of users posts . Usually that kind of analysis group different sentiments or feelings into positive, negative, or neutral categories. The target of this dissertation is to use one of the most famous social media platforms (Twitter) to extract sentiment information (happiness) about the users, performing text mining techniques on tweets. We will focus on sentiment analysis of users for the states of America . After the classification, data analysis will be produced using Business Intelligence tools to query them using various dimensions trying to justify the results and probably identify factors that influence this emotional state .
en
heal.tableOfContents
ABSTRACT III CONTENTS IV 1 INTRODUCTION 7 2 BACKGROUND 10 2.1 SOCIAL MEDIA 10 2.1.1 The Impact of Social Media 17 2.1.2 Social Media Platforms 20 2.2 BIG DATA 26 2.2.1 What is Big Data 26 2.2.2 What is Big Data Analytics 28 2.2.3 Data warehousing Techniques and Tools 28 2.3 DATA MINING 35 2.3.1 What is data mining 35 2.3.2 Data mining techniques and algorithms 42 2.3.3 What is sentiment analysis. 46 2.4 CHOOSE THE RIGHT METRICS FOR DIMENSIONS 47 3 CASE STUDY 49 3.1 DATA COLLECTION 49 3.2 DATA STORAGE 53 3.3 DATA MINING 59 3.4 DATA TRANSFORMATION 64 3.5 CREATING DATA ANALYTICS AND REPORTING 68 4 RESULTS 71 4.1.1 Interpretation of the results from a socio–political point of view 71 5 CONCLUSIONS 75 5.1 SUMMARY 75 5.2 FUTURE WORK 76 BIBLIOGRAPHY 77
en
heal.advisorName
Papadopoulos, Apostolos
en
heal.committeeMemberName
Papadopoulos, Apostolos
en
heal.academicPublisher
IHU
en
heal.academicPublisherID
ihu
en_US
heal.numberOfPages
78
en_US


This item appears in the following Collection(s)

Show simple item record

Related Items