MARKETING RESEARCH AND
MARKETING INFORMATION SYSTEMS
• Marketing Information
Systems (MkIS)
• Primary vs. secondary
data
– Advantages and
disadvantages of each
• Marketing research
tools
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
1
Learning Objectives
• Identify the costs and benefits of
research
• Identify the uses of both primary and
secondary market research
• Identify the respective advantages and
disadvantages of different primary
research methods
• Identify potential research method
problems that can lead to misleading or
incorrect conclusions.
• Determine the proper sequence of
research activities.
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
2
Market Research
• An “investment” to
reduce uncertainty
• Can help guide
decisions on
–
–
–
–
BUAD 307
Whether to enter
Product characteristics
Promotional strategy
Positioning
• Must weigh costs and
benefits of research
– Money
– Time spent
• No perfect method—
tradeoffs between
methods
MARKET RESEARCH
Lars Perner, Instructor
3
Marketing Information Systems
(MkIS)
• Set of procedures and
methods for regular collection
and analysis of information for
marketing decisions
– Databases (internal
information—e.g., sales
volumes)
– Market research
• Primary
• Secondary
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
4
Data Mining
• Processing of vast amounts of
data to find relationships
between variables—e.g.,
– Items frequently purchased together 
“strategic adjacencies” (items placed
together in retail setting)
– Seasonal patterns in sales
– Customer segments
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
5
Some Primary Research Methods
•
•
•
•
•
•
•
•
•
•
•
•
BUAD 307
Surveys
Experimentation
Observation
Focus groups
In-depth interviews
Projective techniques
Physiological Measures
Online research
Scanner data
Conjoint Analysis
Hybrid Methods
Sentiment Analysis
MARKET RESEARCH
Lars Perner, Instructor
6
Primary Research Methods
• Exploratory Methods
• Precision Methods
– Observation (can be
more definitive with larger
sample sizes and focus
on specific behavior)
– In-depth interviews
– Focus groups
– Projective techniques
BUAD 307
MARKET RESEARCH
–
–
–
–
Experiments
Surveys
Panel
Scanner data
Lars Perner, Instructor
7
Choosing a Primary Research
Method
Can the respondent
answer accurately?
(What someone
consciously believes may
differ from “deeper”
opinions; beliefs about
hypothetical products may
not be well developed.)
OPINIONS
NO
YES
EXPLORATORY or
PRECISION
research?
PRECISION
INDIVIDUAL
INTERVIEWS
SURVEYS
FOCUS
GROUPS
SENTIMENT
ANALYSIS
BUAD 307
BEHAVIOR
Can the relevant
behavior be
observed in the
customer’s natural
environment?
PROJECTIVE
METHODS
YES
EXPLORATORY
Does the question
involve OPINIONS or
BEHAVIOR?
NO
SCANNER DATA (e.g., brand
EXPERIMENTATION
choice, impact of advertising,
previous purchases, competing
brands, demographics)
(determine causality—e.g.,
impact of product design,
advertising message)
OBSERVATION (e.g., how
long does the shopper spend?
What does he or she look at? Is
anyone else involved?)
PHYSIOLOGICAL (e.g.,
determine reactions, attention,
arousal)
MARKET RESEARCH
Lars Perner, Instructor
8
Surveys
• Forms
– Mail (self-administered, single time)
– Mail panel (self-administered, multiple surveys
administered over time)
– Telephone (from central location)
– Mall Intercept
– Computer/Internet
• Planned questions
– Open-ended
– Closed-ended
SURVEY COSTS:
USUALLY LOW
• Need large sample sizes for precise
conclusions
– Small samples will have very large standard errors and
thus large margins of error
– E.g., Presidential polls (with only two choices) require a
little more than n=1000 to get results accurate to +/- 3%.
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
9
Characteristics of Some
Problematic Questions
• Difficult to answer—respondent may
not have knowledge needed
– Amounts spent annually on specific
product categories may not be known
• Sensitive (embarrassing)
• Two in one—e.g., “On a scale from 1
to 10, how fast and reliable are
Microsoft programs?”
• Leading questions—giving the
feeling of the “desired” response
– “Do you agree that soft drinks with sugar
are bad for you?”
• Non-exhaustive question
• Non-mutually exclusive answers
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
10
Continuum Questions
• Questions rating the degree of a characteristic (e.g., agreement or
product usage) tend to be more effective than binary “Yes/No” questions
• E.g.,
5
Strongly
Agree
BUAD 307
4
Agree
3
Neither
Agree Nor
Disagree
2
Disagree
MARKET RESEARCH
1
Strongly
Disagree
Lars Perner, Instructor
11
Continuum Scales
• Rather than asking binary (e.g., “Yes” vs. “No”)
questions, it is usually better to ask about a
matter of degree or extent
– E.g., “On a scale from 1-10, with 1 being ‘Not all
interested’ and 10 being ‘Extremely Interested,’
how interested are you in fashion?
– Asking simply “Yes” or “No” on “Are you interested
in fashion?” would result in people with very little
actual interest potentially answering affirmatively
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
12
Some Areas Suited for Continuum
Ratings
• Interest
• Purchase
likelihood
• Satisfaction/
Dissatisfaction
• Brand loyalty
• Price sensitivity
• Knowledge
• Experience
BUAD 307
• Involvement
• Decision control
• Frequency or level of
use
• Awareness
• Information search
• Personality traits
• Variety seeking
MARKET RESEARCH
Lars Perner, Instructor
13
Online Surveys
• Conditional branching—direct skip to relevant
question
• Quality of response
– Time pressures
– Willingness to write out answers or respond to
multiple closed-ended questions
– Willingness to read and follow instructions is
limited
• Reliability and browser compatibility issues
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
14
Conditional Branching
• Traditional surveys: Have you bought a new
car during the last six months? If not, please
skip to Question 11.
• Conditional branching: Respondent will be
taken to the appropriate question according to
answer
• Customization of questions
– E.g., consumer lists three brands  subsequent
questions ask about these specific brands by
name
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
15
Experimentation
• Testing what people actually do rather than way they say or
think they will do
• Useful in trying to determine causation (e.g., does a product
sell more if the packaging is red rather blue?)
• Possible to
– Control for factors that are not equal in real life (e.g., If those who pay
restaurant checks with credit cards are more likely to be reimbursed by their
employers, it is not clear if the credit use was the cause of the higher tip)
– Test and rule out competing explanations (subject to some caveats)—e.g.,
does texting while driving cause accidents because (1) eyes are removed from
the road, (2) attention is diverted to the conversation, or (3) a combination
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
16
Two Basic Types of Experiments
• Between-subject: Different groups of people are treated the
same except for the variable or variables manipulated
– E.g., One group shops in simulated store in which a credit card logo is
displayed; the other group shops in the same simulated store but the
credit card logo is removed
• Within-subject: The same individual is treated differently at
different times (e.g., at time 1 is given cola drink that includes
vanilla and one without at time 2)
– Subjects are usually counter-balanced to rule out order effects (1/2
receives treatment A first and then B, the other half receives B, then A)
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
17
Experimentation
• Subjects in different
groups are usually
treated differently
– E.g., for some, “target”
product is given better
shelf space
– E.g., some get coupon
• Can help isolate causes
• Subject is not biased by
questions—does not
know how others are
treated
EXPERIMENT COSTS:
HIGH
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
18
My Simulated Store…
A shopper in the everyday low price condition…
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
19
Ash’s Instant Coffee Study
GROCERY SHOPPING
LIST
Ground beef
Potatoes
Apples
Flour
Sugar
Laundry detergent
Instant coffee
6 cups of yogurt
Paper towels
Bananas
BUAD 307
GROCERY SHOPPING
LIST
Ground beef
Potatoes
Apples
Flour
Sugar
Laundry detergent
Ground coffee
6 cups of yogurt
Paper towels
Bananas
MARKET RESEARCH
Respondents were
asked to describe
their impressions of a
housewife based only
on her shopping list.
These shopping lists
differ only on one
item.
Lars Perner, Instructor
20
Definition
• Confound: An illusion of one
variable causing another
because of correlation
between two variables
• E.g., does having more toys
cause children to be more
intelligent?
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
21
Some types of confounds
B
A
You will NOT be asked to
draw these diagrams on
the exam or to explain the
specifics of the different
types of confounds.
BUAD 307
Actual cause
Illusory cause
A appears to cause B but it is actually B that causes A
Examples:
• Diversification and profitability. Diversified firms tend
to have higher profit levels. This may be because
more profitable firms need to find ways to re-invest
profits rather than because diversification causes
profitability
• Sales of a brand of soda are higher during weeks of
heavy advertising. However, advertising is allocated
when the stakes are greatest (e.g., during holidays
and summer months). Thus, anticipated sales
actually cause advertising.
MARKET RESEARCH
Lars Perner, Instructor
22
Some types of confounds
Actual cause
Illusory cause
A appears to cause B but both A and B are actually caused
by C
B
Examples:
•
C
•
A
•
BUAD 307
On the average, the more toys a child has, the higher his or her
IQ. Both the number of toys and IQ may be caused by family
resources such as income (providing for better nutrition and
better education)
Individuals taking anti-depressive medication have higher rates
of suicide than the general population. This is because those
who take anti-depressive medication are more likely to be
depressed. In fact, individuals suffering from depression are less
likely to commit suicide than those with depression who do not
take medication.
On the average, students who sit in the front of the class end up
with higher grades. However, students choose where they sit.
MARKET RESEARCH
Lars Perner, Instructor
23
Some types of confounds
Actual cause
Illusory cause
Correlation
A appears to cause B but both A is correlated with C, with
C ultimately causing B
B
Examples:
C
A
BUAD 307
•
•
Sales of laundry detergent are higher during weeks when the
brand is advertised. However, when the brand is advertised,
there is always a price promotion (temporary price reduction).
Most of the sales increase results from the price discount with
a much smaller portion coming from advertising. The deeper
the discount, the greater the sales.
Members of fraternities and sororities on the average have
higher GPAs than people not in the Greek system. There may
be some benefits to Greek membership causing higher grades,
but members of the Greek system also tend to come from
more privileged backgrounds.
MARKET RESEARCH
Lars Perner, Instructor
24
Confounds
• What is cause, what is effect, and what is
coincidence?
• Correlation is not necessarily cause
• “Lurking” factors may be real cause
– Does sitting in front of the room cause higher
grades?
– Does Prozac cause suicide?
– Do fish-heavy diets cause stomach cancer?
– Does fraternity/sorority membership cause
higher grades?
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
25
Confounds: The Bottom Line
• Correlation ǂ cause!
• One can often make a plausible—even compelling—
hypothesis of causation based on the observed relationship
(but a hypothesis is still an open question)
• If one variable appears to cause another
– Both may be caused by a different variable
– The causation may be the other way around (B causes A rather than A
causes B)
– The variable that seems to cause the other may be correlated with the
actual cause (A does not cause C, but a is correlated with B and B
causes C)
• Experiments can be used to test for causality (with certain
caveats) by controlling for potentially confounding variables
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
26
Some other influences on the
relationship between variables
• Restricted range: One population includes only a portion of
another or the sample includes only a small portion of the
population range—e.g.,
– High school GPA school is a limited predictor of college GPA since students with higher
high school GPAs tend to get into more competitive colleges
– Among residents of Rancho Palos Verdes, household income does not predict dental
health. In society as a whole, many people have difficulty paying for quality dental care,
but most residents of Rancho Palos Verdes are relatively affluent
• “Diluting” variables: Variables not considered “drown out”
much of the effect of the variable of interest—e.g.,
– Income is a limited predictor of spending. Although a certain level of income (or wealth)
is needed to buy certain things (necessary condition), income is not a sufficient condition.
Many high income individuals are rather stingy and many lower income individuals live
above their means.
– Ethnicity is a limited predictor of food preferences. Many Caucasians, African-Americans,
Latinos, and Native Americans like raw fish.
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
27
Observation
• Looking at consumes in the field—
e.g.,
– Searching for product category area
– Number of products inspected and time
spent on each
– Apparent scrutiny of labels or other
information
– Involvement of others
– Behavior under limiting circumstances
(e.g., time constraints)
OBSERVATION COSTS:
LOW TO HIGH
(DEPENDING ON CODING AND
ANALYSIS NEEDED)
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
28
Taste Tests
• Not experiments unless
– Two or more groups of people are treated differently (e.g.,
get different food version) or
– The same person is being treated differently at separate
times (e.g., half the participants receive new formulation,
then current; half the participants receive in the opposite
order)
• “Triangle” Measure
– Each respondent is given three items: One current, one
new, and one duplicate of either old or new
– Asked to identify the one that is different and explain why
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
29
Focus Groups
• Groups of 5-12
consumers
assembled
• Start out talking
generally about
context of product
• Gradually “focus” in
on actual product
MOST
APPROPRIATE
AS EARLY
STAGE METHOD
BUAD 307
FOCUS GROUP COSTS:
HIGH
(ESPECIALLY FOR THE AMOUNT
OF INFORMATION COLLECTED)
MARKET RESEARCH
Lars Perner, Instructor
30
Focus Groups: Potential Uses
Note that follow-up with more
precise research methods is
essential before firm conclusions
can be made
BUAD 307
• Identifying possible issues of
concern with a new product
• Probing complex issues where
different factors and issues may
affect opinions
• Probing differences in
perspectives among different
groups
• Very preliminary pilot testing of
ideas
• Identifying the actual language
used by customers
MARKET RESEARCH
Lars Perner, Instructor
31
Focus Groups: Composition
• Members of each focus group
should generally be similar to
each other in terms of factors
affecting comfort in speaking
openly (e.g., age, gender, socioeconomic status)
• If the target market crosses such
variables, different focus groups
should be run
• It may be helpful to run focus
groups—even with customers
otherwise demographically
similar—in different cities
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
32
Focus Groups: Dynamics
• The facilitator should
– Allow the focus groups members
to talk as much as possible to get
at their views and perceptions
– Gently attempt to steer the group
in the desired direction
– Probe and ask for elaboration
when interesting ideas are raised
• The focus group may involve
an activity (e.g., cooking a
meal) and/or sampling a
product
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
33
Focus Groups: Caveats
• Even with ten focus groups each
with ten members, the sample
size is only 100
• Because of social influence, the
opinions expressed by different
members are not independent
• Issues identified in focus groups
should examined with more
powerful methods using larger
sample sizes (e.g., surveys,
scanner data, experiments)
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
34
REMINDER
• Focus groups are most
useful for identifying issues
that should be studied in
more detail with more
precise methods
• Due to the small sample
size and social influence on
individual responses, it is
difficult to generalize much
from focus groups
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
35
In-depth interviews
• Structured vs.
unstructured interviews
• Generalizing to other
consumers
• Biases
– Subtle, inadvertent
feedback
IN-DEPTH
INTERVIEW COSTS:
HIGH
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
36
Projective Techniques
• Getting at motivations that may not be
consciously known— “Tell a story about
this picture.”
• Measurement of attitudes consumers
are unwilling to express
– It is easier to admit something embarrassing
about someone else
• Consumer discusses what other
consumer might think, feel, or do
PROJECTIVE METHODS COSTS:
USUALLY HIGH IF PERSONAL INTERVIEWS OR
EXTENSIVEINTERPRETATION IS NEEDED
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
37
Physiological Measures
• Consumer
bodily
responses are
watched at
various phases
of advertisement
or other
marketing
exposure
• Tracking of
– Eye movements
• For areas of focus
• For attention, involvement
– Heart rate
– Skin conductivity
– Brain waves
• State of mind
• Attention
PHYSIOLOGICAL
METHODS COSTS:
HIGH
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
38
Online Research—Analysis of Customer
Search Queries
• Unmet demand—
search for product not
found on site
• Message
comprehension—
comparison of search
terms to media
message
• Consumer vocabulary
• Feedback analysis
ONLINE SURVEY COSTS:
USUALLY LOW
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
39
Other Online Tools
• “Click Stream Analysis:”
Analysis of “clicking” path—
how does the consumer get
to a desired page or
product?
• Shopping cart analysis
BUAD 307
MARKET RESEARCH
COSTS: HIGH START-UP COSTS;
LOW VARIABLE COSTS
POSSIBLE WITH DEVELOPED
ALGORITHMS
USUALLY LOW
COSTS: HIGH START-UP COSTS;
LOW VARIABLE COSTS
POSSIBLE WITH DEVELOPED
ALGORITHMS
USUALLY LOW
Lars Perner, Instructor
40
Searching for Reports of Personal
Experience
• Sources
• Some issues
– Blogs
(blogsearch.google.com)
– Photos (e.g., Flickr,
Webshots, Picasaweb,
Google image search)
– Video (e.g., Youtube)
–
–
–
–
Joy, enjoyment
Decisions
Anxiety
Social setting and
influence
• Cautions
– May be “staged” or
sensationalized
– May represent what the
writer or photographer
wants to show
– May be limited entries on
certain “mundane” tasks
such as dishwashing
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
41
Conjoint Analysis: Determining the Relative
Importance of Product Attributes
• Consumers rate
several “profiles”
(combinations of
features)
• Statistical analysis is
used to
“decompose”
ratings into
preferences
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
42
Example
Car #1
Gas mileage:
Price:
Safety record:
Performance
Reliability
30 mpg
$18,200
Average
High
Poor
Car #2
Gas mileage:
Price:
Safety record:
Performance
Reliability
20 mpg
$15,200
Excellent
Poor
Excellent
How would you rate car #1 overall How would you rate car #2 overall
on a scale from 1 (Very poor) to
on a scale from 1 (Very poor) to
7 (Excellent?)
7 (Excellent?)
1
2
3
4
5
6
7
1
2
3
4
5
6
7
Each subject will evaluate several (usually 16+) combinations. A
statistical technique determines the importance of each feature.
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
43
Conjoint Analysis: Advantages
• Reveals ultimate preferences of
consumers when competing
influences exist
• Able to predict desirability of
combinations not actually
explored
• Can estimate contribution of
each factor and assess its cost
effectiveness
– Will consumers pay $500.00 to
reduce the weight of a laptop
computer by 2 lbs?
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
44
Conjoint Analysis: Disadvantages
• May be difficult for subjects to rate
many combinations
• May need a large number of
subjects for accurate
measurement/sufficient precision
• Must identify relevant attributes and
levels in advance
• Subject must know about product
category (attributes must be
meaningful)
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
45
Types of scanner data
•
•
•
Supermarket club. This includes purchases by the specific customer when
shopping at the respective chain (assuming that the customer presents his or her
card). Purchases at other locations are not counted. Demographic information may
be of limited accuracy. Shoppers are often motivated to join by large discounts
(often 20-30%). This is also a method of price discrimination. Members may be
given individualized coupons for possible products of interest. Only available for
grocery products.
Scanner data panels. In some communities, people can sign up to be part of a
“panel.” Purchases at all local retailers are included (e.g. supermarkets, gas
stations, drug stores, convenience stores). For a given customer, the database also
includes TV viewing and demographics. Only available for grocery products.
Aggregated retail sales records. Records of sales volumes of products by UPC
may be available from an assortment of retailers. This information is NOT tied to
individual customer data and purchase history. This is available for more types of
products.
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
46
Scanner Panel Data
• Panel members in test
communities agree to
– Swipe a card prior to each purchase
– Have purchases matched to
•
•
•
•
Demographic profiles
Media/coupon exposure
Promotional status of competing brands
Past purchases
• Problems:
– Aggregation over household
– Aggregation bias--averages of
disparate segments obscure!
– Only available for grocery and
some drugstore products
BUAD 307
MARKET RESEARCH
COSTS: HIGH START-UP COSTS;
LOW VARIABLE COSTS
POSSIBLE WITH DEVELOPED
ALGORITHMS
USUALLY LOW
Lars Perner, Instructor
47
Scanner Data Panel Research
(Some of these variables are available for supermarket club
data)
No. of ads seen by
shopper
Ads seen for competing
brands
“Split cable”
RECORDED
PURCHASES
TELEVISION
EXPOSURE
HOUSEHOLD
FILE
DEMOGRAPHIC
INFORMATION
Family size
Occupation
Family size
Income
BUAD 307
Home ownership
Purchase on occasion: Yes, no
Time since previous purchase
Previous purchases
Current price
Previous price
Current promotional status
Previous promotional status
Current display status
Previous display status
Display status of competing
brands
Promotional status of
competing brands
Coupon used: Yes, no
Coupon available: Yes, no
Coupon available for other
brands? Yes, no
Amount of coupon
ANALYSIS
MARKET RESEARCH
Lars Perner, Instructor
48
SCANNER DATA BASED
METHODS OF SEGMENTATION
• Price responsiveness
–
–
–
Price sensitivity (impact of current price on the likelihood of purchase and/or quantity
purchased). The brand elasticity is greater than the product category elasticity.
Deal proneness (propensity to switch to a non-preferred brand when such a competing
brand price promotes through sales, coupons, or other form of discount). [This is one
form of limited brand loyalty]
Purchase acceleration (“stocking up” when an item is on deal—sale and/or coupon)
• Non-price based brand switching
–
–
Variety seeking [Another form of limited brand loyalty]
Accommodation of preferences of different household members
• Shopping practices
–
–
Purchase frequency (within product category) (as distinct from price responsiveness
measures listed above)
Package size preference
• Store and/or retail chain loyalty
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
49
Sentiment Analysis
• Making sense of online postings in social media
–
–
–
–
Twitter
Photo sites (e.g., Instagram)
Blogs
Facebook
• Tracking of massive amounts of data by computer (for large sample
size and powerful predictions)
• Machine (Computer) Interpretation of postings based on
–
–
–
–
Specific words and combinations of words used
Language use (pronouns, active vs. passive voice)
Context
Indicators of sarcasm, irony
• Hashtags as brand identifier and emotion/evaluation
• Heavily proprietary specific methods (firms develop methods and
keep these secret)
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
50
Sentiment Analysis: Some
Functions and Tools
• Association of brands common to posts
• Identification of probable poster characteristics
(e.g., male/female, age) by language use
• Vocabulary use of different consumer groups
• Identifying expressions by opinion leaders
– As a source of influence on large numbers of other
consumers
– As “early warning” of opinions that may emerge
among consumers in general
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
51
Some Complications in Sentiment
Analysis
• Detection of irony, sarcasm, and humor in the specific context
• Emergence of slang:
– New slang terms
– Context-specific slang terms
– Slang used by limited consumer subgroup
• Aggregation of responses from different group (e.g., demographic groups,
positive/negative to the brand) making for meaningless average responses
unless adjusted for group effects
• Change of meaning by context (e.g., a consumer goes to Starbucks to
improve a negative mood; thus, the negative affect should not be attributed
to the brand)
• Interpretation of “pseudo-hashtags” invented to be funny and not to be
used across postings (e.g., #tastedkindofbad)
• Integration of photo or video information into interpretation, especially if text
only makes sense in the context of the images
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
52
Sentiment Analysis: CrossCultural Issues
• Language structure and meaning (e.g., vague or
precise word meaning, sequence of words, ambiguity
of implicit objects/subjects)
• Homonyms (words with same spelling but different
meaning)
• Customs of product category usage (e.g., “candy bar”
vs. “chocolate bar”)
• Slang and word meaning in context
• Focus on self vs. others
BUAD 307
MARKET RESEARCH
Lars Perner, Instructor
53
Choosing a Primary Research
Method
Can the respondent
answer accurately?
(What someone
consciously believes may
differ from “deeper”
opinions; beliefs about
hypothetical products may
not be well developed.)
OPINIONS
NO
YES
EXPLORATORY or
PRECISION
research?
PRECISION
INDIVIDUAL
INTERVIEWS
SURVEYS
FOCUS
GROUPS
SENTIMENT
ANALYSIS
BUAD 307
BEHAVIOR
Can the relevant
behavior be
observed in the
customer’s natural
environment?
PROJECTIVE
METHODS
YES
EXPLORATORY
Does the question
involve OPINIONS or
BEHAVIOR?
NO
SCANNER DATA (e.g., brand
EXPERIMENTATION
choice, impact of advertising,
previous purchases, competing
brands, demographics)
(determine causality—e.g.,
impact of product design,
advertising message)
OBSERVATION (e.g., how
long does the shopper spend?
What does he or she look at? Is
anyone else involved?)
PHYSIOLOGICAL (e.g.,
determine reactions, attention,
arousal)
MARKET RESEARCH
Lars Perner, Instructor
54