Limits...
Predictability of extreme events in social media.

Miotto JM, Altmann EG - PLoS ONE (2014)

Bottom Line: It is part of our daily social-media experience that seemingly ordinary items (videos, news, publications, etc.) unexpectedly gain an enormous amount of attention.Here we investigate how unexpected these extreme events are.This indicates that, despite the inherently stochastic collective dynamics of users, efficient prediction is possible for the most successful items.

View Article: PubMed Central - PubMed

Affiliation: Max Planck Institute for the Physics of Complex Systems, Dresden, Germany.

ABSTRACT
It is part of our daily social-media experience that seemingly ordinary items (videos, news, publications, etc.) unexpectedly gain an enormous amount of attention. Here we investigate how unexpected these extreme events are. We propose a method that, given some information on the items, quantifies the predictability of events, i.e., the potential of identifying in advance the most successful items. Applying this method to different data, ranging from views in YouTube videos to posts in Usenet discussion groups, we invariantly find that the predictability increases for the most extreme events. This indicates that, despite the inherently stochastic collective dynamics of users, efficient prediction is possible for the most successful items.

Show MeSH
Dynamics of views in YouTube.Colored histograms: distributions of views at fixed times after publication (0.3 million videos from our database). Gray lines at the bottom: trajectories of  videos which had the same early success ( views  days after publication). Black histogram: distribution of views of the  selected videos  months after publication.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4219754&req=5

pone-0111506-g001: Dynamics of views in YouTube.Colored histograms: distributions of views at fixed times after publication (0.3 million videos from our database). Gray lines at the bottom: trajectories of videos which had the same early success ( views days after publication). Black histogram: distribution of views of the selected videos months after publication.

Mentions: Universal features of heavy-tailed distributions do not easily lead to a good forecast of specific items [5], a problem of major fundamental and practical interest [15]–[19]. This is illustrated in Fig. 1, which shows that the heavy-tailed distribution appears at very short times but items with the same early success have radically different future evolutions. The path of each item is sensitively dependent on idiosyncratic decisions which may be amplified through collective phenomena. An important question is how to quantify the extent into which prediction of individual items is possible (i.e., their predictability) [20]. Of particular interest –in social and natural systems– is the predictability of extreme events [21]–[26], the small number of items in the tail of the distribution that gather a substantial portion of the public attention.


Predictability of extreme events in social media.

Miotto JM, Altmann EG - PLoS ONE (2014)

Dynamics of views in YouTube.Colored histograms: distributions of views at fixed times after publication (0.3 million videos from our database). Gray lines at the bottom: trajectories of  videos which had the same early success ( views  days after publication). Black histogram: distribution of views of the  selected videos  months after publication.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4219754&req=5

pone-0111506-g001: Dynamics of views in YouTube.Colored histograms: distributions of views at fixed times after publication (0.3 million videos from our database). Gray lines at the bottom: trajectories of videos which had the same early success ( views days after publication). Black histogram: distribution of views of the selected videos months after publication.
Mentions: Universal features of heavy-tailed distributions do not easily lead to a good forecast of specific items [5], a problem of major fundamental and practical interest [15]–[19]. This is illustrated in Fig. 1, which shows that the heavy-tailed distribution appears at very short times but items with the same early success have radically different future evolutions. The path of each item is sensitively dependent on idiosyncratic decisions which may be amplified through collective phenomena. An important question is how to quantify the extent into which prediction of individual items is possible (i.e., their predictability) [20]. Of particular interest –in social and natural systems– is the predictability of extreme events [21]–[26], the small number of items in the tail of the distribution that gather a substantial portion of the public attention.

Bottom Line: It is part of our daily social-media experience that seemingly ordinary items (videos, news, publications, etc.) unexpectedly gain an enormous amount of attention.Here we investigate how unexpected these extreme events are.This indicates that, despite the inherently stochastic collective dynamics of users, efficient prediction is possible for the most successful items.

View Article: PubMed Central - PubMed

Affiliation: Max Planck Institute for the Physics of Complex Systems, Dresden, Germany.

ABSTRACT
It is part of our daily social-media experience that seemingly ordinary items (videos, news, publications, etc.) unexpectedly gain an enormous amount of attention. Here we investigate how unexpected these extreme events are. We propose a method that, given some information on the items, quantifies the predictability of events, i.e., the potential of identifying in advance the most successful items. Applying this method to different data, ranging from views in YouTube videos to posts in Usenet discussion groups, we invariantly find that the predictability increases for the most extreme events. This indicates that, despite the inherently stochastic collective dynamics of users, efficient prediction is possible for the most successful items.

Show MeSH