social listening and intelligence is predictive! now what?
TRANSCRIPT
Social Data is Predictive! Now What?
Rob Key
CEO, Converseon
@robkey
A Legacy of Top Data Quality, Research and Consulting
Award winning Social Consultancy working exclusively
in social media since 2001
Widely recognized for “best data quality” from leading
analysts via its award-winning proprietary Convey
technology (Gartner, Forrester).
Converseon provides the tools, data, models,
research, consulting to help drive actionable social
intelligence throughout organizations.
“Strong Performer’ in The Forrester Wave™:
Enterprise Social Listening Platforms Q1 2014. Top
overall score (5 out of 5) for consulting and research,
as well as data processing and sentiment analysis
(tied).
Dataweek Top Innovator in Social Data Mining for its
ability to “provide near human level precision at the
speed and scale that only software can achieve.”
Copyright Converseon 2014
Though social and digital media are rapidly
transforming marketing and new tools
emerge daily, in most firms the organization
of the function hasn't changed in 40 years.
How should marketers revamp…to meet
the new realities?
- The Ultimate Marketing Machine
by Marc de Swaan Arons, Frank van den
Driest, Keith Weed
Source: Harvard Business Review
Publication Date: Jul 01, 2014.
Social is a Game Changer
“
”
Listening 1.0: Who Offers a Tool?
Ascent Labs, Inc. Attensity Attentio Backtype Betaworks Bivings Group Biz360 Inc. Brands Eye Brandtology Brandwatch BuzzGain Buzzient BuzzLogic BuzzNumbers BuzzStream Cierzo Development S.L Cision Collecta Collective Intellect Converseon Conversition CoTweet Crimson Hexagon Crowd Favorite CustomScoop Digimind DNA13 Dow Jones eCairn e-CBD Echometrix Effyis Emerge Technology Group Expert System Facebook Filtrbox Flaptor Frank Westphal Glam Media Google Hubspot Icerocket iMooty Infegy Inifinimedia Insttant Inuda Innovations Iterasi JamIQ JD Power Kaleidico Klout Linkfluence ListenLogic Macranet Market Sentinel MediaBadger MediaMiser Medimix Mindlab Solutions GmbH Monitter Moreover Technologies mReplay MyFrontSteps Networked Insights New Media Strategies Nielsen Now Metrix Onalytica OneRiot Overdrive Interactive Overtone Pidgin Technologies PR Newswire Radian6 Raven Rees Bradley Hepburn Ltd RepuMetrix Reputation Defender ReputationHQ Samepoint ScoutLabs Sensidea Social Mention SocialMetrix Spiral16 Sports Media Challenge StatsIT StreamWall SWIX Synthesio Sysomos Tealium Technorati Techrigy The Search Monitor ThoughtBuzz TipTop Technologies TNS Cymfony TraceBuzz Trackur LLC. Twazzup TweetBeep Tweetlytics Twitter Twitter Analyzer uberVU Viralheat Visible Measures Visible Technologies Vocus, Inc. Web Analytics Demystified White Noise Inc. Who's Talkin Xerocity Design Group YackTrack … and more
Source: http://wiki.kenburbary.com/social-meda-monitoring-wiki
But Most Of Them Are The Same
Enter your keyword or boolean query into the tool, it searches its list of feeds and then you generally get back charts and tables showing:
1. Volume (of you, your competitors, your category)
2. Venues/Authors
3. General topics
4. Automated influence
5. Basic sentiment
That seems pretty easy, right?
It can be, if all you want to really know is what are people saying about be right now?
Dirty Secret of Most Social Data
6
Current State:
Imprecise –
average sentiment
accuracy is 60%
Analyst bias
Data quality remains an issue. When asked about their satisfaction with general data quality, 74% of respondents
reported positive results. But when we dug deeper and asked about the specifics of the data, many changed their
tunes. In fact, the five responses showing the most dissatisfaction all centered on data: the ability to weed out spam;
the accuracy of the tool’s automated sentiment analysis; influencer identification tools; multilingual and international
capabilities; and the tool’s integration capabilities. These data challenges make a direct call to CI teams to get
involved and bring their past data management experience to the table.
– Forrester Research
“
”
No sample frame
“One size fits all”
“Same old metrics”
High irrelevancy
Don’t know who is speaking
“Garbage in, garbage out”
7
The truth is that for too long, much of social data has been a “coin flip”
Greater insights must begin with better data
Bad Data = False Conclusions
Recently, Researchers at CMU and McGill Recently recognized the issue
9
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
But they also recognized the solution
“
”
Yet Many Market Researchers Are Relying on these Monitoring Tools for Insights
The Next Generation: Precise, Meaningful and Predictive
12
1. Improve Precision, Relevancy and Recall (and Set Standards)
Custom enrichment and
tuning to the brand / product
Custom classifiers
Standard classifiers
2. Move Away From Booleans
13
Machine learning
Custom Classifier
raised relevancy to
85% in less than an
hour
The best boolean query using a leading social monitoring
platform achieved only 15% relevancy
3. Know Who’s Talking
1
• Compiles a comprehensive view of an individual’s
digital footprint across online personas
• Analyzes all public content that an individual has
posted via social media channels
• Understands the type of conversations a particular
person is having publicly online
• Identifies the public venues where an individual
engages
• Understands the interests and life events of customers
and prospects, driving more effective engagement
• Maps network connections
• Helps sampling frame by matching social media
profiles to known populations from customer lists
Build robust views of your audience
by stitching open social data to client
operational data (e.g. customer
databases) as well as fans /
followers of owned social pages
Dissects & classifies your
audience(s) across demographic,
psychographic, sentiment & intent to
identify and extend vital personas
Turns audience and topic data into
prescriptive messages to activate
audiences through more targeted
engagement, offers & services
IDENTIFY SEGMENT TARGET
Who is my audience? What are their interests? How do I engage them?
Our technology also automates the collection / analysis of social
profile data to help activate high-value segments
1
4. Build and Apply Custom Classifiers
Fact / Opinion Product Application Consumer Intent
Brand Personality Product Adoption Brand Champions
Purchase Stage
Sentiment
Demand Gen Cycle
5. Embrace Emotion
11% 14% 13%19%
54%35%
14%22%
41%
14%
22% 42%42%
27%
0%
25%
50%
75%
100%
Problem Recognition Information Search Competitive Evaluation Purchase Decision Post- Purchase
Fear
Distraction
Apprehension
Pensiveness
Acceptance
Trust
Serenity
Surprise
Interest
Sadness
Annoyance
Disgust
Anger
Anticipation
Joy
New classifiers unlock deeper, more
actionable insights such as those
Based on Plutchik’s Wheel of Emotion
1
ConveyAPI via Converseon
Knowledge
-based
Resources
Machine
Learning
SystemTest
Data
Training
Data
• 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
• Future proof: Continually evolves as language evolves
• Custom Classifiers: Enables unlimited number of custom classifiers (intent, purchase phase, etc.)
• High Relevancy and Recall: Isolates key data sets rapidly and at most detailed level.
Dataweek Top Innovator in Social Data Mining.
Proven and validated predictive capabilities
Social Data is Now Predictive: Example 1
Converseon, in partnership with Professor Wendy
Moe and David Schweidel, conducted analysis of
social conversation versus offline brand tracking
Simple average sentiment scoring using regression
analysis showed almost no correlation (.002)
But after cleansing the conversation of offers,
advertising and other clutter, and applying weighting
to the conversation based on influencer and venue,
the researchers were able to find a strong correlation
of .604
Example 2: WOMMA Study
• ,
Conducted by Analytic PartnersIn partnership with Converseon
And Keller Fay
We are at the beginning of a new era
2
Characteristics
Limited Complexity
Free tools
Experimental
People working in
their spare time
“Dictionary Based”
Easy to understand
Difficult to expand to different
languages
Directional
Declarative
Heuristic
Qualitative
Siloed
Higher precision
Embraces language
evolution
Domain specific
Trainable
Adaptable
Customizable
Quantitative/Predictive
Integrated
Modeled
Enterprise
Business Intelligence
Marketing Mix Modeling
Brand Tracking
Product Development, etc.
ExperimentalBusiness Value
“Rules Based” NLP + Machine Learning
Reactive/Limited
Crisis Comm
PR
Campaign tracking
Precision
Recall
Relevancy
Word spotting
2015
Predictive & Quantitative
Reactive & Qualitative
Business Value
Where we Can Now Mainstream Social Data
Campaign Planning/Performance, Unmet Needs,
Segmentation, Outliers, etc
Brand Tracking Innovation
Marketing Mixed Modeling
Advanced
Enrichment
Parting Thoughts
• New technologies and models are creating breakthrough results
• It’s the big picture but also the small (people) level
• Leading brands are indeed beginning to truly mainstream this data across the organization, globally
• It’s important to seek a “single truth”
• Ensure you understand the quality of your data – precision, recall and relevancy (as well as ability to customize)
• And understand how people, rather than researchers, articulate benefit and performance theme
• Assuming you find the same positioning picture coming from social media as from attribute ratings, cut your tracker expense by eliminating continuous tracking of attributes.
• Integrate this data both broadly and specifically
How Can You Access?
2
• If you have an application in need of social data, it is available through
a REST API
• If you have a basic listening tool and want to do additional processing
on the data, a simple-to-use “Conversus” app is available (see booth
for demo)
• If you use Brandwatch, a premium version is now available with the
ConveyAPI enhanced filtering capabilities
• If you are interested in marketing mixed modeling, we can plug data
into your model or make the WOMMA model available (in partnership
with Keller Fay and Analytics Partners)
• If you want to integrate more deeply into other applications, such as
brand tracking, our consulting and research group is available to assist