attention and bias in social information networks
DESCRIPTION
Talk at Workshop on Information Neworks, NYU Stern, 2011TRANSCRIPT
ATTENTION AND BIAS IN SOCIAL INFORMATION NETWORKSSCOTT COUNTS, MICROSOFT RESEARCH
flickr: alshepmcr
Looking time per tweet is short, memory is poor.
Looking time per tweet is short, memory is poor.
Looking time per tweet is short, memory is poor.
Including links, RTs, heavy tweeting all decrease attention and/or interest.
Including links, RTs, heavy tweeting all decrease attention and/or interest.
Including links, RTs, heavy tweeting all decrease attention and/or interest.
Including links, RTs, heavy tweeting all decrease attention and/or interest.
Personal contacts increase attention and memory.
Counts, S., & Fisher, K. (2011). Taking It All In? Visual Attention in Microblog Consumption. In Proc. ICWSM ‘11.
PROBLEM STATEMENT
How does a user’s name influence perception of her and her content?
ANONYMOUS SURVEY SCREEN
NON-ANONYMOUS SURVEY SCREEN
RESULTS – AUTHOR RATINGS
Fairly bimodal distributionsDownward shift in ratings when non-anonymous
RESULTS – RATING DISTRIBUTION
Good author get higher ratings when non-anon.Bad authors hurt most by namesAverage authors similar to good (KL div = .02) but hurt by name (KL div = .23; p < .001)
RESULTS – RATINGS & FOLLOWER COUNT
Results tighten up with names: R2 = .16 -> .21High follower count people get biggest boostMiddle group hurt
Pal, A., & Counts, S. (2011). What’s In a @Name? How Name Value Biases Judgment of Microblog Authors. In Proc. ICWSM ‘11.
CREDIBILITY AND TRUTH
CREDIBILITY AND TRUTH
CREDIBILITY AND TRUTH
CREDIBILITY AND TRUTH
CREDIBILITY AND TRUTH
CREDIBILITY AND TRUTH*
Name type impacts tweet and author credibilityCorrelations between truth and tweet (r = .39) and author (r = .29) modest
* Morris, M., Counts, S., Roseway, A., Hoff, A., & Schwartz, J. (2011). Under review.
BRINGING IT TOGETHER
BRINGING IT TOGETHER
Minimal visual processing/attention
Poor memory encoding
BRINGING IT TOGETHER
Minimal visual processing/attention
Poor memory encoding
Difficulty in determining truthfulness
Systematic use of heuristics (biases)
Friends
Name value
BRINGING IT TOGETHER
Minimal visual processing/attention
Poor memory encoding
Difficulty in determining truthfulness
Systematic use of heuristics (biases)
Friends
Name value
** Peripheral processing route **
IMPLICATIONS
IMPLICATIONS
Effective reach of social media
IMPLICATIONS
Effective reach of social media
Information diffusion
IMPLICATIONS
Effective reach of social media
Information diffusion
Social contagion: Stickiness* (increased adoption and sustained product use) and memory for content
* Aral, S., & Walker, D. (2010). Creating Social Contagion Through Viral Product Design: A Randomized Trial of Peer Influence Networks. Management Science.
ATTENTION AND BIAS IN SOCIAL INFORMATION NETWORKS
SCOTT COUNTS, MICROSOFT RESEARCH
low level :: your brain on facebook*
* Fisher, K., & Counts, S. (2010). Your Brain on Facebook: Neuropsychological Associations with Social Versus Other Media. In Proc. ICWSM ‘10.
social information networks :: levels of analysis
Math/Theory
Social media analytics
Computer-Mediated Communication
Social Cognition
Physiological
RESULTS – FACTORS FOR BIAS: GENDER
Most top authors are gender neutral (e.g., Time, Mashable)Men higher than women when anonymous, but drop more when names shownWomen get slight bump when names shown
Pal, A., & Counts, S. (2011). What’s In a @Name? How Name Value Biases Judgment of Microblog Authors. In Proc. ICWSM ‘11.
social information networks :: levels of analysis
Math/Theory
Social media analytics
Computer-Mediated Communication
Social Cognition
Physiological
PROBLEM STATEMENT
How does a user’s name influence perception of her and her content?
PROBLEM STATEMENT
How does a user’s name influence perception of her and her content?