Tom Broxton el al., Catching a viral video, J Intell Inf Syst 2011

Citation

Tom Broxton and Yannet Interian and Jon Vaver and Mirjam Wattenhofer: Catching a viral video. Journal of Intelligent Information Systems 2011: 1-19.

Online version

[1]

Summary

This is a paper of Google Research introducing the preliminary analysis on viral videos [2](YouTube Analysis). The data set used in the study is a large-scale and confidential data set, thus the revealed conclusion from which is considerable valuable. Specifically it analyzes the correlation between the degree of social sharing and the video view growth, the video category and the social sites linking to it.

Different research reaches the same conclusion that the most distinguishing characteristic of the viral video is its lifespan. Compared with "popular videos" which are also capable of attracting large number of views, the viral videos gain traction in social media quickly and fade quickly as well.

Data set

1.5 million video randomly selected from the set of video uploaded to YouTube between Apirl 2009 and March 2010. Each video is associated with the meta-data including its category, the number of view at daily level and most importantly the "referrer" (It seems impossible for obtain such information outside of Google) which accounts the source from which the user came to watch a particular video. The authors further classify the referrer into social and non-social categories:

• Social: External link and embeds (from a social site such as Facebook, blogs or instant messages) and Unknown (the user typed or copied URL into browser)

• Non-social: Youtube internal link (related or recommended videos) and Youtube search(found by an search engine).

Conclusions

First of all, the authors categorize the videos into 10 group according to their level of "socialness" which is quantified by the fraction of social views during the first 30 days of viewing. The least social group has 0.0 to 6.1% social views whereas the most social group enjoys 81.8 to 100% social views (the number of videos in each group is approximately the same).

Socialness & view growth

Fig.3(a) and Fig.3(b) illustrate the pattern of the view growth from three socialness segments from which which the following observations could be reached:

Fig.3(a) growth of relative views from three video segments

Fig.3(b) growth of absolute views from three video segments

• Observation I: The videos with higher socialness has the highest growth leading up to the peak as well as the highest declination rate.

• Observation II: The videos with higher socialness enjoys the peaks that are systematically higher than less social videos.

Socialness & categories

Different measurement for the level of socialness would yields different categories that are most social, see Fig.5.

Fig.5 Three measures for ranking the level of sharing within video categories

• Observation III: In terms of the fraction of videos within the category that are highly social, the most social category is "Pets & Animal"; in terms of the fraction of views within the category that are social the category becomes "Education"; Regarding the absolute number of social views within category the answer is "Music".

If Facebook and Twitter are regarded as two categories representing social network sites and micro-blogs they found:

• Observation IV: The Twitter views (by a factor of 4.5) are more highly concentrated near the day of peak viewing than the Facebook views (by a factor of 2.4) which may be result of Twitter's real-time sharing paradigm. In addition the Twitter views are more likely to be associated with highly shared videos than Facebook views are.

Viral vs. Popular videos

The authors track two videos a viral video and a popular music video which received most of its views from searches. They found that

• Observation V: The viral video tends to peak more sharply and wane more rapidly whereas the popular music video exhibits a steady and regular growth pattern after the peak view.

• Observation VI: YouTube related video and search are the other two major reasons account for large number of views besides the social sharing. Most of the popular videos (top 1% videos in terms of views) result from the related videos and search.

If defining popular ratio as:

$PR(video)={\frac {\text{Views in the Second Month}}{\text{Views in the First Ten Days}}}\,$

A video is called short-term popular if its PR is low and the one with large PR is called long-term popular, see Fig 12.

Fig.12 Density of percent of social views for popular videos in the first ten days

• Observation VII: the density of viral and non-viral videos in short-term popular videos set are similar. However, almost no viral videos belongs to the long-term popular videos (because viral video fade quickly after its peek view).

Ranking social sites

By the viral videos, the authors propose a method to rank the social blogs in terms of their propensity of spreading the viral videos. Let $V_{p}\,$ be the set of viral videos (with at least 60% of social views in the first month) and $V_{u}\,$ as the set of unpopular videos (with less than 100 views in the first 30 days) and $W_{100}(u)\,$ be the set of videos with at least of 100 views from url u.

$r(u)={\frac {|V_{p}\cap W_{100}(u)|}{|V_{p}\cup V_{u}|}}\,$

r(u) is applied to filter out ($r(u)<r_{low}\,$) some outliers such as Facebook. For each video $v\in V_{p}\,$, $views(u,v)\,$ denotes its number of view coming from url u. Based on the notions, the rank function for each url becomes:

$R(u)=\sum _{v\in V_{p}}views(u,v)\,$

Tab.2 Viral video rank for top 25 urls

The author perform the ranking function through all external links and rank social blogs in terms of their propensity of spreading the viral videos. Tab. 2 presents top 25 sites. To verify the ranking list they compare against the rank on technorati.com which applies different methods for ranking blogs. Though the ranking function seems simple, the comparison demonstrates that their method exhibits a reasonable correlation with the rank list from technorati.com.

Related Papers

There is a paper highly cited paper approaching the similar problem: Gábor Szabó, Bernardo A. Huberman: Predicting the popularity of online content. Commun. ACM 53(8): 80-88 (2010)[3]