Authority, Trust and Influence

1. Authority, Trust and Influence • The Complex Network of Social Media • Bill Rand

2. What does Facebook have to do with Complexity?

3. Social Media is an archetypal Complex System. • Social Networks are where individuals meet groups • Social Science meets Technology • Psychology meets Information Processing • Design meets Engineering • Sociology meets Innovation • All Driven by Constant Change, Permanent Evolution Complex Systems are about individual actions resulting in emergent patterns, and how those patterns feedback to affect individual actions.

4. Questions • Where does authority come from in Social Media? • Authority is not just what you know but who you know and who knows you.... • 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....

5. Authorityjoint work with Shanchan Wu, Tamer Elsayed and Louiqa RaschidSupported by NSF Awards CMMI 0753124, IIS 0960963, & IIS1018361

6. Motivation • Example • Gap logo fiasco in the Fall of 2010 (10/4). • Gap introduced a new logo, changing the iconic logo it had for 20 years almost overnight. • There was an immediate outpouring of negative comments • Gap quickly reverted to the old logo (10/12). • Goal • Identify which author (blog channel) is likely to become an authority on Topic X (e.g., Gap Logo Redesign) in the near future. 6

7. Blog Channels • A blog channel is an event stream of posts or blog entries. • There are links between different blog channels, and links pointing outside of the blogosphere. b1 p1 p7 p10 p4 p6 p8 b2 p3 p5 b3 b4 p9 p2 7

8. Problem Definition • Future Author(ity) Prediction Problem (FAPP) • Given a focal query post on Topic X, what other blog channels (authors) are likely to post on that topic in the (near) future? • The goal is to identify up to K channels that will publish a post on Topic X in the near future X W Y Z X? b1 A X? b2 B D X? b3 C E X? b4 8

9. Features • Content Features • Post Similarity • Profile Similarity • Network Features • Blog-Blog Links • External (non-blog) links 9

10. Prediction Methods • PROF (Profile Based Prediction) • PROF retrieve the Top K blog channels ranked by the their similarity scores to a focal query post q. • VOTE (Voting-Based Prediction) • VOTE chooses the top K channels using the aggregate similarity score of all historical posts in a channel b with a focal query post q. • RSVMP (Ranking SVM Based Prediction) • Content Features • post-post similarity, post-profile similarity, profile-profile similarity, consistency scores, named-entities • Network Features • links, external links 10

11. Dataset and Metrics • Original Data • From Spinn3r, 142 GB, Two months; 44 million blog posts. • Data for experiments • English blog channels only. • Blog channels containing between 30 and 120 posts. • Metric: mean average precision (MAP) 11

12. Results Training data: 30 days Test data (for ground truth): 10 days 12

13. Diffusion Stage The impact of cRatio on the entire test dataset. The impact of cRatio on the “High Consistency” test dataset. 13

14. Impact of Author Distribution • MAP values are highest for high V/AC ratio and consistent blog channels High V/AC: query posts having V/AC [1.5, +∞), calculated in the 10-day test dataset 14

15. Authority • To make good predictions about who is likely to become an authority on a topic, it is important to take in to account network structure as well as content. • This is a limited definition of authority, where authority is defined to be any posting on a topic, but how influential is this blogger? 15

16. Influencejoint work with Forrest Stonedahl and Uri WilenskySupported by NSF Award IIS-0713619

17. 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.

18. NPV of a Network • Calculating the Net Present Value of a Network • Assume a manager can seed an arbitrary fraction of a network and she seeds the most highly influential individuals • Discount rate of .1 (i.e., $1 tomorrow is worth $.90 today) • Then we just add up when people adopt

19. 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)

20. 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?

21. random lattice small-world preferential attachment twitter Experimental Setup • Five networks • Two scenarios: “medium” & “high” virality • 30 genetic algorithm searches to determine the best seeding strategies

24. Best Primary Strategies

25. Optimal Twitter Seeds

26. Alumni Network

27. 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?

28. Trustjoint work with Hossam Sharara and Lise GetoorSupported by NSF Award IIS-0746930 and IIS-1018361

29. Motivation Ann Janet John Bob and Mary will definitely be interested. However, I think Ann is not much into movies Mary WOW… I’ll send it over to everyone MovieRental.com(Refer a friend and get $10 off your next rental) Bob Online Bookstore (Invite a friend and get 10% off your next purchase)

30. Objectives • Capture the diversity in user preferences for different products • Model the change in influence probabilities across multiple campaigns • Design a viral marketing strategy that takes changes in trust based on these factors into account

31. Dataset • Social Network (user-user following links) • 11,942 users • 1.3M follow edges • Digg Network (user-story digging links) • 48,554 news stories • 1.9M digg edges • 6 months (Jul 2010 – Dec 2010)

35. Differential Adaptive Diffusion • The influence probability between two peers (u,v) for product category c can be re-written as Confidence of user vin u at campaign i Confidence of user vin u at campaign i Preference of user vin product type c • The confidence weights are updated at the end of each campaign

36. Experimental Evaluation • Evaluate the model performance in predicting future adoptions • We use the first four months in Digg.com dataset for learning the influence probabilities, and the last two months for testing

37. Results • The Adaptive model, taking both the diffusion dynamics and the users heterogeneity into account, yields better performance

38. 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

39. Experimental Setup • An agent-based model simulates the behavior of customers in different settings • When an agent adopts the product, it makes a probabilistic decision to send a recommendation based on its knowledge about the peers’ preferences • The objective of each agent is to maximize its expected reward according to the existing strategy • Two sets of experiments • Fully observable: The agents are allowed to directly observe the preferences of their peers • Learning preferences: The agents have to learn the peer’s preferences based on their response to previous recommendations

40. Fully Observable • Intermediate values for α (e.g. α = 0.5) consistently maintains high adoption rates and high overall trust over large number of marketing campaigns

41. Learning Preferences • Allowing agents to learn the preferences accounts for both the product preference as well as the confidence level

42. 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.

43. Authority Trust Influence

44. Any Questions?wrand@umd.eduwww.rhsmith.umd.edu/ccb/bit.ly/ccbssrn

45. Best Solution vs. “pure degree” seeding

46. Case Study: Digg.com • Social news website • Users “submit” stories in differenttopics, which can then be “digged”by other users • Users can “follow” other users to get their submissions and diggs on their homepage • Following links define the social network • User submissions serve as proxy of user preferences for different topics • User diggs are analogous to product adoptions

47. Adaptive Viral Marketing • User recommendations are most effective when recommended to the right subset of friends • Highly selective behavior  Limited exposure • Spamming  lower confidence levels, limited returns • What is the appropriate mechanism for maximizing both the product spread and adoption?

48. Kernel Functions • Linear Kernel • If v adopts the product • Each peer u who recommended the product to v gets a credit proportional to the time elapsed (last recommender  max. credit) • If v doesn’t adopt the product • Each peer u who recommended the product to v gets penalized proportional to the time elapsed (last recommender  max. penalty)

49. Experimental Setup • Two sets of experiments • Fully observable: The agents are allowed to directly observe the preferences of their peers • Learning preferences: The agents have to learn the peer’s preferences based on their response to previous recommendations • Simulate the diffusion of 500 campaigns for products from 5 different categories • We use a linear kernel for adjusting the confidence levels between peers after each campaign

50. Effect of Spammers • To test the robustness of our proposed method, we inserted spamming agents in the network • A spamming agent forwards all product recommendation for all its peers, regardless of their preferences • We set (α = 0.5) for all the other agents, and vary the number of seeded spammers