Conversation Research: Leveraging the power of social media market research

Conversation Research:

Leveraging the power

of social media Market

Research

For MRS Members Evening

By Robert Dossin, Managing Director, InSites

Consulting London office

Battle of the platforms

Social media mixology

Time to cook up your social media

cocktail.

Based on target group

women.

business.

30+ affluents.

For brand/positioning

Creative Industry.

#inspirational

Service Industry.

#customerexperience

Where is Social Media now?

‘Social

Media?’

‘We gotto do

something’.

‘We’re on

Facebook

and Twitter’.

‘We have a

strategy’.

2006-’07

‘Pinwhat?

Snapwhat?

Tumbwhat?

Instawhat?’

2008-’09

2010

2011

2012-’13

‘Time for a

strategic

review

2014

The world as it used to be

Research has changed

From asking questions...

...to having a conversation

Conversation research

‘Passive’ Listening Active Listening

Active Passive

Recycle and askRecruitmentGiving backKnowledge

Panel pressureBuilding a community

Only spontaneous feedbackRepresentativenessInformed consent

Giving back

Tapping into ACTIVE online

conversations

Social Media Nethnography

Social MediaDashboards / Monitoring

exploratory for enhanced quality

11EphMRA Conference Masterclass © InSites Consulting 2011

Observational

research

Social media netnography

= research methodology

that makes use of publicly

available user-generated-

content in order to answer a

research question

12

Social Media

Netnography

ANALYSIS

SURVEY/ TOPIC GUIDE DEVELOPMENT

SAMPLINGRESPONDENTS

FRAMEWORKDEVELOPMENT

SAMPLINGUNIVERSE DETECTION

PASSIVE DATA COLLECTION

Traditional research Social media nethnography

TOP-DOWN & BOTTOM-UPCONTENT & TEXT ANALYTICS

ACTIVEDATA COLLECTION

Reversed research process

Social Media

Netnography


1. Universe detection

Social Media

Netnography

Representativeness

‘It’s the end of the world as we know it’


Social Media

Netnography

Conversations are the new unit of analysis

Keywords for sampling

Conversations onepilespy

Conversations onEpilepsy brands


Selecting the right keywords

Social Media

Netnography

Conversations ondoctor

Analysis

Conversations onepilespy

Conversations onEpilepsy brands


Selecting the right keywords

Social Media

Netnography

Good definition of a universe


Social Media

Netnography

Google keywords

Thesaurus

Keywords for search engine optimization


Social Media

Netnography

Sampling is still key


Social Media

Netnography

Vis

ito

rs

# sources

Small #Large influence

Medium influenceSpecialized in topics

Long tail


Social Media

Netnography

Vis

ito

rs

# sources

http://www.healthboards.com/

http://www.coping-with-epilepsy.com/http://scott-lwe.blogspot.com/

http://bschool.pepperdine.edu/studentblog/index.php/2010/07/freedom-from-epilepsy-

doesnt-come-free/


Social Media

Netnography

Profile information on poster / user level

– Internet has no boundaries

– Only information available that is spontaneously shared

– Representativity: what do we know about profile on social media?

Profile information on source level

– Type of social media source

– Meta data

About influentials

– On person level

– On source

About profile information

Social Media

Netnography


2. Data collection

Social Media

Netnography


Social Media

Netnography

All doubles, headers & footers eliminated

One post can only appear once!

Data restructuring

= maximum error reduction

Social Media

Netnography

Historical data

0%

10%

20%

30%

40%

50%

60%

70%

80%

90%

100%

week 1

week 2

week 3

week 4

week 5

week 6

week 7

week 8

week 9

week 10

week 11

week 12

brand 1 65% 82% 64% 63% 50% 25% 23% 35% 40% 45% 48% 49%

Market 75% 55% 55% 48% 29% 54% 58% 60% 65% 63% 68% 70%


Social Media

Netnography

Public & fan pages only

Becoming friends


Social Media

Netnography


3. Framework development

Social Media

Netnography

Top down analysis

Bottom-up analysis

Two core principles

Social Media

Netnography

Text analytics is the process of

extracting knowledge and

information from text

Stage 1: Extraction of terms

What do I want to use?

Stage 2: Group terms in higher level

concepts or categories

The power of text analytics

Social Media

Netnography

3.Qualitativeanalysis

2.Associativepattern

recognition

1. Descriptivetaxonomydetection

To what extent do we find our research

topics back?

Which terms often co-occur? Which

concept are often mentioned bottom-up?

Analyse original verbatims via qualitative

content analysis

Analysis process

Social Media

Netnography

Sentiment of the

conversationSentiment of a

brand / topic

'I had a terrible day. I used brand x and felt better'

'I had a terrible day. I used brand x and felt better'

Conversation level Sentence level

1 positive – 1 negative 1 positive

Sentiment analysis

Social Media

Netnography

Emo

tio

ns

Excitement

Relaxed

Social

Beauty

Violence

Swear words

Despair

Weak

Loneliness

Elated, Excited, Enthusiastic

Contented, Relaxed, Satisfied

HappinessHappy Joyful

Cheerful SatisfiedProud

Trust, Love, Respect

Beautiful, Admired, Attractive

Aggressive, Abusive, Dominating

Agony, Despair, Ashamed

Tired , Bored, Weak

Lonely, Rejected, Alienated

SurpriseAmazed Surprised

Astonished

FearAfraid NervousTense Worried

Insecure

AngerAngry FuriousMad Irritated

Resentful

SadnessSad DisappointedRegretful Gloomy

Pessimistic

DisgustDisgust Contempt

Nasty

Social Media

Netnography


4. Analysis

Social Media

Netnography

Methodology

– Different clusters of words in the buzz are found that refer

to different themes

– For each theme, we determine the size of the cluster and

the sentiment of the cluster

Interpretation

– The themes are divided into different quadrants, based

on quartiles in volume and sentimeter.

– The different quadrants thus need to be interpreted in a

relative way, and within a certain language. E.g. themes

in quadrant are relatively more positive than themes in

quadrant but can still have a negative sentiment.

– Meaning of different quadrants

• 1: Act: themes that are often mentioned with a negative

sentiment

• 2: Develop: themes that are often mentioned with a positive

sentiment

• 3: Threats: themes with negative sentiment that are

currently not often mentioned but that are explicitely

negative for certain niches

• 4: Potential: themes with mixed sentiment that are often

mentioned. In the future, we can try to influence the

sentiment of those themes positively

1

2

3

4

Qu

art

ile

1Q

ua

rtile

2 &

3Q

ua

rtile

4

Quartile 1 Quartile 2 & 3 Quartile 4

2

1

Main conversation themes

Social Media

Netnography

Se

nti

me

ter

family

seizures

stakeholders

symptoms

medication brands

medication

epilepsy

diagnosis

types epilepsy

social impactchildren

administration

medication

Success

treatment

(no) control

surgery

side effects

budget

diet

generic medication

Frequency and

duration seizures

Seizure triggers

Medication

unloyalty

Treatment

Specific triggers

knowledgeMolecules

Polytherapy

Alternative

treatment

Other treatments

Volume

Main conversation themes in epilepsy

Social Media

Netnography

21%

15%

9%

9%

7%

7%

6%

6%

6%

6%

5%

4%

4%

4%

3%

3%

3%

1%

sleep issues and fatigue

stress and anxiety

emotional and mood

dizziness

pain

other psychological

other

headache

memory issues

symptoms

cardiovascular

confusion

weight issues

muscles

vision

respiratory

gastro

tumor

What symptoms are most often mentioned in

online conversations?

Social Media

Netnography


Product evaluation

&

branding

Social Media

Netnography

Share of brands in total amount of

conversations

Total sample

N = 42469

Brands

14%

N = 5836

30%

N = 12754

Pharmaceutical treatment

Total sample

100%

N = 42469

2% (832 conversations)

are about generic

products

Brands for epilepsy

treatment are

mentioned in about

14% of online

conversations

Social Media

Netnography

Applications


Social Media

Netnography

Typical research questions

Get insights directly from patients based on their spontaneous online discussions

1. Which are the main topics that are discussed by patients and their caregivers?

2. Which language do patients use when talking about these themes?

3. What is the emotionality of the different topics? How can these emotions be explained?

4. What are the main information sources consulted by patients & caregivers?

Increase the effectiveness of the brand plans

1. How big is the buzz about product brands (you and competitors)? How did this change over time?

2. What is the tone of voice of the buzz about product brands ? Which sentiments are used?

3. Is this in line with the desired brand positioning?

Digital strategy Netnography study that results in an integrated communication & conversations

strategy in terms of who to target, with which content, on which platform.

(Reporting will be based on our activation model.)

Consumer insightment Netnography study that results in insights and ideas on

unmet consumer needs, buying decision processes & product category usage.

Campaign evaluation trackerNetnography study that results in an ad-hoc evaluation or tracking of a campaign

Online Brand audit Netnography study that results in a 360° view on your brand

and its main competitors

Product evaluation netnography / trackerNetnography study that results in ad-hoc evaluation or tracking of a product

Other Applications

Business Objectives & Approach

To empower patients and carers to initiate conversations with HCPs, and each other and to raise awareness of the benefits of continuous medication, the research needed to identify what patients discussed, how they discussed it, in what context and what were opportunities for Janssen to start the conversation with patients suffering from Schizophrenia, but also carers and HCPs.

EMEA Schizophrenia 24 x 7

How understanding patients helped Janssen to improve its websiteusing Social Media NetnographyResearch

Outcomes

Healthcare Janssen Pharma – EMEA Schizophrenia 24 x 7

Corinne Pilgrim, EMEA Product Director Psychiatry, Janssen Pharmaceuticals,

• Different landing zones for different patient segments

• In 16 countries/5 languages

• 200K unique visitors• 20% revisit rate

In Summary

………………………………………………………………………………………………….…….

………………………………………………………………………………………………….…….

49

Social media netnography: benefits

Access to highly involved patientand difficult topics

Many conversationsMost on relevant topics

Ideal to explore new TAs/topics

50

Social media netnography: limitations

Less of the uninvolvedpatient

No probing Only what is relevant for them

Internet has no boundaries

Thoughts to hold on to

Have a conversation with your consumers – start with active

listening BEFORE joining

Netnography is a great method to mine user generated content from

YOUR Consumer

Consumers want to be engaged, ‘cause they are engaged.

We should reinvent ourselves, using technology to engage with

them where they are and when they want

Not just send our tradional messages via new channels

But by starting a conversation with them!

www.insites-consulting.com

Thank you! Robert Dossin, Managing Director

[email protected]

@robert_dossin

http://uk.linkedin.com/in/robertdossin

+44 7904 288 898

New York I Timisoara I London I Rotterdam I Ghent

Rosebery Avenue 151 - 4th floor I EC1R 4AB London I United Kingdom

https://twitter.com/kristofdewulf

https://twitter.com/kristofdewulf

http://www.linkedin.com/in/dewulfkristof

http://www.linkedin.com/in/dewulfkristof

mailto:[email protected]

mailto:[email protected]

http://www.insites-consulting.com

http://www.insites-consulting.com

Conversation Research: Leveraging the power of social media market research

Business

social media mixologytime

social media cocktail

research methodology

right keywords keywords

service industry

right keywordsconversations

topicslong tail

mrs members evening