Modeling Trust and Influence on Blogosphere using Link Polarity

1
Modeling Trust and Influence on Blogosphere
using Link Polarity

• Anubhav Kale
• Masters Thesis, 2007

2
Overview

• Motivation
• Problem Statement
• Approach
• Link Polarity
• Trust Propagation
• Experiments
• Future Work
• Q A

3
Overview

• Motivation
• Problem Statement
• Approach
• Link Polarity
• Trust Propagation
• Experiments
• Future Work
• Q A

4
Social Media

• Social media describes the online tools and
  platforms that people use to share opinions,
  insights, experiences, and perspectives -
  wikipedia
• Level of user participation and thought sharing
  across varied topics

Twitterment beta
5
Blogs Essence of Social Media

• Blogs
• Means by which new ideas and information spreads
  rapidly on social media

6
Communities in Blogosphere

• Can you track the buzz about Ipod among bloggers
  ?
• What are the blogs that always criticize Ipod and
  the ones that are Ipod fans ?
• Are there any neutral bloggers who would like to
  have the best of both worlds ?
• Can you analyze the changes in opinions/biases ?
  
• Are there any influential blogs in both
  communities ?

• Can you find the right set of individuals
  (like-minded) to target ?

7
Overview

• Motivation
• Problem Statement
• Approach
• Link Polarity
• Trust Propagation
• Experiments
• Future Work
• Q A

8
Problem Statement

• Convert a sparsely connected blog graph without
  any knowledge of sentiments across blog-blog
  links, to a densely connected graph with
  sentiments associated to every link.
• Sentiment represents the opinion/trust/distrust
  of the blogger nodes connected by the link.
• Use the densely connected polar graph to
  determine like-minded blogs

9
Overview

• Motivation
• Problem Statement
• Approach
• Link Polarity
• Trust Propagation
• Experiments
• Future Work
• Q A

10
Approach

• Identify the polarity of link that points from
  one blog post to another
• Simple sentiment detection techniques
• Polarity may be positive, negative or neutral
• Use trust propagation models to spread the
  sentiment from the subset of connected blogs to
  all blogs
• Compute polarity from pre-defined influential
  blogs in each community to deduce like-minded
  blogs
• Validation with a hand-labeled dataset

11
Birds Eye View Step 1
E
C
B
D
foo
F
A

12
Birds Eye View Step 2
cool!
E
C
B
I like him
What crap!
He is great
D
foo
amazing!
ridiculous
F
A
-ve bias
ve bias

13
Birds Eye View Step 3
E
C
B
D
foo
F
A
-ve bias
ve bias

14
Birds Eye View Step 4
E
C
B
D
foo
F
A
-ve bias
ve bias

15
Birds Eye View Step 4
E
C
B
D
foo
F
A
-ve bias
ve bias

16
Overview

• Motivation
• Problem Statement
• Approach
• Link Polarity
• Trust Propagation
• Experiments
• Future Work
• Q A

17
Link Polarity

• Its very generic !
• In co-authorship graphs, polarity may be defined
  as the number of times authors have collaborated
• On Amazon.com, polarity is the ranking scheme in
  the reviews
• How does it apply to blogs ?
• Represents the opinion of source blog about
  destination blog
• Sign represents whether the bias is for, against
  or neutral
• Magnitude represents the strength or weakness of
  bias

18
How to compute polarity ?

• Blogrolls
• Measure of association between blogs
• Indicates that the blogger is interested in
  following the blog
• May not indicate any bias
• Static nature once created, never updated

Blogroll from dailykos ?
19
How to compute polarity ?

• Comments
• Feedback on complete blog post granularity is
  coarse
• Verbose comments a challenge for NLP
• Pull source blog may not be associated with
  the comment author
• Tendency to comment anonymously on controversial
  topics

20
How to compute polarity ?

• Explicit Links
• Strongest evidence of interaction
• Text surrounding the link generally contains
  sentiments
• Shallow Natural Language Processing can help
  since the target text is highly focused.

21
How to compute polarity ?

• Explicit Links
• Strongest evidence of interaction
• Text surrounding the link generally contains
  sentiments
• Shallow Natural Language Processing can help
  since the target text is highly focused.

22
Our Approach to Link Polarity

• Sentiment Analysis
• Calculate the number of positively oriented (Np)
  and Negatively oriented words (Nn) in the
  text-window around the link
• Apply Stemming, basic canonicalization
• Corpus includes simple bi-grams of the form
  not_good
• Polarity (Np Nn) / (Np Nn)
• Denominator acts as a normalization mechanism
• Natural Language Processing is shallow, yet
  large-scale effects help !

23
Link Polarity Example

• Stephen Colbert's performance at the White House
  Correspondents' Association dinner has garnered
  him huge applause in the blogosphere and also on
  C-Span where it was shown more than once. Those
  of us who have been angry with Bush for quite
  some time because of his arrogant and feckless
  corruption of our country were even more thrilled
  to see and know that he had no recourse but to
  sit there and watch his aspirations for greatness
  be destroyed by a master of irony.
• This will be his legacy I stand by this
  man. I stand by this man because he stands for
  things. Not only for things, he stands on things.
  Things like aircraft carriers and rubble and
  recently flooded city squares. And that sends a
  strong message, that no matter what happens to
  America, she will always rebound -- with the most
  powerfully staged photo ops in the world. We who
  have been watching Stephen Colbert eviscerate
  politicians that have come on his show knew he
  was a gifted comedian. But it took Saturday's
  dinner to demonstrate how incredibly effective
  the art form Colbert has chosen is for exposing
  the Potemkin Regime Bush and his henchmen have
  created. Rove and the right wing machine have no
  answer to the performance but to say "it bombed",
  "it wasn't funny", and to hope that by ignoring
  it, the caustic cleansing agent it has lobbed
  into their camp can be contained. Yet, the
  Republican spinmeisters are the masters of
  spin.2
• This - http//dailykos.com/storyonly/2006/4/30/1
  441/59811
• 2http//www.pacificviews.org/weblog/archives/00
  1989.html

24
Link Polarity Example

• Stephen Colbert's performance at the White House
  Correspondents' Association dinner has garnered
  him huge applause in the blogosphere and also on
  C-Span where it was shown more than once. Those
  of us who have been angry with Bush for quite
  some time because of his arrogant and feckless
  corruption of our country were even more thrilled
  to see and know that he had no recourse but to
  sit there and watch his aspirations for greatness
  be destroyed by a master of irony.
• This will be his legacy I stand by this
  man. I stand by this man because he stands for
  things. Not only for things, he stands on things.
  Things like aircraft carriers and rubble and
  recently flooded city squares. And that sends a
  strong message, that no matter what happens to
  America, she will always rebound -- with the most
  powerfully staged photo ops in the world. We who
  have been watching Stephen Colbert eviscerate
  politicians that have come on his show knew he
  was a gifted comedian. But it took Saturday's
  dinner to demonstrate how incredibly effective
  the art form Colbert has chosen is for exposing
  the Potemkin Regime Bush and his henchmen have
  created. Rove and the right wing machine have no
  answer to the performance but to say "it bombed",
  "it wasn't funny", and to hope that by ignoring
  it, the caustic cleansing agent it has lobbed
  into their camp can be contained. Yet, the
  Republican spinmeisters are the masters of
  spin.2
• This - http//dailykos.com/storyonly/2006/4/30/1
  441/59811
• Np 8, Nn 4 Polarity Np Nn / Np Nn
  0.33
• 2http//www.pacificviews.org/weblog/archives/00
  1989.html

25
Overview

• Motivation
• Problem Statement
• Approach
• Link Polarity
• Trust Propagation
• Experiments
• Future Work
• Q A

26
Trust Propagation

• Based on work of Guha et al1 for modeling
  propagation of trust and distrust
• Framework
• Mij represents bias from user i to j.(0 1)
• Belief Matrix M represents the initial set of
  known beliefs
• Mij can be based on trust matrix (T), distrust
  matrix (D) or a combination of trust and distrust
  (T-D) from i to j.
• T Positive Polarities and D Negative
  Polarities
• Goal is to compute all unknown values in M
• Results from validations on dataset from
  epinions are impressive
• 1 Guha R, Kumar R, Raghavan P, Tomkins A.
  Propagation of trust and distrust. In
  Proceedings of the Thirteenth International World
  Wide Web Conference, New York, NY, USA, May 2004.
  ACM Press, 2004.

27
Atomic Propagation

• Direct Propagation
• Given A trusts B and B trusts C
• Implies A trusts C
• Operator M
• Co-citation
• Given A trusts B and C, D trust C
• Implies D trusts B
• Operator MT M

B
C
A
A
B
C
D
28
Atomic Propagation Contd

• Transpose Trust
• Given A trusts B and C trusts B
• Implies C trusts A, A trusts C
• Operator MT
• Trust Coupling
• Given D trusts A, A trusts C
• and B trusts C
• Implies D trusts B
• Operator M MT

A
B
C
C
A
B
D
29
Atomic Propagation contd

• Combined Operator
• Ci a1 M a2 MTM a3 MT a4 MMT
• ai 0.4, 0.4, 0.1, 0.1 represents weighing
  factor
• Belief Matrix after ith atomic propagation
• Mi1 Mi Ci
• We perform propagations till convergence (till
  the new iteration does not change values in M
  above threshold)

30
Models to compute final belief matrix

• Trust-only
• Ignore distrust (negative polarities) completely
• Final Belief Matrix Mk , M0 T
• (K Number of atomic propagations till
  convergence)
• One-step Distrust
• Distrust propagates single step while trust
  propagates repeatedly
• Final Belief Matrix Mk (T-D) , M0 T
• (K Number of atomic propagations till
  convergence)
• Propagated Distrust
• Treat distrust and trust equivalent
• Final Belief Matrix Mk , M0 T - D
• (K Number of atomic propagations till
  convergence)

31
Models to compute final belief matrix

• Trust-only
• Ignore distrust (negative polarities) completely
• Final Belief Matrix Mk , M0 T
• (K Number of atomic propagations till
  convergence)
• One-step Distrust
• Distrust propagates single step while trust
  propagates repeatedly
• Final Belief Matrix Mk (T-D) , M0 T
• (K Number of atomic propagations till
  convergence)
• Propagated Distrust
• Treat distrust and trust equivalent
• Final Belief Matrix Mk , M0 T - D
• (K Number of atomic propagations till
  convergence)

32
Overview

• Motivation
• Problem Statement
• Approach
• Link Polarity
• Trust Propagation
• Experiments
• Future Work
• Q A

33
Experiments

• Domain
• Political Blogosphere
• Dataset from Buzzmetrics2 provides post-post
  link structure over 14 million posts
• Few off-the-topic posts help aggregation
• Potential business value
• Reference Dataset
• Hand-labeled dataset from Lada Adamic et al3
  classifying political blogs into right and left
  leaning bloggers
• Timeframe 2004 presidential elections, over
  1500 blogs analyzed
• Overlap of 300 blogs between Buzzmetrics and
  reference dataset
• Goal
• Classify the blogs in Buzzmetrics dataset as
  democrat and republic and compare with reference
  dataset

• 2 Lada A. Adamic and Natalie Glance, "The
  political blogosphere and the 2004 US Election",
  in Proceedings of the WWW-2005 Workshop
• Buzzmetrics www.buzzmetrics.com

34
Effect of Link Polarity

• Republican blogs classified more correctly than
  democrats
• Trust propagation on polar links more effective
  than over non-polar links
• Link Polarity improves classification by
  approximately 26

35
Effect of text window size

• Optimal window size is 750 characters for our
  experiments
• Small window size Non-opinionated phrases
• Large Window size Analysis of non-related text
• Specific to our experiments, numbers may not be
  generalized

36
Effect of atomic propagation parameters

• X-axis Bitset direct trust, cocitation,
  transpose trust and trust coupling 0001 -
  1111
• Each parameter set to either 0 or its optimal
  value
• Collective influence of all parameters helps !

37
Evaluation Metrics
Confusion Matrix
How did I compute the numbers ?
38
Evaluation Metrics Continued

• Accuracy 73
• True Positive Rate (Recall) 78
• False Positive Rate (FP) 31
• True Negative Rate (Recall) 69
• False Negative Rate (FN) 21
• Precision (Positive) 75
• Precision (Negative) 72
• (Positive Republican, Negative Democrat)

http//www2.cs.uregina.ca/dbd/cs831/notes/confusi
on_matrix/confusion_matrix.html
39
Sample Data

• Trust propagation compensates for initial
  incorrect polarity (DK AT)
• Trust propagation does not change correct
  polarity (AT-DK)
• Trust propagation assigns correct polarity for
  non-existent direct links (AT-IP)
• Numbers in italics problematic (MM-AT)
• Improve sentiment detection ?

40
Main Stream Media Classification

• Goal
• Classify main stream media news sources (e.g.
  guardian, foxnews, truthout ) as left and right
  leaning
• Use links from blog posts to media sources ( drop
  blog-blog links )
• Graph Structure

P
a
b
c
Blogs
Q
MSM
d
R
41
MSM Classification Results
42
Interesting Observations

• 24 out of 27 sources classified correctly
• Well-known sources like guardian, foxnews,
  truthout and mediamatters classified
  correctly
• Main Outliers -- thenation and boston globe
• google news classified as left leaning
• Both left and right leaning blogs talk negatively
  about nytimes and abcnews and positively
  about rawstory and examiner

43
Overview

• Motivation
• Problem Statement
• Approach
• Link Polarity
• Trust Propagation
• Experiments
• Future Work
• Q A

44
Future Work

• Link Polarity
• More sophisticated NLP techniques
• Topic as a parameter
• Trust Propagation
• Evaluate other models
• Augment trust model with data from other domains
  (communities in MySpace etc)
• Experiments
• Evaluations on larger heterogeneous datasets
• Domains with noisy data and multi-subject posts

45
Thank You !!

• Questions?