DATA SETS. What were the data collection process. When, where, and how? PRE-PROCESSING. Natural language data pre-processing steps
|
|
- Felicia Newman
- 6 years ago
- Views:
Transcription
1
2 01 DATA SETS What were the data collection process. When, where, and how? 02 PRE-PROCESSING Natural language data pre-processing steps
3 03 RULE-BASED CLASSIFICATIONS Without using machine learning, can we use some basic rules to classify sentiments? 04 MACHINE LEARNING BINARY CLASSIFICATIONS Using machine learning algorithms, we attempt to classify positive and negative sentiments 05 MACHINE LEARNING MULTI-CLASS CLASSIFICATIONS Using machine learning to predict positive, neutral and negative sentiments and determine the best model for data with unknown sentiments
4 06 REASULTS The summary and statistics of the collected airline tweets 07 CLOSING THOUGHTS FEEDBACK Q&A
5 Where, when and how?
6 AA DELTA SOUTHWEST UNITED #americanairlines #deltaairlines #southwestairlines #unitedairlines #americanair #deltaair #southwestair #unitedair
7 k 80,121 Tweets TWITTER API Using Python and twython to retrieve tweets through Twitter s API during 7 days period. 14,640 Tweets KAGGLE Reformatted/cleaned tweets with graded sentiment of Major Airlines from Feb ,000 Tweets Newsroom Commercial datasets provided by Newsroom with machine graded tweets
8
9 Natural language processes to prepare and transform the tweet content for various classification models and sentiment analysis
10 Major processing steps Tokenize all tweet Perform regular Remove all the English For machine learning contents expression stop words Vector Matrix get it?
11 tweet.lower() re.sub('((www\.[^\s]+) (https?://[^\s]+))','url',tweet) r'\1', tweet) Lower Cases Eliminate URLs Turn all letters to lower cases. One Turn all and www format to Convert to display just option is to retain original upper cases display just the word URL username without sign re.sub(r'#([^\s]+)', r'\1', tweet) Replace #hastags & re.sub(r'&', r' and', tweet) Replace & Signs re.sub('[\s]+', ' ', tweet) Remove Additional Spaces Convert all #hashtagwords to just Replacing all & symbols with the Remove all annoying white spaces hashtagwords actual words and with a space
12 RULE BASED First we will use two simple rule-based techniques to conduct our sentiment analysis to see what happens
13 (pos) x (pos) = (pos) This movie is very good (pos) x (neg) = (neg) This movie is not good at all (neg) x (neg) = (pos) This movie was not bad
14
15 VADER is a lexicon and rulebased sentiment analysis tool that is especially attuned to sentiments expressed in social media.
16 Examples VADER is smart, handsome and funny. { neg : 0.0, neu : 0.254, pos : 0.746, compound : } Today SUX! { neg : 0.779, neu : 0.221, pos : 0.0, compound : } VADER is very smart, handsome, and funny! { neg : 0.0, neu : 0.293, pos : 0.707, compound : } Today kinda sux! But I ll get by, lol :) { neg : 0.154, neu : 0.42, pos : 0.426, compound : } VADER is VERY SMART, handsome, and FUNNY!!! { neg : 0.0, neu : 0.233, pos : 0.767, compound : } At least it isn t a horrible book. { neg : 0.0, neu : 0.637, pos : 0.363, compound : 0.431}
17
18 Part I Binary Classifications
19 Data Prep Remove All Neutral Sentiment Random Forest Perform Random Forest Model Linear SVM Perform Support Vector Classifier Hyperplane
20 k k TRAINING: 9,266 TESTING: 2,275 Training Accuracy: 99.87% Testing Accuracy: 89.58% k TRAINING: 1,124 TESTING: 290 Training Accuracy: 99.91% Testing Accuracy: 84.48% TRAINING: 11,541 TESTING: 1,843 Training Accuracy: 99.88% Testing Accuracy: 86.49%
21 k TRAINING: 1,124 TESTING: 290 Training Accuracy: 99.56% Testing Accuracy: 84.14% TRAINING: 11,541 TESTING: 1,843 Training Accuracy: 99.12% Testing Accuracy: 86.38% k k TRAINING: 9,266 TESTING: 2,275 Training Accuracy: 99.18% Testing Accuracy: 90.95%
22 MACHINE LEARING Part II Multi-Class Classifications
23 k TRAINING: 2,040 TESTING: 360 TRAINING: 14,640 TESTING: 2,400
24 CV Accuracy 67.80% 64.86% Test Accuracy 60.88% 66.94% [+1] Precision 33.85% 60.34% [ne] Precision 1.43% 50.00% [ -1] Precision 65.25% 96.89% 0% 20% 40% 60% 80% 100% 120% Kaggle->Tweet Tweet->Tweet While the test accuracy is slightly lower, using Kaggle data as training set proved to be a stronger predictor based on the crossvalidation accuracy results. In addition, it is superior in positive and neutral precision, not to mention much higher training volume.
25 CV Accuracy 71.91% 66.39% Test Accuracy 69.08% 69.72% [+1] Precision 47.69% 60.34% [ne] Precision 14.29% 49.10% [ -1] Precision 79.34% 93.33% 0% 10% 20% 30% 40% 50% 60% 70% 80% 90% 100% Kaggle->Tweet Tweet->Tweet Again, while we see the precision of the twitter data is superior, the Kaggle data yields a more balanced results for all three sentiments. Because the overall test accuracy is about the same, we chose to use Kaggle data as training due to its superior CV accuracy as well as its large sum of data points (~8X).
26 Support Vector Classifier Model Parameters: decision_fun= ovo, kernel= linear, cost=0.4, gamma=0 Use Entire Kaggle Dataset as Training Set (14,640 data points) Apply Model to Tweets of Unknown Sentiment
27 Now we have the model, let s take a look at the results of collected tweets!
28 American 10,516 18,762 Delta 5,728 11,718 Southwest 5,478 9,647 United 5,705 12, ,000 4,000 6,000 8,000 10,000 12,000 14,000 16,000 18,000 20,000 Original Tweets Re-Tweets
29 Negative 52,694 Original Tweets Neutral Positive
30 20, % 18,000 90% 16,000 80% 14,000 70% 12,000 60% 10,000 50% 8,000 40% 6,000 30% 4,000 20% 2,000 10% 0 American Delta Southwest United 0% American Delta Southwest United Negative Netual Positive Negative Netual Positive
31 Negative Sentiment Cenk Uygur Positive Sentiment -
32 Negative Sentiment Delta Assist Positive Sentiment -
33 Negative Sentiment Dalton Rapattoni Positive Sentiment Dalton Rapattoni
34 Negative Sentiment Muslim, Shame Positive Sentiment Happy Birthday, 90th"
35 59.5% 49.2% If the sentiment is classify accurately, people are more likely to retweet a neutral or positive tweets than a negative tweet. 26.0% 31.7% 14.5% 19.1% NEGATIVE NEUTRAL POSITIVE Original Tweets Retweets
36 10,260 I know it's crazy #DFWsnow I'm just excited 2see my baby girl! Man freaking out next 2 me isn't helping 3,795 Retweets The and Lucian Grainge #MusicIsUniversal #UMGShowcase 17,093 Retweets We re partnering to send a lucky fan to games 1 & 2! RT for your chance to win #DeltaMetsSweeps 3,535 Retweets for adding our movie to all your flights! If any of you are traveling and bored make sure u peep it 3,362 Retweets Yo #Kimye, we're really happy for you, we'll let you finish, but South is one of the best names of all time. 1,952 Retweets Been home in Dallas for hours now but still in the PLEASE find my bag. Please RT. #SWAFindDalto 3,329 Retweets this skank bitch was SO RUDE to me on my I asked for her name and she goes, "it's Britney bitch. 352 Retweets Arab-American family of 5 going on vacation - 3 young kids in tow - removed plane for "safety reasons"
37 iphone 60% 50% 40% 30% 20% Others 10% 0% Android The majority of the tweets are from iphone. There is also almost 20% of tweets from Android devices. The rest from the Web client and other applications. There is little difference between the source of negative and positive tweets; but there seems to be more alternative sources for the neutral sentiment. Web Negative Neutral Positive
38 Photo Photo Link Video Link Negative Neutral Positive
39 ENDING THOUGHTS Discussing final thoughts and some future steps
40 COORDINATES MULTIPLE VALIDATION OTHER MODELS CLUSTERING Current coordinates data Each data point being Naïve Bayes Unsupervised model to isn t great for Geo-location validated by multiple people Lemmatization discover words association analysis
41
42 Project Description Prior to machine learning, the project conducted two rule-based sentiment classifications. One of which simply count the number of positive and negative words, and the other utilizes VADER lexicon, a pre-built sentiment analysis tool for Python. Both rule-based sentiment classifications achieved an accuracy of 47% to 55%. The project aims to use rule-based classification and machine learning algorithms to predict content sentiments of Twitter feeds that mentioned four major airlines: American Airline, United, Delta, and Southwest. Next, the project used machine learning algorithms Random Forest, and Support Vector Classifier to conduct binary classification on positive and negative sentiments by removing all known neutral tweets. 85% to 90% accuracy were achieved on the test dataset. The project collected 80,121 tweets during a 7-day period via Twitter s API using Twython, a Python package; among these tweets, 2,400 randomly selected tweets were given a sentiment rating manually (test). Through Kaggle, the project also obtained a cleaned dataset contains 14,640 airline tweets with already rated sentiments (training). Finally, the project used Ada Boost and Support Vector Classifier to conduct multi-class classifications by including back all neutral tweets. Through grid-search and cross-validation, the project achieved a 70% overall accuracy on prediction and an 80% precision on negative sentiment prediction on the test dataset. To start off the project, the tweets were processed using tokenization, regular expression, stop words removals, and vectorization. In regular expression, the project eliminated all sign, # sign, and replaced & sign with the word and. Using the best model and parameters found, the model is applied to tweets with unknown sentiments. The statistics summary were included in the later half of the presentation. The presented word clouds also captured interesting stories during the time the tweets were collected.
Predicting the Odds of Getting Retweeted
Predicting the Odds of Getting Retweeted Arun Mahendra Stanford University arunmahe@stanford.edu 1. Introduction Millions of people tweet every day about almost any topic imaginable, but only a small percent
More informationNew restaurants fail at a surprisingly
Predicting New Restaurant Success and Rating with Yelp Aileen Wang, William Zeng, Jessica Zhang Stanford University aileen15@stanford.edu, wizeng@stanford.edu, jzhang4@stanford.edu December 16, 2016 Abstract
More informationContext-Sensitive Classification of Short Colloquial Text
Context-Sensitive Classification of Short Colloquial Text TU Delft - Network Architectures and Services (NAS) 1/12 Outline Emotions propagate through a social network like viruses. Some people influence
More informationOPEN ENROLLMENT SOCIAL MEDIA TOOLKIT
Action for Health Justice OPEN ENROLLMENT SOCIAL MEDIA TOOLKIT Asian & Pacific Islander American Health Forum Association of Asian Pacific Community Health Organizations Asian Americans Advancing Justice
More informationCOMPLEX MEDIA: BRINGING SOCIAL STATS TO EVERY DEPARTMENT
COMPLEX MEDIA: BRINGING SOCIAL STATS TO EVERY DEPARTMENT TABLE OF CONTENTS Introduction The Social Media Team The Ad Sales Team The Content Team The Dev Team Social Strategy Tips INTRODUCTION There are
More informationHow to Set-Up a Basic Twitter Page
How to Set-Up a Basic Twitter Page 1. Go to http://twitter.com and find the sign up box, or go directly to https://twitter.com/signup 1 2. Enter your full name, email address, and a password 3. Click Sign
More informationData Mining in Social Network. Presenter: Keren Ye
Data Mining in Social Network Presenter: Keren Ye References Kwak, Haewoon, et al. "What is Twitter, a social network or a news media?." Proceedings of the 19th international conference on World wide web.
More informationPredicting Airbnb Bookings by Country
Michael Dimitras A12465780 CSE 190 Assignment 2 Predicting Airbnb Bookings by Country 1: Dataset Description For this assignment, I selected the Airbnb New User Bookings set from Kaggle. The dataset is
More informationLOAN OFFICER GUIDE TO MARKETING : LEAD NURTURING REALTOR GUIDE TO MARKETING TOTALMORTGAGE.COM PART 1
LOAN OFFICER GUIDE TO MARKETING : EMAIL LEAD NURTURING REALTOR GUIDE TO MARKETING ADVERTISING EMAIL LEAD ON NURTURING SOCIAL MEDIA TOTALMORTGAGE.COM PART 1 Table of Contents LinkedIn...4 Understanding
More informationMeasure Social Media Like a Pro: Social Media Analytics Uncovered
Measure Social Media Like a Pro: Social Media Analytics Uncovered To kick off the year 2016, more than 1 billion people logged onto Facebook. Every day, 934 million users access Facebook from their mobile
More informationTwitter page management for beginners
Twitter page management for beginners Twitter page management for beginners 2 Contents Executive Summary.... 4. Introduction to Twitter... 5 Twitter Statistics. 5 Twitter Demographics 6... Logging In &
More informationNLP WHAT S HAPPENING TO NLP?
WHAT S HAPPENING TO NLP? A Guide to Synthesio s New & Improved Natural Language Processing Capabilities WHAT IS HAPPENING TO NLP? Synthesio s Natural Language Processing (NLP) model is about to undergo
More informationBrian Macdonald Big Data & Analytics Specialist - Oracle
Brian Macdonald Big Data & Analytics Specialist - Oracle Improving Predictive Model Development Time with R and Oracle Big Data Discovery brian.macdonald@oracle.com Copyright 2015, Oracle and/or its affiliates.
More informationExperiences in the Use of Big Data for Official Statistics
Think Big - Data innovation in Latin America Santiago, Chile 6 th March 2017 Experiences in the Use of Big Data for Official Statistics Antonino Virgillito Istat Introduction The use of Big Data sources
More informationwww.pipelineroi.com 1-866-300-1550 Introduction Over 100 million people log in to Twitter daily to share articles, read the news, Tweet photos of their breakfast, and connect with others. In this crowded
More informationHow To Attract Crowds To Your Webinar
How To Attract Crowds To Your Webinar Introduction The success of your webinar depends on attracting the right crowd. Of course, you ve already spent a lot of time preparing the event. Now make an extra
More informationwww.pipelineroi.com 1-866-300-1550 Introduction Over 100 million people log in to Twitter daily to share articles, read the news, Tweet photos of their breakfast, and connect with others. In this crowded
More informationData Preprocessing, Sentiment Analysis & NER On Twitter Data.
IOSR Journal of Computer Engineering (IOSR-JCE) e-issn: 2278-0661,p-ISSN: 2278-8727 PP 73-79 www.iosrjournals.org Data Preprocessing, Sentiment Analysis & NER On Twitter Data. Mr.SanketPatil, Prof.VarshaWangikar,
More informationSocial Media and Self-Advocacy KIT MEAD AUTISTIC SELF ADVOCACY NETWORK (ASAN)
Social Media and Self-Advocacy KIT MEAD AUTISTIC SELF ADVOCACY NETWORK (ASAN) The Presenter! -I m Kit Mead, ASAN s Technical Assistance Coordinator! -I run ASAN s chapters and PADSA. -I give help to our
More informationPredicting Stock Prices through Textual Analysis of Web News
Predicting Stock Prices through Textual Analysis of Web News Daniel Gallegos, Alice Hau December 11, 2015 1 Introduction Investors have access to a wealth of information through a variety of news channels
More informationCONSUMER SENTIMENT ANALYSIS USING TWITTER
CONSUMER SENTIMENT ANALYSIS USING TWITTER A Paper Submitted to the Graduate Faculty of the North Dakota State University of Agriculture and Applied Science By Rumana Rashid In Partial Fulfillment of the
More informationTwitterRank: Finding Topicsensitive Influential Twitterers
TwitterRank: Finding Topicsensitive Influential Twitterers Jianshu Weng, Ee-Peng Lim, Jing Jiang Singapore Management University Qi He Pennsylvania State University WSDM 2010 Feb 5, 2010 Outline Introduction
More informationA Guide to Social Media Team
A Guide to Social Media Team Advocacy Why should your employees support your business via social media? Increases Brand Exposure Extends Awareness in Marketplace Generates Business Opportunities Cultivates
More informationSocial Media Savvy: Facebook and Twitter. Jennifer Li AFSCME Digital Communications
Social Media Savvy: Facebook and Twitter Jennifer Li AFSCME Digital Communications Facebook Profile vs. Page vs. Group Profiles should only be used for personal use Pages more professional; allows for
More informationEmployer Branding Essentials. 4 Tips Inspired by LinkedIn s Top Attractors Ranking
Employer Branding Essentials 4 Tips Inspired by LinkedIn s Top Attractors Ranking Introduction Your reputation as an employer is everything. If you have a good one, top candidates want to work for you
More informationFACEBOOK GUIDE HOW TO USE FACEBOOK FOR RECRUITMENT MARKETING
FACEBOOK GUIDE HOW TO USE FACEBOOK FOR RECRUITMENT MARKETING 01 01 CONTENTS INTRODUCTION 2 WHAT IS A FACEBOOK PAGE? 3 WHY DO EMPLOYERS USE FACEBOOK? 4 FACEBOOK STRATEGY 5 GETTING STARTED 6 THE BASICS 8
More informationAN INTRODUCTION TO FACEBOOK FOR BUSINESS.
AN INTRODUCTION TO FACEBOOK FOR BUSINESS. A setup and strategy guide for marketers. f A publication of 2 CONTENTS. 03 04 Why use Facebook? An Introduction to Facebook 09 Setting up Your Facebook Business
More informationTHE COVER LETTER CHECKLIST: 9 INGREDIENTS YOU NEED FOR A STAND-OUT COVER LETTER.
THE COVER LETTER CHECKLIST: 9 INGREDIENTS YOU NEED FOR A STAND-OUT COVER LETTER. YOUR COVER LETTER MATTERS. Nothing turns off a recruiter or hiring manager more than a generic cover letter. It s important
More informationSocial Media. An introductory guide.
Social Media An introductory guide About this resource This resource is intended as an introductory guide It is not intended to give comprehensive guidance on all matters relating to Social Media In this
More informationWhen Social Media Meets Employer Branding: Your Guide to Doing It Right
When Social Media Meets Employer Branding: Your Guide to Doing It Right Why does social media matter for employer branding? You know your company is a great place to work but does everyone else? Social
More informationApplication of Machine Learning to Financial Trading
Application of Machine Learning to Financial Trading January 2, 2015 Some slides borrowed from: Andrew Moore s lectures, Yaser Abu Mustafa s lectures About Us Our Goal : To use advanced mathematical and
More informationA Framework for Analyzing Twitter to Detect Community Crime Activity
SESSION ID: CCT2-W05 A Framework for Analyzing Twitter to Detect Community Crime Activity Safaa S. Al Dhanhani @ssdhanhani Outline Why? Literature review What is the framework Approach How? 2 Cont. Outline
More informationWho s Here Today? B2B Social Media: Why?
Who s Here Today? Agenda B2B Social Media Going Beyond LinkedIn B2B: Why Use Social Media? Best Practices Facebook LinkedIn Twitter Analytics B2B Social Media: Why? B2B Social Media: Why? B2B Social Media:
More informationGet started and get better Erwin Taets VIVES Leisure Management Research & Expertise Center
Social Media 2.0 Get started and get better Erwin Taets VIVES Leisure Management Research & Expertise Center VIVES previously known as KATHO new name: VIVES since September 2013 VIVES = you will live in
More informationTwitter Set-up Guide. How to Optimize Your Profile
Twitter Set-up Guide How to Optimize Your Profile WHY TWITTER IS VALUABLE TO YOUR BUSINESS Before You Get Started Consider if you want a personal or a business Twitter account. Both are good to have but
More informationHow to Make Your Content Go VIRAL!
How to Make Your Content Go VIRAL! The number one rule in marketing is to create crisp, compelling content from the heart but without any intent of it going viral. Initially, that may sound confusing but
More informationWelcome to. The Social Media System Twitter Success System
Welcome to The Social Media System 2016 Twitter Success System 1 330 Million users worldwide Interesting Twitter Stats Daily active Twitter users: 100 million Average number of followers: 208 4 th largest
More informationE-Commerce Sales Prediction Using Listing Keywords
E-Commerce Sales Prediction Using Listing Keywords Stephanie Chen (asksteph@stanford.edu) 1 Introduction Small online retailers usually set themselves apart from brick and mortar stores, traditional brand
More informationBIZZLOC! - Locate Your Business Group Web Mining Project
BIZZLOC! - Locate Your Business Group Web Mining Project 5/13/2014 MIS 510: Web Mining Team 1 Team Members Rohit Bhalerao Rohit Garg Kushagra Parikh Elias Paramo 0 Contents Team Members and Responsibilities...2
More informationPAST research has shown that real-time Twitter data can
Algorithmic Trading of Cryptocurrency Based on Twitter Sentiment Analysis Stuart Colianni, Stephanie Rosales, and Michael Signorotti ABSTRACT PAST research has shown that real-time Twitter data can be
More informationHOW TO SETUP YOUR PROFILE
Twitter 101 Not sure how to set up a Twitter account? Already signed up, but wondering how to get started? This guide is for you! We ll give you step-by-step instructions so you can dive into Twitter,
More informationThree Ways to Better Connect Your Workforce with Enterprise Social
Three Ways to Better Connect Your Workforce with Enterprise Social Published: July 2014 For the latest information, please visit http://aka.ms/connectedworkforce 1 Table of Contents The World Has Become
More informationProactive Listening: Taking Action to Meet Customer Expectations
2013 Proactive Listening: Taking Action to Meet Customer Expectations Summary: Proactive listening lets your company meet your customers demands for coordinated, responsive treatments. A proactive listening
More informationA Personalized Company Recommender System for Job Seekers Yixin Cai, Ruixi Lin, Yue Kang
A Personalized Company Recommender System for Job Seekers Yixin Cai, Ruixi Lin, Yue Kang Abstract Our team intends to develop a recommendation system for job seekers based on the information of current
More informationThe Importance of Supplementing NPS Scores with Insights Drawn from Real Comments and Reviews. Whitepaper
The Importance of Supplementing NPS Scores with Insights Drawn from Real Comments and Reviews Whitepaper INTRODUCTION/EXECUTIVE SUMMARY The Net Promoter Score (NPS) system has transformed the way businesses
More informationInferring Nationalities of Twitter Users and Studying Inter-National Linking
Inferring Nationalities of Twitter Users and Studying Inter-National Linking Wenyi Huang Ingmar Weber Sarah Vieweg Information Sciences and Technology Pennsylvania State University University Park, PA
More informationHow Beacons Can Reshape Retail Marketing
How Beacons Can Reshape Retail Marketing Written by Peter Lewis Published August 2016 Beacon technology is poised to change the way consumers interact with brands, making devices more helpful and revolutionizing
More informationEvaluation of Machine Learning Algorithms for Satellite Operations Support
Evaluation of Machine Learning Algorithms for Satellite Operations Support Julian Spencer-Jones, Spacecraft Engineer Telenor Satellite AS Greg Adamski, Member of Technical Staff L3 Technologies Telemetry
More informationFill in the worksheet with your responses (per the instructions in the write up for the deliverable).
ANALYTICSLM Worksheet 1 Fill in the worksheet with your responses (per the instructions in the write up for the deliverable). Word Clouds 1. Briefly describe your two writing samples and why you have chosen
More informationSocial Media. BootCamp
Social Media BootCamp Shawn Busse Kinesis Brand Strategist Wendy Maynard Social Guru Shawn Busse Social Pragmatist What is a Brand? ...a brand is your company s face to the world. It starts with the name,
More informationTWITTER GUIDE TABLE OF CONTENTS
TWITTER GUIDE Not sure how to set up a Twitter account? Already signed up, but wondering how to get started? This guide is for you! We ll give you step-by-step instructions so you can dive into Twitter,
More informationPrediction of Google Local Users Restaurant ratings
CSE 190 Assignment 2 Report Professor Julian McAuley Page 1 Nov 30, 2015 Prediction of Google Local Users Restaurant ratings Shunxin Lu Muyu Ma Ziran Zhang Xin Chen Abstract Since mobile devices and the
More informationPredictive Modelling for Customer Targeting A Banking Example
Predictive Modelling for Customer Targeting A Banking Example Pedro Ecija Serrano 11 September 2017 Customer Targeting What is it? Why should I care? How do I do it? 11 September 2017 2 What Is Customer
More informationLittle Caesars Pizza
Trevor Builta STCM 315 Monday, November 6, 2017 Little Caesars Pizza IN THIS DOCUMENT I HAVE MADE SOME SUGGESTIONS AS TO HOW LITTLE CAESARS COULD EXPAND THEIR SOCIAL MEDIA AND BRAND. THERE ARE FIRST, THREE
More informationSigning up, managing your team and monitoring your team s progress is easy to do online.
Online Fundraising Signing up, managing your team and monitoring your team s progress is easy to do online. At marchforbabies.org you ll find everything you need to help your team succeed. In a case study
More informationMedia Kit 2015 BRINGS 'BUMPER OPPORTUNITIES! Australia s No.1 magazine FOR YOUNG HORSE LOVERS!
Australia s No.1 magazine FOR YOUNG HORSE LOVERS! Media Kit Because anyone who says, You should never work with kids or animals, simply doesn t know the meaning of FUN! 2015 BRINGS 'BUMPER OPPORTUNITIES!
More informationAlek Irvin
Social Media Audit This audit is to be viewed with: https://magic.piktochart.com/output/5164157-untitled-infographic. Introduction: Strategic use of social media channels is essential for any organization
More information2017 SOCIAL MEDIA BENCHMARK REPORT. Industry benchmarks across the most important social media metrics
2017 SOCIAL MEDIA BENCHMARK REPORT Industry benchmarks across the most important social media metrics INTRODUCTION There isn t a week that goes by when we don t have a brand ask how they compare against
More informationData Mining Applications with R
Data Mining Applications with R Yanchang Zhao Senior Data Miner, RDataMining.com, Australia Associate Professor, Yonghua Cen Nanjing University of Science and Technology, China AMSTERDAM BOSTON HEIDELBERG
More informationCopyr i g ht 2012, SAS Ins titut e Inc. All rights res er ve d. ENTERPRISE MINER: ANALYTICAL MODEL DEVELOPMENT
ENTERPRISE MINER: ANALYTICAL MODEL DEVELOPMENT ANALYTICAL MODEL DEVELOPMENT AGENDA Enterprise Miner: Analytical Model Development The session looks at: - Supervised and Unsupervised Modelling - Classification
More informationPredicting International Restaurant Success with Yelp
Predicting International Restaurant Success with Yelp Angela Kong 1, Vivian Nguyen 2, and Catherina Xu 3 Abstract In this project, we aim to identify the key features people in different countries look
More informationBest Practices. for Social Media Marketing Success
10 Best Practices for Social Media Marketing Success In the evolving world of social media marketing, it can be hard for a time-starved small business or organization to keep pace and know what to do when
More informationSOCIAL MEDIA. Facebook. Instagram. Twitter. Hashtags # Using Facebook, Twitter and Instagram to build your team!
SOCIAL MEDIA Using Facebook, Twitter and Instagram to build your team! Social Media is a great way to get the word out that you re fundraising for epilepsy. Here s a quick overview of the three different
More informationSocial Media Training
Social Media Training Media Training Outline Intro CWA Smartphone APP Union Social Media Social Media Theory Crafting a clear message Facebook Training Twitter Training Sign up for Twitter Using Social
More informationSEO & CONTENT MARKETING: A SPEED DATE
SEO & CONTENT MARKETING: A SPEED DATE EBOOK Oct 2017 www.castleford.com.au SEO & CONTENT MARKETING: A SPEED DATE Search engine optimisation (SEO) and content marketing have both had their moments in the
More informationPredicting Corporate Influence Cascades In Health Care Communities
Predicting Corporate Influence Cascades In Health Care Communities Shouzhong Shi, Chaudary Zeeshan Arif, Sarah Tran December 11, 2015 Part A Introduction The standard model of drug prescription choice
More informationPredicting the Future With Social Media
Predicting the Future With Social Media Sitaram Asur Social Computing Lab The Social Computing Lab focuses on methods for harvesting the collective intelligence of groups of people in order to realize
More informationNEWS RELEASES AND IMPROVE ROI REVENUE-GENERATING HOW TO OPTIMIZE STRATEGY. CHAPTER 1 Achieve Better Results with Targeted News Release Distribution
REVENUE-GENERATING NEWS RELEASES HOW TO OPTIMIZE STRATEGY AND IMPROVE ROI CHAPTER 1 Achieve Better Results with Targeted News Release Distribution 1 INTRODUCTION GET THE MOST OUT OF YOUR NEWS RELEASE Public
More informationUnveiling the Patterns of Video Tweeting: A Sina Weibo-based Measurement Study
Unveiling the Patterns of Video Tweeting: A Sina Weibo-based Measurement Study Zhida Guo 1, Jian Huang 1, Jian He 1, Xiaojun Hei 2, and Di Wu 1. 1 Sun Yat-sen University, China 2 Huazhong University of
More informationRank hotels on Expedia.com to maximize purchases
Rank hotels on Expedia.com to maximize purchases Nishith Khantal, Valentina Kroshilina, Deepak Maini December 14, 2013 1 Introduction For an online travel agency (OTA), matching users to hotel inventory
More informationTwitter. Runa Sarkar Indian Institute of Management Calcutta
Twitter Runa Sarkar Indian Institute of Management Calcutta What is it? A 140 character microblog that enables users to send and receive messages known as tweets A Tweet is an expression of a moment or
More informationI WANT TO START MY OWN USE-IT!
I WANT TO START MY OWN USE-IT! WHAT IS USE-IT? WHAT IS USE-IT? USE-IT is the quality label for no-nonsense tourist info for young people. USE-IT initiatives currently exist in 40 cities in Europe. They
More informationRadian6 Overview What is Radian6?... 1 How Can You Use Radian6? Next Steps... 9
Radian6 Overview What is Radian6?... 1 How Can You Use Radian6?... 6 Next Steps... 6 Set up Your Topic Profile Topic Profile Overview... 7 Determine Your Keywords... 8 Next Steps... 9 Getting Started Set
More informationSocial MEDIA in the hospitality
Social MEDIA in the hospitality and leisure industry foreword We are delighted to share with you the insights from our survey undertaken across Senior Executives in the hospitality and leisure sector.
More informationDetermining NDMA Formation During Disinfection Using Treatment Parameters Introduction Water disinfection was one of the biggest turning points for
Determining NDMA Formation During Disinfection Using Treatment Parameters Introduction Water disinfection was one of the biggest turning points for human health in the past two centuries. Adding chlorine
More informationStream-based active learning for sentiment analysis in the financial domain
Stream-based active learning for sentiment analysis in the financial domain Jasmina Smailović 1,2, Miha Grčar 1,2, Nada Lavrač 1,2,3, Martin Žnidaršič 1,2 1 Jožef Stefan Institute, Jamova 39, 1000 Ljubljana,
More informationDETECTING COMMUNITIES BY SENTIMENT ANALYSIS
DETECTING COMMUNITIES BY SENTIMENT ANALYSIS OF CONTROVERSIAL TOPICS SBP-BRiMS 2016 Kangwon Seo 1, Rong Pan 1, & Aleksey Panasyuk 2 1 Arizona State University 2 Air Force Research Lab July 1, 2016 OUTLINE
More informationLumière. A Smart Review Analysis Engine. Ruchi Asthana Nathaniel Brennan Zhe Wang
Lumière A Smart Review Analysis Engine Ruchi Asthana Nathaniel Brennan Zhe Wang Purpose A rapid increase in Internet users along with the growing power of online reviews has given birth to fields like
More informationDean College Social Media Handbook
Dean College Social Media Handbook Goals of this Handbook To help Dean College employees and groups engage with social media in constructive and fun ways while contributing to the overall goals of the
More informationText Mining. Theory and Applications Anurag Nagar
Text Mining Theory and Applications Anurag Nagar Topics Introduction What is Text Mining Features of Text Document Representation Vector Space Model Document Similarities Document Classification and Clustering
More informationSECRETS TO BOOST YOUR
SECRETS TO BOOST YOUR OFFER ACCEPTANCE RATES newtonsoftware.com sales@newtonsoftware.com 415-593-1190 TABLE OF CONTENTS 3 Introduction 4 The Intake 5 The Pre-close 6 The Verbal Offer 7 The Written Offer
More informationThere are many ways to use Twitter, but you want to use it in the most
twitter Chapter 6 Aligning Your Twitter Strategy with Your Business There are many ways to use Twitter, but you want to use it in the most efficient, effective way to grow your business. Like all social
More informationSOCIAL MEDIA TOOLKIT FOR NONPROFITS
SOCIAL MEDIA TOOLKIT FOR NONPROFITS OVERVIEW OF SOCIAL MEDIA ------------------------------------------------------2 GIVE LOCAL YORK S SOCIAL MEDIA ACCOUNTS-------------------------------------3 USING
More informationSOCIAL MEDIA GLOSSARY General terms
SOCIAL MEDIA GLOSSARY General terms API Application programming interface: Specifies how software components interact. On the web, APIs allow content to be embedded and shared between locations (it s a
More informationInsights Partners Overview
Insights Partners Overview Radian6 Partners Enhanced Demographics In-Depth Sentiment Analysis Understand Intention Discover Trends and Emerging Issues Find Online Influencers Table of Contents Social Media
More informationHOST REWARDS. Step 1 - Create your Presentation Step 2 - Invite Guests Step 3 - Enter Orders Step 4 - Redeem Rewards. Virtual Guests.
We are thrilled to bring you a simplified Host Rewards Program that includes an exciting element we are calling the Virtual Guest. This is designed to help you reach more guests, create more orders and
More informationVideo Traffic Classification
Video Traffic Classification A Machine Learning approach with Packet Based Features using Support Vector Machine Videotrafikklassificering En Maskininlärningslösning med Paketbasereade Features och Supportvektormaskin
More informationOnline Tools. For Intelligence Work. 29 tried and tested ways to explore digital open sources. Updated December 2016.
Online Tools For Intelligence Work 29 tried and tested ways to explore digital open sources. Updated December 2016. www.intelligence-training.com Copyright Atlas Intelligence Training, December 2016 Welcome
More informationPredictive Analytics Using Support Vector Machine
International Journal for Modern Trends in Science and Technology Volume: 03, Special Issue No: 02, March 2017 ISSN: 2455-3778 http://www.ijmtst.com Predictive Analytics Using Support Vector Machine Ch.Sai
More information8 Ways To Build Your Brand Using Social Media
TIP SHEET 8 Ways To Build Your Brand Using Social Media TABLE OF CONTENTS: 03 04 04 05 05 06 06 07 07 08 Intro Tip 1 - Determine Goals for Your Social Media Engagement Tip 2 - Determine Your Online Brand
More informationPage 1 of 29
Page 1 of 29 Contents Introduction....page. 2 The Simple 5 Step System....page. 4 Step 1 - Look for people that have the ability and are willing to promote what we are offering to a big audience QUICKLY...page.
More informationHow to Increase Clicks Using Social Media Advertising. Ashley Ward CEO & Social Media Director Madhouse Marketing
How to Increase Clicks Using Social Media Advertising Ashley Ward CEO & Social Media Director Madhouse Marketing Ashley Who? Background: Social Media Social Media Advertising CEO IPA Enthusiast www.madhouse.marketing
More informationPERSONAL BRANDING SOCIAL SELLING NOT FOR PUBLICATION - PROPERTY OF GAIL MERCER-MACKAY
PERSONAL BRANDING SOCIAL SELLING WELCOME BACK Managing your digital footprint Pictures & words Marathon, not a sprint Define your brand LinkedIn and Twitter WHAT YOU LEARNED Coming up with 'key' descriptive
More informationSunnie Chung. Cleveland State University
Sunnie Chung Cleveland State University Data Scientist Big Data Processing Data Mining 2 INTERSECT of Computer Scientists and Statisticians with Knowledge of Data Mining AND Big data Processing Skills:
More informationFrom Tweets to Polls: Linking Text Sentiment to Public Opinion Time Series
From Tweets to Polls: Linking Text Sentiment to Public Brendan O Connor Opinion Time Series Machine Learning Department Carnegie Mellon University http://brenocon.com Presentation at AAPOR, May 2012 Joint
More informationFive trends in Capacity Management
Five trends in Capacity Management Planning ahead to meet business requirements and SLAs while managing: When we look at capacity management today there are a lot of challenges out there. We typically
More informationBig Data and Automotive IT. Michael Cafarella University of Michigan September 11, 2013
Big Data and Automotive IT Michael Cafarella University of Michigan September 11, 2013 A Banner Year for Big Data 2 Big Data Who knows what it means anymore? Big Data Who knows what it means anymore? Associated
More information5 Great Reasons to Start Using Sendible
5 Great Reasons to Start Using Sendible Sendible is an online marketing service for businesses and marketers to promote, grow and track their brands through the use of Social Media, Email and SMS messaging.
More informationHow To Get Leads. The Complete Guide to a Fully Integrated B2C Social Media Program. Brought to you by
How To Get Leads (And REVENUE) From Social Media The Complete Guide to a Fully Integrated B2C Social Media Program Brought to you by So you ve heard talk about this social media thing, but maybe your take
More information