7. Social
Sentiment
Analysis
in
Social
Data
11
March
2015
7
Social
Data?
• Profiles.
• Identity,
categories.
• Connections.
• Elements:
Directionality,
degree.
• Content:
Text,
photos,
videos,
• Actions:
Likes,
Clicks,
Shares…
• Elements:
Time,
location,
target,
sequence.
Sentiment
can
be
extracted
or
inferred
from
all
of
these.
How?
8. Social
Sentiment
Analysis
in
Social
Data
11
March
2015
8
Analytics
is
the
systematic
application
of
algorithmic
methods
that
derive
and
deliver
information,
typically
expressed
quantitatively,
whether
in
the
form
of
indicators,
tables,
visualizations,
or
models.
• Systematic
means
formal
&
repeatable.
• Algorithmic
contrasts
with
heuristic.
Analytics
creates
and/or
applies
models.
9. Social
Sentiment
Analysis
in
Social
Data
11
March
2015
9
Sentiment
–
• Opinion,
attitude,
emotion,
and
mood:
Affective
states.
• Communicated
via
expressions
and
actions.
• Understood
contextually.
• Applied
situationally.
Anyone
who
tells
you
that
sentiment
analysis
is
solely
about
computing
a
positive/
negative/neutral(/mixed)
evaluation
is
probably
hawking
a
weak
solution.
10. Social
Sentiment
Analysis
in
Social
Data
11
March
2015
10
The
sentiment
value
of
an
opinion
may
be
expressed
as
a
quintuple
(oj,
fjk,
soijkl,
hi,
tl):
• oj
is
a
target
object.
• fjk
is
an
feature
of
the
object
oj.
• hi
is
an
opinion
holder.
• tl
is
the
time
when
the
opinion
is
expressed.
• soijkl
is
the
sentiment
value
of
the
opinion
of
the
opinion
holder
hi
regarding
feature
fjk
of
object
oj
at
time
tl.
• soijkl
is
+ve,
-‐ve,
or
neu,
or
a
more
granular
rating.
Bing
Liu,
NLP
Handbook
11. Social
Sentiment
Analysis
in
Social
Data
11
March
2015
11
Comparative
opinions
-‐-‐
(O1,
O2,
F,
po,
h,
t):
• O1
and
O2
are
object
sets
being
compared
based
on
shared
features
F.
• po
is
the
preferred
object
set
of
the
opinion
holder
h.
• t
is
the
time
when
the
comparative
opinion
is
expressed.
Bing
Liu
15. Social
Sentiment
Analysis
in
Social
Data
11
March
2015
15
Questions
for
business
(&
government):
What
are
people
saying?
What’s
hot/trending?
What
are
they
saying
about
{topic|person|product}
X?
...
about
X
versus
{topic|person|product}
Y?
How
has
opinion
about
X
and
Y
evolved?
How
has
opinion
correlated
with
{our|competitors’|
general}
{news|marketing|sales|events}?
Who
(and
What,
When
&
How)
are
opinion
leaders?
How
does
sentiment
propagate
across
multiple
channels?
What’s
behind
opinion,
the
root
causes?
(How)
Can
we
link
opinions,
profiles,
behaviors
&
transactions
to
discern
intent
and
predict
actions?
16. Social
Sentiment
Analysis
in
Social
Data
11
March
2015
16
Measurement
methods
–
• Polling,
surveys
including
NPS.
• Natural
language
processing.
• Action
stats.
• Network
and
information-‐flow
analysis.
• Biometrics.
Modelled
concepts
–
• Affinities
(clusters).
• Influence,
Authority.
• Satisfaction,
Loyalty,
Motivation.
• Likelihood
to
buy,
Churn
propensity...