Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
SlideShare a Scribd company logo

Stanford Info Seminar: Unfollowing and Emotion on Twitter

•
•
M
mor

This document summarizes two studies on social dynamics on Twitter. The first study examines the relationship between a user's expression of emotion in tweets and their social network characteristics like number of followers and network density. The second study analyzes what network structure properties like reciprocity and common connections predict whether users will unfollow each other on Twitter. Both studies analyzed data from over 100,000 tweets to understand social information sharing and tie persistence on Twitter.

1 of 45
Downloaded 12 times
Emotion, Tie Persistence, and Network Structure on Twitter Mor Naaman Rutgers SC&I | School Media Information Lab
social media information lab?
social media research: 1. what are people doing (and why)?
social media research: 2. understanding social systems at scale
social media research: 3. creating new experiences
social media awareness streams networks
today’s big story generate a better understanding of the social dynamics validate theories from social sciences in these new and important settings
today’s more specific story Twitter and networks: Part 1. social sharing of emotion and networks on Twitter Part 2. unfollowing on Twitter
study 1 emotion & social networks Kivran-Swaine & Naaman. Network Properties and Social Sharing of Emotions in Social Awareness Streams. (CSCW 2011).
main question How does users’ social sharing of emotion in SAS relate to the properties of their social networks? picture by palo
research questions RQ1 What is the association between people’s tendency to express emotion (joy, sadness, other) in their posts (updates or interactions) and their number of followers?
research questions RQ2 What is the association between people’s tendency to express emotion (joy, sadness, other) in their posts (updates or interactions) and their network characteristics like density and reciprocity rate?
Stanford Info Seminar: Unfollowing and Emotion on Twitter
1.5 step ego-centric network
theory background expression of emotion  number of followers ( - ) people who mostly post about themselves have significantly lower number of followers* ( + ) emotional broadcaster theory * Naaman, Boase, Lai (CSCW 2010)
theory background expression of emotion  network density expression of emotion  reciprocity rate ( + ) intimacy ( - ) curbing
data content dataset from Naaman, Boase, Lai (2010) social network dataset from Kwak et al. (2010) 105,599 messages from 628 users who: had no more than 5,000 followers or followees posted at least one Twitter update in July 2009 in English still had public profile in April 2010
pilot study joy on average 23% of a user’s updates “Fireworks at the Cumming fairgrounds were Yay!” “Just snagged last copy of wii sports resort. awesome. Sophia had a blast. Lucy said, “ooooh,” over and over. Good times with my family.!” sadness on average 10% of a user’s updates “RIP Kathy. Live life for today. You never know how long you have.!”
study details automated analysis of the users’ tweets based on LIWC “expression of emotion” => “existence of emotive words”
some gender differences joy sadness other emotions
analysis independent variables: joy (interactions-updates), sadness (interactions-updates), emo (interactions-updates) 3 linear regression models for dependent variables: number of followers network density reciprocity rate
results … explaining number of followers (R2 = .22) @follower … joy-interactions .35 ** @follower … sadness-interactions .20 ** ** p < .01
results … explaining network density (R2 = .33) yay! joy-updates -.10 ** @follower … sadness-interactions -.18 ** number of followers -.50 ** ** p < .01
limitations & future work better emotion classifier improve sampling, increase dataset culture dependent dyad-level analysis
today’s more specific story Twitter and networks: Part 1. social sharing of emotion and networks on Twitter Part 2. unfollowing on Twitter
study 2 unfollowing on Twitter Kivran-Swaine, Govindan & Naaman. The Impact of Network Structure on Breaking Ties in Online Social Networks: Unfollowing on Twitter. (CHI 2011).
blue=unfollow
main question: what structural properties of the social network of nodes and dyads predict the breaking of ties (unfollows) on Twitter?
theory background tie strength embeddedness within networks power & status
data content dataset from Naaman, Boase, Lai (2010) social network dataset from Kwak et al. (2010) Twitter API – connections still exist 9 months later? 715 seed nodes 245,586 “following” connections to seed nodes 30.6% dropped between 07/2009 & 04/2010
analysis * independent variables (computed for our 245K dyads) seed properties follower-count, follower-to-followee ratio, network density, reciprocity rate, follow-back rate follower properties follower-count, follower-to-followee ratio dyad properties reciprocity, common neighbors, common followers, common friends, right transitivity, left transitivity, mutual transitivity, prestige ratio
<disclaimer> the following slides are NOT scientific evidence and are shown here for illustration purposes no control for intra-seed effects; no inter-variable effects no R installation was harmed in the making of the following figures
effect of number of followers (none):
effect of reciprocity (large):
effect of follow-back rate
effect of common neighbors
</disclaimer> back to scientific results (made R break sweat) sparing you the details, though
in-depth analysis the details you did not want to know… multi-level logistic regression (dyads/edges nested within seed nodes) three models; full one includes seed, follower, and dyadic/edge variables complete details: in the paper
some results effect of tie strength on breaking of ties *** dyadic reciprocity (-) *** network density (-) *** highly statistically significant
some results effect of power & status on breaking of ties *** prestige ratio (+) *** follow-back rate (-) *** f’s follower-to followee ratio (-) *** dyadic reciprocity (-) *** highly statistically significant
some results effect of embeddedness on breaking of ties *** common neighbors (-) *** highly statistically significant
limitations & future work only two snapshots: add more additional (non-structural) variables (e.g., frequency of posting!) emotion and tie breaks
…and even broader what can we learn from social dynamics on Twitter (and Facebook) about: our relationships? our language? our society and culture? our interests and activities?
for more details http://bit.ly/MorInfoSeminar
thank you mornaaman.com mor@rutgers.edu @informor http://bit.ly/MorInfoSeminar Rutgers SC&I Social Media Information Lab

More Related Content

Stanford Info Seminar: Unfollowing and Emotion on Twitter

  • 1. Emotion, Tie Persistence, and Network Structure on Twitter Mor Naaman Rutgers SC&I | School Media Information Lab
  • 3. social media research: 1. what are people doing (and why)?
  • 4. social media research: 2. understanding social systems at scale
  • 5. social media research: 3. creating new experiences
  • 6. social media awareness streams networks
  • 7. today’s big story generate a better understanding of the social dynamics validate theories from social sciences in these new and important settings
  • 8. today’s more specific story Twitter and networks: Part 1. social sharing of emotion and networks on Twitter Part 2. unfollowing on Twitter
  • 9. study 1 emotion & social networks Kivran-Swaine & Naaman. Network Properties and Social Sharing of Emotions in Social Awareness Streams. (CSCW 2011).
  • 10. main question How does users’ social sharing of emotion in SAS relate to the properties of their social networks? picture by palo
  • 11. research questions RQ1 What is the association between people’s tendency to express emotion (joy, sadness, other) in their posts (updates or interactions) and their number of followers?
  • 12. research questions RQ2 What is the association between people’s tendency to express emotion (joy, sadness, other) in their posts (updates or interactions) and their network characteristics like density and reciprocity rate?
  • 15. theory background expression of emotion  number of followers ( - ) people who mostly post about themselves have significantly lower number of followers* ( + ) emotional broadcaster theory * Naaman, Boase, Lai (CSCW 2010)
  • 16. theory background expression of emotion  network density expression of emotion  reciprocity rate ( + ) intimacy ( - ) curbing
  • 17. data content dataset from Naaman, Boase, Lai (2010) social network dataset from Kwak et al. (2010) 105,599 messages from 628 users who: had no more than 5,000 followers or followees posted at least one Twitter update in July 2009 in English still had public profile in April 2010
  • 18. pilot study joy on average 23% of a user’s updates “Fireworks at the Cumming fairgrounds were Yay!” “Just snagged last copy of wii sports resort. awesome. Sophia had a blast. Lucy said, “ooooh,” over and over. Good times with my family.!” sadness on average 10% of a user’s updates “RIP Kathy. Live life for today. You never know how long you have.!”
  • 19. study details automated analysis of the users’ tweets based on LIWC “expression of emotion” => “existence of emotive words”
  • 20. some gender differences joy sadness other emotions
  • 21. analysis independent variables: joy (interactions-updates), sadness (interactions-updates), emo (interactions-updates) 3 linear regression models for dependent variables: number of followers network density reciprocity rate
  • 22. results … explaining number of followers (R2 = .22) @follower … joy-interactions .35 ** @follower … sadness-interactions .20 ** ** p < .01
  • 23. results … explaining network density (R2 = .33) yay! joy-updates -.10 ** @follower … sadness-interactions -.18 ** number of followers -.50 ** ** p < .01
  • 24. limitations & future work better emotion classifier improve sampling, increase dataset culture dependent dyad-level analysis
  • 25. today’s more specific story Twitter and networks: Part 1. social sharing of emotion and networks on Twitter Part 2. unfollowing on Twitter
  • 26. study 2 unfollowing on Twitter Kivran-Swaine, Govindan & Naaman. The Impact of Network Structure on Breaking Ties in Online Social Networks: Unfollowing on Twitter. (CHI 2011).
  • 28. main question: what structural properties of the social network of nodes and dyads predict the breaking of ties (unfollows) on Twitter?
  • 29. theory background tie strength embeddedness within networks power & status
  • 30. data content dataset from Naaman, Boase, Lai (2010) social network dataset from Kwak et al. (2010) Twitter API – connections still exist 9 months later? 715 seed nodes 245,586 “following” connections to seed nodes 30.6% dropped between 07/2009 & 04/2010
  • 31. analysis * independent variables (computed for our 245K dyads) seed properties follower-count, follower-to-followee ratio, network density, reciprocity rate, follow-back rate follower properties follower-count, follower-to-followee ratio dyad properties reciprocity, common neighbors, common followers, common friends, right transitivity, left transitivity, mutual transitivity, prestige ratio
  • 32. <disclaimer> the following slides are NOT scientific evidence and are shown here for illustration purposes no control for intra-seed effects; no inter-variable effects no R installation was harmed in the making of the following figures
  • 33. effect of number of followers (none):
  • 36. effect of common neighbors
  • 37. </disclaimer> back to scientific results (made R break sweat) sparing you the details, though
  • 38. in-depth analysis the details you did not want to know… multi-level logistic regression (dyads/edges nested within seed nodes) three models; full one includes seed, follower, and dyadic/edge variables complete details: in the paper
  • 39. some results effect of tie strength on breaking of ties *** dyadic reciprocity (-) *** network density (-) *** highly statistically significant
  • 40. some results effect of power & status on breaking of ties *** prestige ratio (+) *** follow-back rate (-) *** f’s follower-to followee ratio (-) *** dyadic reciprocity (-) *** highly statistically significant
  • 41. some results effect of embeddedness on breaking of ties *** common neighbors (-) *** highly statistically significant
  • 42. limitations & future work only two snapshots: add more additional (non-structural) variables (e.g., frequency of posting!) emotion and tie breaks
  • 43. …and even broader what can we learn from social dynamics on Twitter (and Facebook) about: our relationships? our language? our society and culture? our interests and activities?
  • 45. thank you mornaaman.com mor@rutgers.edu @informor http://bit.ly/MorInfoSeminar Rutgers SC&I Social Media Information Lab