William Rand, University of Maryland, presents at the 2012 Big Analytics Roadshow.
The dramatic feature of social media is that it gives everyone a voice; anyone can speak out and express their opinion to a crowd of followers with little or no cost or effort, which creates a loud and potentially overwhelming marketplace of ideas. The good news is that the organizations have more data than ever about what their consumers are saying about their brand. The bad news is that this huge amount of data is difficult to sift through. We will look at developing methods that can help sift through this torrent of data and examine important questions, such as who do users trust to provide them with the information and the recommendations that they want? Which tastemakers have the greatest influence on social media users? Using agent-based modeling, machine learning and network analysis we begin to examine and shed light on these questions and develop a deeper understanding of the complex system of social media.
20100506 aster data big data summit - microstrategy (shareable)
Trust and Influence in the Complex Network of Social Media
1. TRUST AND INFLUENCE
in the Complex Network of Social Media
Bill Rand
Director, Center for Complexity in Business
Asst. Professor of Marketing and Computer Science
Robert H. Smith School of Business
University of Maryland
2. Connecting the CMO to the CIO...
• Organizations have more data than ever
before...
• Computational power and storage is
cheaper than ever before...
• This enables analytics that can be used,
for example, to:
1. Gain new customers / stop old
customers from churning
2. Find out additional information to
increase share of customer
3. Analyze word-of-mouth and ROI for
media events
4. Teasers
• Who are the most influential individuals in social media?
• It may not just be those who are the most popular...
• How is trust earned in social media?
• We can design new social network mechanisms that
increase trust in social networks....
6. Who are the most influential
individuals in social networks?
•How does network structure affect
influence?
•What is the value of an individual in a
network?
•If we can simulate a diffusion process at the
micro-level then we can answer these
questions.
7. Who should you seed?
•Which individuals will allow you to reach the widest
audience as soon as possible?
•Standard Rule-of-Thumb is to seed those with the
highest number of connections
•Alternative Strategies
•Seed the people whose friends do not talk to each
other, spread the message widely (low clustering
coefficient)
•Seed the people who are the closest to everyone else
in the network, centralize your message (low average
path length)
8. How many to Seed?
•Seeding more people means the
message spreads quicker, but
•Seeding more people costs more, and
•At a certain point you start seeding
people who would have adopted anyway
because of their friends
•So how many people should we seed?
12. Influence
• People with lots of friends know other
people with lots of friends which
constrains social contagion.
• The most influential people have lots of
friends but their friends don’t know each
other.
• But this assumes that all individuals trust
each other equally, what happens when
trust varies over a network?
13. Trust
joint work with Hossam Sharara and Lise Getoor
Supported by NSF Award IIS-0746930 and IIS-1018361
14. Motivation
Ann Janet
John
Bob and Mary will
definitely be
interested.
However, I think Mary
Ann is not WOW… I’ll
interested in send it over
movies to everyone
MovieRental.com Bob Book Store
(Refer a friend and get (Invite a friend and get 10%
$10 off your next rental) off your next purchase)
17. The Model
• Our model takes two factors in to
account:
1. People have different preferences for
different product categories
2. Trust between individuals in
recommendations changes in time
• We can then use this model to predict
who is likely to accept recommendations
in the future.
18. Results
The Adaptive model, taking both the diffusion dynamics
and the users heterogeneity into account, yields better
performance
19. A New Viral Marketing
Marketing Mechanism:
Adaptive Rewards
Successful recommendations are awarded (α x r) units,
while failed ones are penalized ((1-α) x r) units
• α conservation parameter
Most existing viral marketing strategies assume α=1
(no reason for the user to be selective)
The penalty term helps maintain the average overall
confidence level between different peers
20. Experimental Results
• Allowing agents to learn the preferences accounts for
both the product preference as well as the confidence
level
21. Trust
• We can make better predictions about
adoption if we take in to account
heterogeneous preferences and
dynamic trust.
• We can create better mechanisms that
encourage more trust within social
networks.