Social Media Analytics: Techniques and Insights for Extracting Business Value Out of Social Media / Edition 1

by Matthew Ganis, Avinash Kohirkar

Overview

Transform Raw Social Media Data into Real Competitive Advantage

There’s real competitive advantage buried in today’s deluge of social media data. If you know how to analyze it, you can increase your relevance to customers, establishing yourself as a trusted supplier in a cutthroat environment where consumers rely more than ever on “public opinion” about your products, services, and experiences.

Social Media Analytics is the complete insider’s guide for all executives and marketing analysts who want to answer mission-critical questions and maximize the business value of their social media data. Two leaders of IBM’s pioneering Social Media Analysis Initiative offer thorough and practical coverage of the entire process: identifying the right unstructured data, analyzing it, and interpreting and acting on the knowledge you gain.

Their expert guidance, practical tools, and detailed examples will help you learn more from all your social media conversations, and avoid pitfalls that can lead to costly mistakes.

You’ll learn how to:

• Focus on the questions that social media data can realistically answer
• Determine which information is actually useful to you—and which isn’t
• Cleanse data to find and remove inaccuracies
• Create data models that accurately represent your data and lead to more useful answers
• Use historical data to validate hypotheses faster, so you don’t waste time
• Identify trends and use them to improve predictions
• Drive value “on-the-fly” from real-time/ near-real-time and ad hoc analyses
• Analyze text, a.k.a. “data at rest”
• Recognize subtle interrelationships that impact business performance
• Improve the accuracy of your sentiment analyses
• Determine eminence, and distinguish “talkers” from true influencers
• Optimize decisions about marketing and advertising spend

Whether you’re a marketer, analyst, manager, or technologist, you’ll learn how to use social media data to compete more effectively, respond more rapidly, predict more successfully…grow profits, and keep them growing.

Product Details

ISBN-13:	9780133892567
Publisher:	IBM Press
Publication date:	12/25/2015
Series:	IBM Press Series
Edition description:	New Edition
Pages:	304
Product dimensions:	6.00(w) x 8.90(h) x 0.70(d)

About the Author

Dr. Matthew Ganis, a member of IBM’s Academy of Technology, is currently an IBM Senior Technical Staff Member located in Somers, New York. His current areas of interest include social media analytics, the Internet of Things, and Agile software methodologies. He is an adjunct professor of computer science and astronomy at Pace University in Pleasantville, New York, where he teaches at both the undergraduate and graduate level.

Dr. Ganis holds a BS degree in computer science and an MBA in information systems from Pace University, an MS degree in astronomy from the University of Western Sydney, Australia, and a doctorate of professional studies in computing from Pace University. He has authored or co-authored over 40 papers in both of his fields of interest, ranging from programming techniques, computer system administration, computer networking, and topics on stellar evolution and radio astronomy. He is also the proud coauthor of A Practical Guide to Distributed Scrum published by IBM Press.

In his 30-year career at IBM, he has been responsible for a number of technological advances such as the creation of the first enterprise firewalls for IBM; the creation of highly available World Wide Web platforms to support the Atlanta, Sydney, and Nagano Olympics (which secured Dr. Ganis and his team a spot in the Guinness Book of World Records for the highest sustained rate of Internet web traffic); and the proliferation of advanced software development techniques across IBM’s worldwide development laboratories.

He can be found on LinkedIn (https://www.linkedin.com/in/mattganis), on Twitter as @mattganis, or on his blog at http://mganis.blogspot.com.

Avinash Kohirkar is currently Manager of Social Business Adoption in IBM. His current areas of interest include deployment and adoption of social technologies within an enterprise, social engagement dashboards, and social media analytics. Avinash Kohirkar holds a BS degree in electronics and communications engineering from Osmania University (India), an MS degree in industrial engineering from NITIE (India), and an MBA in finance from California State University. He has contributed to IBM white papers and has given numerous presentations on social analytics in IBM and outside IBM. He has authored a number of articles on this subject that have been published in the Cutter IT Journal and Infosys Lab Briefings.

In his 19-year career at IBM, he has leveraged technologies such as e-business, Web 2.0, social collaboration, social graph technologies, big data, and social media and text analytics for the business benefit of IBM and IBM’s customers. He is recognized as a thought leader in the project management profession within IBM and is certified as Executive Project Manager at the highest level within IBM. He has held several technical, business, and management positions during his career: Architect, Development Manager, Project Manager, Project Executive, Associate Partner, Project Executive, and Business Manager.

He can be found on LinkedIn (https://www.linkedin.com/in/ AvinashKohirkar) and on Twitter as @kohirkar.

Table of Contents

Foreword xviii

Preface: Mining for Gold (or Digging in the Mud) xx

Just What Do We Mean When We Say Social Media? xx

Why Look at This Data? xxi

How Does This Translate into Business Value? xxii

The Book’s Approach xxiv

Data Identification xxiv

Data Analysis xxv

Information Interpretation xxvi

Why You Should Read This Book xxvii

What This Book Does and Does Not Focus On xxix

Acknowledgments xxxi

Matt Ganis xxxi

Avinash Kohirkar xxxi

Joint Acknowledgments xxxii

About the Authors xxxiv

Part I: Data Identification

Chapter 1: Looking for Data in All the Right Places 1

What Data Do We Mean? 2

What Subset of Content Are We Interested In? 4

Whose Comments Are We Interested In? 6

What Window of Time Are We Interested In? 7

Attributes of Data That Need to Be Considered 7

Structure 8

Language 9

Region 9

Type of Content 10

Venue 13

Time 14

Ownership of Data 14

Summary 15

Chapter 2: Separating the Wheat from the Chaff 17

It All Starts with Data 18

Casting a Net 19

Regular Expressions 23

A Few Words of Caution 27

It’s Not What You Say but WHERE You Say It 28

Summary 29

Chapter 3: Whose Comments Are We Interested In? 31

Looking for the Right Subset of People 32

Employment 32

Sentiment 32

Location or Geography 33

Language 33

Age 34

Gender 34

Profession/Expertise 34

Eminence or Popularity 35

Role 35

Specific People or Groups 35

Do We Really Want ALL the Comments? 35

Are They Happy or Unhappy? 37

Location and Language 39

Age and Gender 41

Eminence, Prestige, or Popularity 42

Summary 45

Chapter 4: Timing Is Everything 47

Predictive Versus Descriptive 48

Predictive Analytics 49

Descriptive Analytics 53

Sentiment 55

Time as Your Friend 57

Summary 58

Chapter 5: Social Data: Where and Why 61

Structured Data Versus Unstructured Data 63

Big Data 65

Social Media as Big Data 67

Where to Look for Big Data 69

Paradox of Choice: Sifting Through Big Data 70

Identifying Data in Social Media Outlets 74

Professional Networking Sites 75

Social Sites 77

Information Sharing Sites 78

Microblogging Sites 79

Blogs/Wikis 80

Summary 81

Part II: Data Analysis

Chapter 6: The Right Tool for the Right Job 83

The Four Dimensions of Analysis Taxonomy 84

Depth of Analysis 85

Machine Capacity 86

Domain of Analysis 88

External Social Media 88

Internal Social Media 93

Velocity of Data 99

Data in Motion 99

Data at Rest 100

Summary 101

Chapter 7: Reading Tea Leaves: Discovering Themes, Topics, or Trends 103

Validating the Hypothesis 104

Youth Unemployment 104

Cannes Lions 2013 110

56th Grammy Awards 112

Discovering Themes and Topics 113

Business Value of Projects 114

Analysis of the Information in the Business Value

Field 115

Our Findings 115

Using Iterative Methods 117

Summary 119

Chapter 8: Fishing in a Fast-Flowing River 121

Is There Value in Real Time? 122

Real Time Versus Near Real Time 123

Forewarned Is Forearmed 125

Stream Computing 126

IBM InfoSphere Streams 128

SPL Applications 129

Directed Graphs 130

Streams Example: SSM 131

Step 1 133

Step 2 134

Step 3 134

Step 4 135

Steps 5 and 6 136

Steps 7 and 8 136

Value Derived from a Conference Using Real-Time

Analytics 138

Summary 139

Chapter 9: If You Don’t Know What You Want, You Just May Find It!: Ad Hoc Exploration 141

Ad Hoc Analysis 142

An Example of Ad Hoc Analysis 144

Data Integrity 150

Summary 155

Chapter 10: Rivers Run Deep: Deep Analysis 157

Responding to Leads Identified in Social Media 157

Identifying Leads 158

Qualifying/Classifying Leads 160

Suggested Action 161

Support for Deep Analysis in Analytics Software 163

Topic Evolution 163

Affinity Analysis in Reporting 165

Summary 167

Chapter 11: The Enterprise Social Network 169

Social Is Much More Than Just Collaboration 170

Transparency of Communication 171

Frictionless Redistribution of Knowledge 172

Deconstructing Knowledge Creation 172

Serendipitous Discovery and Innovation 172

Enterprise Social Network Is the Memory of the Organization 172

Understanding the Enterprise Graph 174

Personal Social Dashboard: Details of Implementation 175

Key Performance Indicators (KPIs) 177

Assessing Business Benefits from Social Graph Data 183

What’s Next for the Enterprise Graph? 185

Summary 186

Part III: Information Interpretation

Chapter 12: Murphy Was Right! The Art of What Could Go Wrong 189

Recap: The Social Analytics Process 190

Finding the Right Data 193

Communicating Clearly 195

Choosing Filter Words Carefully 198

Understanding That Sometimes Less Is More 198

Customizing and Modifying Tools 201

Using the Right Tool for the Right Job 204

Analyzing Consumer Reaction During Hurricane Sandy 204

Summary 209

Chapter 13: Visualization as an Aid to Analytics 211

Common Visualizations 212

Pie Charts 213

Bar Charts 214

Line Charts 216

Scatter Plots 218

Common Pitfalls 219

Information Overload 219

The Unintended Consequences of Using 3D 220

Using Too Much Color 221

Visually Representing Unstructured Data 222

Summary 225

Appendices

Appendix A: Case Study 227

Introduction to the Case Study: IBMAmplify 228

Data Identification 228

Taking a First Pass at the Analysis 234

Data Analysis 241

A Second Attempt at Analyzing the Data 243

Information Interpretation 244

Conclusions 247

Index 249