Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community...

63
Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center for Complex Networks and Systems Research (CNetS) School of Informatics and Computing

Transcript of Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community...

Page 1: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Virality Prediction and Community Structure

in Social NetworksLilian Weng, Filippo Menczer, Yong-Yeol Ahn

Center for Complex Networks and Systems Research (CNetS)School of Informatics and Computing

Page 2: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Uploaded to Youtube on 2012 July 15More than 1.38 billions views now!

Page 3: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Uploaded to Youtube on 2012 July 15More than 1.38 billions views now!

World population7.07 billions

Page 4: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

http://researchinprogress.tumblr.com

As a PhD student:

As a post doc:

We are pleased to inform you that your paper has been accepted!

4 months2.4k FB likes 71 notes

As a professor:

by Nikolaj & Jilles

Page 5: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

CorporationsGovernment

Political Campaigns

Page 6: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center
Page 7: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Virality Attention

Page 8: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Viral information spread through

social networks

Page 9: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Epidemic Spreading:Germs and viruses spread

through the “social” network

Page 10: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Ideas and behaviors also spread

Page 11: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Are they same?

Page 12: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Aha! They are Different

Page 13: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Social ReinforcementMultiple exposures

Page 14: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Social ReinforcementMultiple exposures

Page 15: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Social ReinforcementMultiple exposures

Page 16: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Social ReinforcementMultiple exposures

Page 17: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Social ReinforcementMultiple exposures

Page 18: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

D. Centola, Science 2010

“Small” world“Large” world

Which network is better at spreading information quickly?

Page 19: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Information spread more quickly on “large” world network

D. Centola, Science 2010

Page 20: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Information spread more quickly on “large” world network

Easier to haveMultiple exposure

D. Centola, Science 2010

Page 21: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Information spread more quickly on “large” world network

D. Centola, Science 2010

Page 22: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Information spread more quickly on “large” world network

Harder to haveMultiple exposure

D. Centola, Science 2010

Page 23: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Simple Contagions

Epidemic Spreading:Germs spread through the

“social” network

Page 24: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Ideas and behaviors also spread

D. Centola and M. Macy. Complex Contagions and the Weakness of Long Ties. AJS, 2007.

Complex Contagions

Page 25: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

(Node)Users

Page 26: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

(Edge) Social Relationship

Page 27: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Social Circles(Community)

Page 28: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Social Circles(Community)

Page 29: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

How do communities affect information

diffusion?

Page 30: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Exposures

Figure 1: The importance of community structure in the spreading of social contagions.(A) Structural trapping: dense communities with few outgoing links naturally trap informa-tion flow. (B) Social reinforcement: people who have adopted a meme (black nodes) triggermultiple exposures to others (red nodes). In the presence of high clustering, any additionaladoption is likely to produce more multiple exposures than in the case of low clustering, in-ducing cascades of additional adoptions. (C) Homophily: people in the same community (samecolor nodes) are more likely to be similar and to adopt the same ideas. (D) Diffusion structurebased on retweets among Twitter users sharing the hashtag #USA. Blue nodes represent Englishusers and red nodes are Arabic users. Node size and link weight are proportional to retweet ac-tivity. (E) Community structure among Twitter users sharing the hashtags #BBC and #FoxNews.Blue nodes represent #BBC users, red nodes are #FoxNews users, and users who have used bothhashtags are green. Node size is proportional to usage (tweet) activity, links represent mutualfollowing relations.

10

Structural Trapping

Page 31: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Traps for random walkers

Page 32: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Social Reinforcement

(B) Social Reinforcement

High Clustering Low Clustering

A

MultipleExposures Multiple

Exposures

Figure 1: The importance of community structure in the spreading of social contagions.(A) Structural trapping: dense communities with few outgoing links naturally trap informa-tion flow. (B) Social reinforcement: people who have adopted a meme (black nodes) triggermultiple exposures to others (red nodes). In the presence of high clustering, any additionaladoption is likely to produce more multiple exposures than in the case of low clustering, in-ducing cascades of additional adoptions. (C) Homophily: people in the same community (samecolor nodes) are more likely to be similar and to adopt the same ideas. (D) Diffusion structurebased on retweets among Twitter users sharing the hashtag #USA. Blue nodes represent Englishusers and red nodes are Arabic users. Node size and link weight are proportional to retweet ac-tivity. (E) Community structure among Twitter users sharing the hashtags #BBC and #FoxNews.Blue nodes represent #BBC users, red nodes are #FoxNews users, and users who have used bothhashtags are green. Node size is proportional to usage (tweet) activity, links represent mutualfollowing relations.

10

A AB B

Page 33: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

(C) Homophily

Figure 1: The importance of community structure in the spreading of social contagions.(A) Structural trapping: dense communities with few outgoing links naturally trap informa-tion flow. (B) Social reinforcement: people who have adopted a meme (black nodes) triggermultiple exposures to others (red nodes). In the presence of high clustering, any additionaladoption is likely to produce more multiple exposures than in the case of low clustering, in-ducing cascades of additional adoptions. (C) Homophily: people in the same community (samecolor nodes) are more likely to be similar and to adopt the same ideas. (D) Diffusion structurebased on retweets among Twitter users sharing the hashtag #USA. Blue nodes represent Englishusers and red nodes are Arabic users. Node size and link weight are proportional to retweet ac-tivity. (E) Community structure among Twitter users sharing the hashtags #BBC and #FoxNews.Blue nodes represent #BBC users, red nodes are #FoxNews users, and users who have used bothhashtags are green. Node size is proportional to usage (tweet) activity, links represent mutualfollowing relations.

10

Homophily

Page 34: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Communities trap information.

(1) Structural Trapping(2) Social Reinforcement(3) Homophily

More communication within than across communities;

Page 35: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center
Page 36: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

500 million users340 million tweets per day

Page 37: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Gardenhose (10%)

Page 38: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

FollowSubscribe users

HashtagTopic identifier, i.e. #ows

TweetShort messages

RetweetSpread messages

Mention@users

Page 39: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Hashtag ~ Meme

[1] Richard Dawkins. The Selfish Gene. 1989.

[1]

Page 40: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Hashtag ~ Meme

[1] Richard Dawkins. The Selfish Gene. 1989.

[1]

truthy.indiana.edu

Page 41: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Two community detection methods

Disjoint CommunitiesInfomap (Rosvall & Bergstrom, 2008)

Overlapping Communities

Link clustering (Ahn, Bagrow, Lehmann, 2010)

Page 42: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

BBC News#bbc

Fox News#foxnews

(E) Follower Network

Figure 1: The importance of community structure in the spreading of social contagions.(A) Structural trapping: dense communities with few outgoing links naturally trap informa-tion flow. (B) Social reinforcement: people who have adopted a meme (black nodes) triggermultiple exposures to others (red nodes). In the presence of high clustering, any additionaladoption is likely to produce more multiple exposures than in the case of low clustering, in-ducing cascades of additional adoptions. (C) Homophily: people in the same community (samecolor nodes) are more likely to be similar and to adopt the same ideas. (D) Diffusion structurebased on retweets among Twitter users sharing the hashtag #USA. Blue nodes represent Englishusers and red nodes are Arabic users. Node size and link weight are proportional to retweet ac-tivity. (E) Community structure among Twitter users sharing the hashtags #BBC and #FoxNews.Blue nodes represent #BBC users, red nodes are #FoxNews users, and users who have used bothhashtags are green. Node size is proportional to usage (tweet) activity, links represent mutualfollowing relations.

10

Follower Network

English#usa

Arabic#usa

Figure 1: The importance of community structure in the spreading of social contagions.(A) Structural trapping: dense communities with few outgoing links naturally trap informa-tion flow. (B) Social reinforcement: people who have adopted a meme (black nodes) triggermultiple exposures to others (red nodes). In the presence of high clustering, any additionaladoption is likely to produce more multiple exposures than in the case of low clustering, in-ducing cascades of additional adoptions. (C) Homophily: people in the same community (samecolor nodes) are more likely to be similar and to adopt the same ideas. (D) Diffusion structurebased on retweets among Twitter users sharing the hashtag #USA. Blue nodes represent Englishusers and red nodes are Arabic users. Node size and link weight are proportional to retweet ac-tivity. (E) Community structure among Twitter users sharing the hashtags #BBC and #FoxNews.Blue nodes represent #BBC users, red nodes are #FoxNews users, and users who have used bothhashtags are green. Node size is proportional to usage (tweet) activity, links represent mutualfollowing relations.

10

Retweet Network

Page 43: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Do the edges inside communities transmit

more information?

Page 44: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

For each community, we measure the average edge weights of intra-

and inter-community links.

wRT w@ wRT w@

(A)

Figure 2: Meme concentration in communities. We show (A) community edge weight and(B) user community focus using box plots. Boxes cover 50% of data and whisker cover 95%.The line and triangle in a box represent the median and mean, respectively. Changes in memeconcentration as a function of meme popularity are illustrated by plotting (C) meme usagedominance, (D) meme usage entropy, (E) meme adopter dominance, and (F) meme adopterentropy. Dominance and entropy ratios are averaged across hashtags in each popularity bin,with popularity defined as number of tweets T or adopters U ; error bars indicate standard errors.Gray areas represent the ranges of popularity in which actual data exhibit weaker concentrationthan the baseline model M2. Similar results for different types of networks and communitymethods are described in Supplementary Information.

11

Page 45: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

f RT f RTf @ f @

(B)

Figure 2: Meme concentration in communities. We show (A) community edge weight and(B) user community focus using box plots. Boxes cover 50% of data and whisker cover 95%.The line and triangle in a box represent the median and mean, respectively. Changes in memeconcentration as a function of meme popularity are illustrated by plotting (C) meme usagedominance, (D) meme usage entropy, (E) meme adopter dominance, and (F) meme adopterentropy. Dominance and entropy ratios are averaged across hashtags in each popularity bin,with popularity defined as number of tweets T or adopters U ; error bars indicate standard errors.Gray areas represent the ranges of popularity in which actual data exhibit weaker concentrationthan the baseline model M2. Similar results for different types of networks and communitymethods are described in Supplementary Information.

11

For each user, we measure fraction of activity that is directed to each neighbor

in the same or different community.

Page 46: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Is the communication concentrated inside

communities?

Page 47: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

No concentrationRandomly distributed

Page 48: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Weak concentrationRandomly diffusion

Page 49: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Distributed more in a few communities

Strong Concentration

Page 50: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Null models

Random selection

Random diffusion(structural trapping)

M1

M2

Page 51: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Real(C)

Figure 2: Meme concentration in communities. We show (A) community edge weight and(B) user community focus using box plots. Boxes cover 50% of data and whisker cover 95%.The line and triangle in a box represent the median and mean, respectively. Changes in memeconcentration as a function of meme popularity are illustrated by plotting (C) meme usagedominance, (D) meme usage entropy, (E) meme adopter dominance, and (F) meme adopterentropy. Dominance and entropy ratios are averaged across hashtags in each popularity bin,with popularity defined as number of tweets T or adopters U ; error bars indicate standard errors.Gray areas represent the ranges of popularity in which actual data exhibit weaker concentrationthan the baseline model M2. Similar results for different types of networks and communitymethods are described in Supplementary Information.

11

Proportion of #tweets in dominant

community

Total #tweets

Relative Usage Dominance

Page 52: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

f ff f

Real (D)

Figure 2: Meme concentration in communities. We show (A) community edge weight and(B) user community focus using box plots. Boxes cover 50% of data and whisker cover 95%.The line and triangle in a box represent the median and mean, respectively. Changes in memeconcentration as a function of meme popularity are illustrated by plotting (C) meme usagedominance, (D) meme usage entropy, (E) meme adopter dominance, and (F) meme adopterentropy. Dominance and entropy ratios are averaged across hashtags in each popularity bin,with popularity defined as number of tweets T or adopters U ; error bars indicate standard errors.Gray areas represent the ranges of popularity in which actual data exhibit weaker concentrationthan the baseline model M2. Similar results for different types of networks and communitymethods are described in Supplementary Information.

11

Entropy of #tweets distributed in

different communities

Total #tweets

Relative Usage Entropy

Page 53: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Viral memes are less trapped by communities, spreading like diseases.

Page 54: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Viral memes

(B) Social Reinforcement

High Clustering Low Clustering

(A) Structural Trapping (C) Homophily

(D) Retweet Network

A

MultipleExposures Multiple

Exposures

(E) Follower Network

Figure 1: The importance of community structure in the spreading of social contagions.(A) Structural trapping: dense communities with few outgoing links naturally trap informa-tion flow. (B) Social reinforcement: people who have adopted a meme (black nodes) triggermultiple exposures to others (red nodes). In the presence of high clustering, any additionaladoption is likely to produce more multiple exposures than in the case of low clustering, in-ducing cascades of additional adoptions. (C) Homophily: people in the same community (samecolor nodes) are more likely to be similar and to adopt the same ideas. (D) Diffusion structurebased on retweets among Twitter users sharing the hashtag #USA. Blue nodes represent Englishusers and red nodes are Arabic users. Node size and link weight are proportional to retweet ac-tivity. (E) Community structure among Twitter users sharing the hashtags #BBC and #FoxNews.Blue nodes represent #BBC users, red nodes are #FoxNews users, and users who have used bothhashtags are green. Node size is proportional to usage (tweet) activity, links represent mutualfollowing relations.

10

Just thisOther memes

Page 55: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Viral memes

(B) Social Reinforcement

High Clustering Low Clustering

(A) Structural Trapping (C) Homophily

(D) Retweet Network

A

MultipleExposures Multiple

Exposures

(E) Follower Network

Figure 1: The importance of community structure in the spreading of social contagions.(A) Structural trapping: dense communities with few outgoing links naturally trap informa-tion flow. (B) Social reinforcement: people who have adopted a meme (black nodes) triggermultiple exposures to others (red nodes). In the presence of high clustering, any additionaladoption is likely to produce more multiple exposures than in the case of low clustering, in-ducing cascades of additional adoptions. (C) Homophily: people in the same community (samecolor nodes) are more likely to be similar and to adopt the same ideas. (D) Diffusion structurebased on retweets among Twitter users sharing the hashtag #USA. Blue nodes represent Englishusers and red nodes are Arabic users. Node size and link weight are proportional to retweet ac-tivity. (E) Community structure among Twitter users sharing the hashtags #BBC and #FoxNews.Blue nodes represent #BBC users, red nodes are #FoxNews users, and users who have used bothhashtags are green. Node size is proportional to usage (tweet) activity, links represent mutualfollowing relations.

10

Just thisOther memes

Simple Contagions

Complex Contagions

Page 56: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Avg. #exposures required for each

adopters

Total #tweets

Page 57: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Complex Contagions

Simple Contagions

No enough data

Page 58: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Maybe....We can do virality prediction by

qualifying concentration?

Page 59: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Old New Less dominant More dominant

Early Stage Late Stage

(A) #ThoughtsDuringSchool

Early Stage Late Stage

(B) #ProperBand

Figure 4: Evolution of two contrasting memes (viral vs. non-viral) in terms of commu-nity structure. We represent each community as a node, whose size is proportional to thenumber of tweets produced by the community. The color of a community represents thetime when the hashtag is first used in the community. (A) The evolution of a viral meme(#ThoughtsDuringSchool) from the early stage (30 tweets) to the late stage (200 tweets) ofdiffusion. (B) The evolution of a non-viral meme (#ProperBand) from the early stage (30tweets) to the final stage (65 tweets).

13

30 tweets

30 tweets

Page 60: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Old New Less dominant More dominant

Early Stage Late Stage

(A) #ThoughtsDuringSchool

Early Stage Late Stage

(B) #ProperBand

Figure 4: Evolution of two contrasting memes (viral vs. non-viral) in terms of commu-nity structure. We represent each community as a node, whose size is proportional to thenumber of tweets produced by the community. The color of a community represents thetime when the hashtag is first used in the community. (A) The evolution of a viral meme(#ThoughtsDuringSchool) from the early stage (30 tweets) to the late stage (200 tweets) ofdiffusion. (B) The evolution of a non-viral meme (#ProperBand) from the early stage (30tweets) to the final stage (65 tweets).

13

30 tweets

30 tweets

200 tweets

65 tweets

Page 61: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Prec

isio

n

Community-based predictionCommunity-blind predictionRandom guess

(A) (B)

(C) (D)

Reca

ll

0.250.20

0.12

0.50 0.48

0.28

0.780.71

0.50

0.0

0.2

0.4

0.6

0.8

300 500 1000

0.210.15 0.11

0.52

0.350.29

0.760.67

0.49

0.0

0.2

0.4

0.6

0.8

300 500 1000

0.250.19 0.12

0.390.31

0.08

0.55 0.53

0.24

0.0

0.2

0.4

0.6

0.8

300 500 1000

0.220.14 0.11

0.41

0.21

0.08

0.600.49

0.23

0.0

0.2

0.4

0.6

0.8

300 500 1000

Figure 3: Prediction performance. We predict whether a meme will go viral or not; a meme islabeled as viral if it produces more than a certain threshold (q = 300,500,1000) of tweets (T ) oradopters (U). We use the random forests classifier trained on community concentration features,which are calculated based on the initial n = 50 tweets for each meme. Prediction resultsare robust across different networks and community detection methods (see SupplementaryInformation). We compute precision and recall to compare our prediction results against twobaselines.

12

Viral memes tweets.� ⇥T

Prec

isio

n

Community-based predictionCommunity-blind predictionRandom guess

(A) (B)

(C) (D)

Reca

ll

0.250.20

0.12

0.50 0.48

0.28

0.780.71

0.50

0.0

0.2

0.4

0.6

0.8

300 500 1000

0.210.15 0.11

0.52

0.350.29

0.760.67

0.49

0.0

0.2

0.4

0.6

0.8

300 500 1000

0.250.19 0.12

0.390.31

0.08

0.55 0.53

0.24

0.0

0.2

0.4

0.6

0.8

300 500 1000

0.220.14 0.11

0.41

0.21

0.08

0.600.49

0.23

0.0

0.2

0.4

0.6

0.8

300 500 1000

Figure 3: Prediction performance. We predict whether a meme will go viral or not; a meme islabeled as viral if it produces more than a certain threshold (q = 300,500,1000) of tweets (T ) oradopters (U). We use the random forests classifier trained on community concentration features,which are calculated based on the initial n = 50 tweets for each meme. Prediction resultsare robust across different networks and community detection methods (see SupplementaryInformation). We compute precision and recall to compare our prediction results against twobaselines.

12

⇥T ⇥T

Prec

isio

n

Community-based predictionCommunity-blind predictionRandom guess

(A) (B)

(C) (D)

Reca

ll

0.250.20

0.12

0.50 0.48

0.28

0.780.71

0.50

0.0

0.2

0.4

0.6

0.8

300 500 1000

0.210.15 0.11

0.52

0.350.29

0.760.67

0.49

0.0

0.2

0.4

0.6

0.8

300 500 1000

0.250.19 0.12

0.390.31

0.08

0.55 0.53

0.24

0.0

0.2

0.4

0.6

0.8

300 500 1000

0.220.14 0.11

0.41

0.21

0.08

0.600.49

0.23

0.0

0.2

0.4

0.6

0.8

300 500 1000

Figure 3: Prediction performance. We predict whether a meme will go viral or not; a meme islabeled as viral if it produces more than a certain threshold (q = 300,500,1000) of tweets (T ) oradopters (U). We use the random forests classifier trained on community concentration features,which are calculated based on the initial n = 50 tweets for each meme. Prediction resultsare robust across different networks and community detection methods (see SupplementaryInformation). We compute precision and recall to compare our prediction results against twobaselines.

12

Page 62: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Summary•Communities give us invaluable information about

spreading patterns of memes.

•We can predict viral memes by looking at communities

•Non-viral memes seems to act like complex contagions, strongly affected by social reinforcement and homophily, while viral memes are not.

•Viral memes spread like (literally) epidemics.

Page 63: Virality Prediction and Community Structure in Social Networks · Virality Prediction and Community Structure in Social Networks Lilian Weng, Filippo Menczer, Yong-Yeol Ahn Center

Thanks! Questions?

Lilian Weng Fil Menczer YY Ahn

{weng, fil, yyahn}@indiana.edu