GR Semicolon EN

Show simple item record

dc.contributor.author
Oikonomou, Lazaros
en
dc.date.accessioned
2017-03-24T16:39:32Z
dc.date.available
2017-03-25T01:00:20Z
dc.date.issued
2017-03-24
dc.identifier.uri
https://repository.ihu.edu.gr//xmlui/handle/11544/15204
dc.rights
Default License
dc.title
Predicting the USA presidential elections using Twitter Data
en
heal.type
masterThesis
el
heal.creatorID.email
l.oikonomou@ihu.edu.gr
heal.keywordURI.LCSH
Internet research
heal.keywordURI.LCSH
Social media--Planning
heal.keywordURI.LCSH
Social media--Political aspects
heal.keywordURI.LCSH
Social media--Political aspects--United States
heal.keywordURI.LCSH
Social media--Research
heal.keywordURI.LCSH
Social media--United States
heal.keywordURI.LCSH
Twitter
heal.keywordURI.LCSH
Twitter--Political aspects--United States
heal.keywordURI.LCSH
Twitter--Social aspects
heal.keywordURI.LCSH
Presidents--United States--Election
heal.keywordURI.LCSH
Voting--United States
heal.language
en
el
heal.access
free
el
heal.license
http://creativecommons.org/licenses/by-nc/4.0
el
heal.references
[1] http://www.politico.com/2016 - election/results/map/presi dent [2] Paper: Tweets mining for French Presidential Election [3] Paper: Mining Twitter Big Data to Predict 2013 Pakistan Election Winner [4] Paper: Twitter as a tool for predicting election results [5] Paper: Prediction of Election Result by Enhanced Sentiment Analysis on Twitter Data using Word Sense Disambiguation [6] Paper: Emotion analysis of Twitter using Opinion mining [7] Paper: Opinion Mining about a Produc t by Analyzing Public Tweets in Twitter [8] https://dev.twitter.com/oauth [9] https://dev.twitter.com/rest/public/rate - limits [10] https://twitter.com/search - home [11] https://twitter.com/search - advanced [12] https://dev.twitter.com/rest/public/search [13] https://dev. twitter.com/rest/public/timelines [1 4 ] http://php.net/manual/en/book.curl.php [1 5 ] https://github.com/J7mbo [1 6 ] https://www.daftlogic.com/projects - google - maps - area - calculator - tool.htm [1 7 ] https://www.google.gr/maps [18] http://thinknook.com/twitter - sentiment - analysis - training - corpus - dataset - 2012 - 09 - 22/ [1 9 ] https://textblob.readthedocs.io/en/dev/ [20] http://www.nytimes.com/interactive/2016/us/elections/polls.html [21] http://www.usatoday.com/pages/interactives/2016/election/poll - tracker/ [22] http://www.stoiximan.gr
el
heal.recordProvider
School of Science and Technology, MSc in Information & Communication Technology Systems
el
heal.publicationDate
2017-11-07
heal.abstract
This Dissertation was written for the International Hellenic University’s MSc in Information and Communication Technology systems by student Lazaros Oikonomou under the supervision of Dr Christos Tjortjis. Social media is a part of our lives for some years now. More and more people tend to express themselves via social media. This is an opportunity for analysts to exploit the information available for free in these websites , and use them to foresee future results for events like elections, product releases and many more. In this dissertation we are going to gather information from the famous social media Twitter and analyze it with the purpose of predicting the results of the upcoming elections in the United States of America. We will use different tools and develop code that enables and enhances the analyzing process.
en
heal.tableOfContents
ABSTRACT TABLE OF CONTENTS LIST OF FIGURES 1. INTRODUCTION 1.1 THE PROBLEM 1.2 WHY TWITTER 1.3 DISSERTATION OBJECTIVES 1.4 ABOUT USA ELECTIONS 1.4.1 THE CANDIDATES 1.4.2 THE KEY STATES 1.4.3 THE IMPORTANT DATES 1.5 STRUCTURE 2. LITERATURE REVIEW 2.1 TWEETS MINING FOR FRENCH PRESIDENTIAL ELECTIONS 2.2 MINING TWITTER BIG DATA TO PREDICT 2013 PAKISTAN ELECTION WINNER 2.3 TWITTER AS A TOOL FOR PREDICTING ELECTION RESULTS 2.4 PREDICTION OF ELECTION RESULT BY ENHANCED SENTIMENT ANALYSIS ON TWITTER DATA USING WORD SENSE DISAMBIGUATION 2.5 EMOTION ANALYSIS OF TWITTER USING OPINION MINING 2.6 OPINION MINING ABOUT A PRODUCT BY ANALYZING TWEETS IN TWITTER 2.7 LITERATURE REVIEW CONCLUSIONS 3. DATA GATHERING 3.1 REST API 3.1.1 REST API RATE LIMITS 3.1.2 SEARCH API 3.2 PAGING PROBLEM 3.2.1 THE MAX_ID PARAMETER 3.2.2 THE SINCE_ID PARAMETER 3.3 STREAMING API 3.4 OUR APPROACH 3.5 PHP CODE REVIEW 4. SENTIMENT ANALYSIS 4.1 WHAT IS SENTIMENT ANALYSIS? 4.2 MACHINE LEARNING APPROACH 48 4.3 DATA PREPROCESS 4.4 PYTHON CODE REVIEW 4.5 IMPEMENTATION SUMMARY 5. TESTING & EVALUATION 5.1 TESTING 5.1.1 TESTING OUR PHP CODE 5.1.2 TESTING OUR PYTHON CODE 5.2 EVALUATION OF THE PROJECT 5.2.1 FLORIDA RESULTS 5.2.2 OHIO RESULTS 5.2.3 N. CAROLINA RESULTS 6. CONCLUSIONS AND FUTURE WORK 6.1 CONCLUSIONS 6.2 FUTURE WORK 6.2.1 DIFFERENT APPROACHES 6.2.2 LEXICONS 6.2.3 OTHER TOOLS FOR SENTIMENT ANALYSIS 7. REFERENCES AND BIBLIOGRAPHY
en
heal.advisorName
Christos, Tjortjis
en
heal.committeeMemberName
Christos, Berberidis
en
heal.academicPublisher
IHU
en
heal.academicPublisherID
ihu
el
heal.numberOfPages
70
el
heal.spatialCoverage
United States of America
en


This item appears in the following Collection(s)

Show simple item record

Related Items