COMP 621U WEEK 3 SOCIAL INFLUENCE AND NFORMAT|○ND|FFUS|ON Nathan Liu (nliu(@cse. Ust. hk)
COMP 621U WEEK 3 SOCIAL INFLUENCE AND INFORMATION DIFFUSION Nathan Liu (nliu@cse.ust.hk)
What are social Influences 口| nfluence: a People make decisions sequentially a Actions of earlier people affect that of later people a two class of rational reasons for influence: a Direct benefit: Phone becomes more Useful if more people use it a Informational: Choosing restaurants a Influences are the results of rational inferences from limited information
What are Social Influences? Influence: People make decisions sequentially Actions of earlier people affect that of later people Two class of rational reasons for influence: Direct benefit: ◼ Phone becomes more useful if more people use it Informational: ◼ Choosing restaurants Influences are the results of rational inferences from limited information. 2
Herding: Simple Experiment Consider an urn with 3 ball. It can be either: a Majority-blue: 2 blue 1 red a Majority-red: 2 red, 1 blue n Each person wants to best guess whether the urn is majority is majority-blue or majority-red n Experiment: One by one each person a Draws a ball a Privately looks at its color ad puts it back a Publicly announces his quess o Everyone see all the guesses beforehand 口 How should you guess?
Herding: Simple Experiment Consider an urn with 3 ball. It can be either: Majority-blue: 2 blue 1 red Majority-red: 2 red, 1 blue Each person wants to best guess whether the urn is majority is majority-blue or majority-red: Experiment: One by one each person: Draws a ball Privately looks at its color ad puts it back Publicly announces his guess Everyone see all the guesses beforehand How should you guess? 3
Herding: What happens 口 What happens? a is person: guess the color drawn a 2nd person: guess the color drawn person: If the two before made different guesses then go with his own color Else: just go with their guess(regardless of the color you see o Can be modeled Bayesian rule( the first two guesses may bias the prior) a P(RIrrb)=P(rrb R)P(R)/P(rrb)=2/3 口 Non-optimal outcome: a With prob 1/3x1 3=1 /9, the first two would see the wrong color from then on the whole population would guess wrong
Herding: What happens? What happens? 1 st person: guess the color drawn 2 nd person: guess the color drawn 3 rd person: ◼ If the two before made different guesses, then go with his own color ◼ Else: just go with their guess (regardless of the color you see) Can be modeled Bayesian rule(the first two guesses may bias the prior) P(R|rrb)=P(rrb|R)P(R)/P(rrb)=2/3 Non-optimal outcome: With prob 1/3×1/3=1/9, the first two would see the wrong color, from then on the whole population would guess wrong 4
Examples: Information Diffusion 5 obscure technology ry tech blog Slashdot high-profile blog Wired New Scientist SJ Merc New York BBC Times
Examples: Information Diffusion 5
Example: Viral Propagation
Example: Viral Propagation 6
Example: Viral Marketing a Recommendation referral program a Senders and followers of recommendations receive discounts on products 1o% credit 10% off
Example: Viral Marketing Recommendation referral program: Senders and followers of recommendations receive discounts on products 7
Early Empirical Studies of Diffusion and Influence 8 a Sociological study of diffusion of innovation a Spread of new agricultural practices[Ryan-Gross 1943 Studied the adoption of a new hybrid -corn between the 259 farmers in lowa Found that interpersonal network plays important role a Spread of new medical practices [Coleman et al 1966 Studied the adoption of new drug between doctors in lllinois Clinical studies and scientific evaluation were not sufficient to convince doctors It was the social power of peers that led to adoption n The contagion of obesity [Christakis et al. 2007 a If you have an overweight friend, your chance of becoming obese by57%! increase by
Early Empirical Studies of Diffusion and Influence Sociological study of diffusion of innovation: Spread of new agricultural practices[Ryan-Gross 1943] ◼ Studied the adoption of a new hybrid-corn between the 259 farmers in Iowa ◼ Found that interpersonal network plays important role Spread of new medical practices [Coleman et al 1966] ◼ Studied the adoption of new drug between doctors in Illinois ◼ Clinical studies and scientific evaluation were not sufficient to convince doctors ◼ It was the social power of peers that led to adoption The contagion of obesity [Christakis et al. 2007] If you have an overweight friend, your chance of becoming obese increase by 57%! 8
Applications of social Influence Models 9 Backward network Forward network engineering engineering Backward Learn from Forward predictions observed data predictions a Forward Predictions: viral marketing influence maximization a Backward Predictions: effector/initiator finding, sensor placement cascade detection
Applications of Social Influence Models Forward Predictions: viral marketing, influence maximization Backward Predictions: effector/initiator finding, sensor placement, cascade detection Forward network engineering Backward predictions Forward predictions Backward network engineering Learn from observed data 9
Dynamics of Viral Marketing (Leskovec 07) Senders and followers of recommendations receive discounts on prodUCtS 10% credit it 10%of Recommendations are made to any number of people at the time of purchase Only the recipient who buys first gets a discount
10 Dynamics of Viral Marketing (Leskovec 07) Senders and followers of recommendations receive discounts on products 10% credit 10% off ◼ Recommendations are made to any number of people at the time of purchase ◼ Only the recipient who buys first gets a discount 10
