Transcript PowerPoint template

Can you predict
who will win the
US election?
Samvel Gevorgyan
CEO, CYBER GATES
2016 © CYBER GATES
Who Dares Wins
2016
2012
WWW.CYBERGATES.ORG
Who will win the 2016 U.S.
presidential election?
Source: https://www.predictit.org/Market/1234/Who-will-win-the-2016-US-presidential-election
WWW.CYBERGATES.ORG
How good are you at predicting
election winners?
Dell Buys EMC For $67B In
Largest Deal In Tech History
EMC, a company worth twice Dell's value.
WWW.CYBERGATES.ORG
Data analysis
Data is Messy and Noisy
1.Data: raw data that has not been processed
for use.
2.Information: data that are processed to be
useful; provides answers to "who", "what",
"where", and "when" questions
3.Knowledge: application of data and
information; answers "how" questions
4.Understanding: appreciation of "why"
5.Wisdom: evaluated understanding.
WWW.CYBERGATES.ORG
What happens in an internet
minute?
Think before you post online
what you are thinking and
feeling about the election
race.
Facebook
293,000 statuses are updated
31,25 million messages are sent
Twitter
440,640 new tweets go online, etc.
Sources:
 http://www.internetlivestats.com
 https://zephoria.com/top-15-valuable-facebookstatistics/
WWW.CYBERGATES.ORG
Text Mining and Sentiment Analysis
Negative Words
Positive Words
A
abysmal
adverse
alarming
angry
annoy
anxious
apathy
appalling
atrocious
awful
B
bad
banal
barbed
belligerent
bemoan
beneath
boring
broken
A
absolutely
adorable
accepted
acclaimed
accomplish
accomplishment
achievement
action
active
admire
adventure
affirmative
affluent
agree
agreeable
amazing
angelic
appealing
approve
Source: http://www.enchantedlearning.com/wordlist/negativewords.shtml
WWW.CYBERGATES.ORG
Text Mining and Sentiment Analysis
positive
negative
The objective is to classify to tweets as Positive, Neutral, or Negative.
WWW.CYBERGATES.ORG
Text Mining and Sentiment Analysis
negative
Summary
Hillary Clinton
 Positive: 1
 Negative: 1
Donald Trump
 Positive: 0
 Negative: 1
WWW.CYBERGATES.ORG
Other JUCY information about the
audience
Metadata
 Genders
 Ages
 Locations
 Interests
WWW.CYBERGATES.ORG
Positive and negative reactions
from others
Assume you hate Donald Trump and you post some
negative thoughts about him online. Can we predict
your friends’ thoughts based on their likes or other
reactions?
WWW.CYBERGATES.ORG
Thank You!
Contacts
 Corporate website
www.cybergates.org
 Company profile on Twitter
www.twitter.com/CyberGatesLLC
 Company fan page on Facebook
www.facebook.com/Cyber.Gates.page
 Company profile on LinkedIn
www.linkedin.com/company/CyberGates-LLC
 Company channel on Vimeo
www.vimeo.com/CyberGates
 Company channel on YouTube
www.youtube.com/TheCyberGates