Contenu connexe Similaire à The Next Generation of Social Listening Intelligence (20) The Next Generation of Social Listening Intelligence1. © 2014 Converseon Inc. Proprietary and Confidential
The Next Generation of Social Intelligence
Advertising Research Foundation Re:Think
March 14, 2016
Rob Key, CEO, Converseon
2. © 2014 Converseon Inc. Proprietary and Confidential 2
Our Mission:
To Provide the World’s Best Social
Insights and Help Integrate Them into
our Clients’ Organizations to
Take Meaningful Action
3. © 2014 Converseon Inc. Proprietary and Confidential
The Dirty Secrets of Social Listening (to date)
3
“Far from being
unfixable, however,
miscalculations in
social-media
analyses can already
be fixed using
methods developed
to fix similar
problems in studies
in epidemiology,
statistics and
machine learning.”
- ComputerWorld
4. © 2014 Converseon Inc. Proprietary and Confidential 4
Reasons: Booleans Ineffective
("enterprise 2.0" OR "Social Biz" OR "social business" OR "#SocBiz" OR "#SocialBiz" OR "#socialbusiness" OR SocBiz
OR SocialBiz OR socialbusiness OR "enterprise social business" OR "enterprise social network" OR "enterprise social
grid" OR "social CRM" OR "social BPM") AND ("activity stream" OR "activity streams" OR "application development"
OR "best practices" OR "business model" OR "business models" OR "content management" OR "crowd sourcing" OR
"customer service" OR "disruptive technologies" OR "disruptive technology" OR "human resources" OR "information
technology" OR "next generation social" OR "open social" OR "organizational culture" OR "predictive analytics" OR
"product lifecycle management" OR "social analytics" OR "social mail" OR "social portal" OR "social portals" OR
"social commerce" OR "customer experience management" OR "innovation management" OR "social app" OR "social
application" OR "social applications" OR "social apps" OR "social business app" OR "social business application" OR
"social business applications" OR "social business apps" OR "social collaboration" OR "social computing" OR "social
learning" OR "social media" OR "social network" OR "social networks" OR "social platform" OR "social platforms" OR
"social software" OR "social softwares" OR "social technologies" OR "social technology" OR "soft ware" OR "tool kit"
OR "unified telephony" OR "analytics" OR "app" OR "application" OR "applications" OR "apps" OR "benefit" OR
"benefits" OR "blog" OR "blogs" OR "bookmark" OR "bookmarks" OR "BPM" OR "collaboration" OR "collaborative"
OR "commerce" OR "communication" OR "communities" OR "community" OR "compliance" OR "innovation" OR
"connection" OR "connections" OR "CRM" OR "crowdsourcing" OR "engagement" OR "ERM" OR "information" OR
"intelligence" OR "intelligent" OR "interaction" OR "interactive" OR "internet" OR "interoperability" OR "learning" OR
"mail" OR "marketing" OR "mobile" OR "network" OR "nimble" OR "optimization" OR "optimized" OR "organization"
OR "organizational" OR "organizations" OR "platform" OR "platforms" OR "portal" OR "portals" OR "productive" OR
"productivity" OR "risk" OR "risks" OR "sales" OR "software" OR "softwares" OR "technologies" OR "technology" OR
"tool" OR "toolkit" OR "tools" OR "transparency" OR "transparent" OR "value" OR "voIP" OR "wiki" OR "collective
intelligence" OR "customer self service" OR "social grid" OR "content" OR "social content" OR "insights" OR "social
selling" OR "social communications" OR "collaborative communications" OR "human capital management" OR
"business process management" OR "enterprise resource management" OR "enterprise resource planning")
15% Relevancy
5. © 2014 Converseon Inc. Proprietary and Confidential
• Is this tweet positive or negative?
• It depends on whether you work for Verizon or Sprint
• Often, your viewpoint is what makes something positive or negative, but most text
analytics systems are not up to the challenge
Reasons: Listening Tools Have Lacked Context
6. © 2014 Converseon Inc. Proprietary and Confidential
The same words mean different things
• An “unpredictable” movie is good, but
“unpredictable” braking, not so much
• We like “small” cell phones but not “small”
legroom
• “Faded” jeans are good, but
not “faded” interiors
And Taken a “One Size Fits All” Approach
Your industry has its own
lexicon
7. © 2014 Converseon Inc. Proprietary and Confidential 7
It’s Simple Math
60% (precision) x 15% Relevancy X Low “Recall” = Problems
9. © 2014 Converseon Inc. Proprietary and Confidential 9
New Deep/Machine Learning Approaches Unlocking Insights
Knowledge
-based
Resources
Machine
Learning
System
Test
Data
Training
Data/
Libraries
Semi Supervision: Keeps “humans in the loop”
for continuous training
Customizable: Trains to domain and brands
(“small” may be good for selling smartphones,
bad for hotel rooms)
Accurate: Close approximation of human
performance at scale (humans that agree with
each other) – generally 90-95%
Scalable: Now allows the accuracy of human
coding at large scale and speed
Vertical and Brand/Domain Specific
Custom Classifiers: Enables unlimited number
of custom classifiers (intent, purchase phase,
etc.)
Vertical and brand specific
High Relevancy and Recall: Isolates key data
sets rapidly and at most detailed level.
Data approach as represented by
Converseon’s ConveyAPI technology
10. © 2014 Converseon Inc. Proprietary and Confidential
• Relevance feedback allows you to be in control
• 85% accurate
with less than
one hour’s work vs 15% by
boolean
No More Booleans
11. © 2012 Converseon Inc. Proprietary and Confidential 11
High Recall, Precision, Relevancy Example
negative
4%
neutral
15%
positive
81%
Cool Whip Sentiment:
Convey
negative
3%
neutral
84%
positive
13%
Cool Whip Sentiment:
Industry Standard
Industry standard sentiment analysis for Cool Whip over-indexes neutral, failing to
represent true consumer opinions of the brand and identify brand advocates:
Industry Standard Convey
Sentiment Precision 38% 83%
Relevancy 46% 91%
12. © 2014 Converseon Inc. Proprietary and Confidential
High Recall: Entity (Facet) Level Analysis
12
13. © 2014 Converseon Inc. Proprietary and Confidential
• It had a slightly buttery off-note
• I disliked the aftertaste
• The taste was decidedly foul
• I would never eat this again
• The taste of it turned my stomach
• This the worst tasting #@&*% ever
New Metrics: Intensity
14. © 2012 Converseon Inc. Proprietary and Confidential 14
New Metrics: Emotion and Intensity Analysis
Example
Emotion analysis reveals the insight that Thanksgiving is when consumers turn to social media
to share their feelings about Cool Whip, associating it directly with the joy of Thanksgiving
dinner with family
N/A
Low
Intensity
Medium
Intensity
High
Intensity
joy
10%
45%
28%
14%
disgust
0%
1%
1%
0%
anticipation
0%
1%
0%
0%
anger
0%
0.1%
0.3%
0.1%
sadness
0%
0.1%
0.1%
0%
trust
0%
0%
0%
0%
surprise
0%
0%
0%
0%
fear
0%
0%
0%
0%
0 200 400 600
Oct
Nov
Dec
Jan
Feb
Mar
Apr
May
Jun
Jul
Aug
Sep
Oct
Monthly Expressions of Joy in
Mentions about eating Cool Whip
20142015
Emotion and Intensity in Messages
about Eating Cool Whip
“I'm so excited for
thanksgiving just for
pumpkin pie. With a giant
tub of cool whip. And
some apple cider. Maybe
with a side of turkey.”
Source: Converseon analysis of public online records, November 2015.
15. © 2014 Converseon Inc. Proprietary and Confidential 15
Custom Classifiers Unlock Deeper Insight and Facilitate
Organizational Adoption
Advocacy
Brand
Champions
Product
Adoption
Fact / Opinion
Product
Applications
Brand
Personality
Purchase
Intent
Purchase
Stage
Sentiment
Technology allows an unlimited number custom classifiers
16. © 2014 Converseon Inc. Proprietary and Confidential
5%
17%
11%
35%
17%
11%
12%
6%
0%
25%
50%
75%
100%
Customer Journey Analysis Example
Smartphone
Category
11%
14%
13%
19%
54%
35%
14%
22%
41%
14%
22%
42%
42%
27%
0%
25%
50%
75%
100%
Fear
Distrac>on
Apprehension
Pensiveness
Acceptance
Trust
Serenity
Surprise
Interest
Sadness
Annoyance
Disgust
Anger
An>cipa>on
Joy
Mul>ple
Categories
Emotions in the Purchase Funnel
17. © 2015 Converseon Inc. Proprietary and Confidential 17
New Metrics: Audience Analysis
WOMEN make up 70%
of Cool Whip Advocates
80% of Cool Whip
Advocates are WHITE
0% 8%
73%
18%
1%
13-17 18-24 25-34 35-44 45+
White
79%
Black
16%
Hispanic
4%
73% of Advocates
are aged 25-34
Food 58%
Religion 58%
Beverages 49%
Humor 49%
Nutrition 41%
Parenting 39%
Fitness 39%
School Life 38%
Health Care 38%
Family 37%
Cool Whip Advocates are
interested in FOOD,
FAMILY LIFE, and HEALTH
@AshleyKfit Ashley Kaltwasser
Athlete
Top interests: Fitness, Multimedia, Travel
@how2girl Courtney Sixx
Model and step-mother
Top interests: Fashion, Family, Charity
@manwhohasitall
Comedian and father
Top interests: Parenting, Nutrition, Beauty
Top Advocate Influencers
are minor celebrities –
comedian, model, athlete
18. © 2014 Converseon Inc. Proprietary and Confidential
Multiple Peer Reviewed Studies Have Shown Predictive
Capabilities of Convey-Powered Data
18
Professor Wendy Moe and David Schweidel, conducted
analysis of social conversation versus offline brand tracking
using Converseon data.
.
New WOMM Media Mixed Modeling
Study (utilizing Converseon data)
95% precision + 85% Relevancy +
High Recall
19. © 2014 Converseon Inc. Proprietary and Confidential
And is Enabling Mainstreaming and Integration
19
Business
Outcomes
Brand Equity
(Brand Preference &
Advocacy)
Sales / Share Outcomes
Meaning &
Engagement
Meaning
(Language, Attributes,
Culture, Consumer
Interest Profiles)
Engagement
Behaviors
(Community Size &
Behavior Toward
Brand)
Purchase
Disposition
(Path to purchase)
Marketing
Effectiveness
Spending
Impressions
(Amplification via Paid,
Owned vs. Earned)
Return
(Marketing Return on
Investment)
Social Inputs/
Classifiers:
Brand Equity: Consumer preference + advocacy; Social NPS (actual advocating versus intent)
Brand Meaning: language, topics, emotions, imagery, opinions, perceptions
Engagement Behaviors: Interacting with brand beyond functional purpose. (likes, retweets, etc.)
Purchase: Purchase funnel analysis; intent to buy
20. © 2014 Converseon Inc. Proprietary and Confidential
…Across Organizations
Product Launch, Unmet Needs,
Segmentation, Outliers, etc
Brand Tracking
Innovation
Customer Journey/Advocay
Advanced
Enrichment
21. © 2014 Converseon Inc. Proprietary and Confidential
How to Access….
21
• If you have an application in need of social data, it is available
through a ConveyAPI REST API
• For basic listening, it is available in Conversation Monitor
• Also available through growing number of ecosystem
partners
• Converseon provides a full range of research and
consulting products to clients looking for turnkey solutions
22. © 2014 Converseon Inc. Proprietary and Confidential 22
Introducing Conversus™: DIY
Works as
stand alone or
in conjunction
with most
basic listening
platforms for
enhanced
listening,
intelligence
and
integration
23. © 2014 Converseon Inc. Proprietary and Confidential
Final Thoughts: Social Intelligence in 2016
23
ü Pervasive data layer, not application specific (APIs)
ü Interoperable with legacy systems
ü Accurate and predictive
ü Domain and brand adaptable
ü The rise of custom classifiers
ü Integrated with other Voice of Customer intelligence
ü Brand tracking, market mixed modeling, business intelligence and more
ü Integrated
24. © 2014 Converseon Inc. Proprietary and Confidential
Thank You
rkey@converseon.com
@robkey
24