{"id":324,"date":"2012-02-15T18:45:40","date_gmt":"2012-02-15T18:45:40","guid":{"rendered":"http:\/\/rulesofreason.wordpress.com\/?p=324"},"modified":"2012-02-15T18:45:40","modified_gmt":"2012-02-15T18:45:40","slug":"google-tries-to-find-the-funniest-videos","status":"publish","type":"post","link":"http:\/\/re-design.dimiter.eu\/?p=324","title":{"rendered":"Google tries to find the funniest videos"},"content":{"rendered":"

Following my recent post<\/a> on the project which tries to explain why some video clips go viral, here is a report<\/a> on Google’s efforts to find the funniest videos:<\/p>\n

You\u2019d think the reasons for something being funny were beyond the reach of science \u2013 but Google\u2019s brain-box researchers have managed to come up with a formula for working out which YouTube video clips are the funniest.<\/p><\/blockquote>\n

The Google researcher behind the project is quoted saying:<\/p>\n

\u2018If a user uses an \u201cloooooool\u201d vs an \u201cloool\u201d, does it mean they were more amused? We designed features to quantify the degree of emphasis on words associated with amusement in viewer comments.\u2019<\/p><\/blockquote>\n

Other factors taken into account are tags, descriptions, and ‘whether audible laughter can be heard in the background<\/em>‘. Ultimately, the algorithm gives a ranking of the funniest videos \u00a0(with No No No No Cat<\/a> on top, since you asked).<\/p>\n

Now I usually have high respect for all things Google, but this ‘research’ at first appeared to be a total piece of junk. Of course, it turned out that it is just the way it is reported by the Daily Mail (cited above), New Scientist<\/a> and countless other more or less reputable outlets.<\/p>\n

Google’s new algorithm does not provide a normative ranking<\/strong>\u00a0of the funniest videos ever based on some objective criteria; it is a\u00a0predictive<\/strong> score about the video’s comedic potential. Google trained the algorithm on a bunch of videos (it’s unclear from the original source<\/a> what the external ‘fun’ measure used for the training part was) in order to inductively extract features \u00a0associated with the video being funny. Based on these features, the program can then score any possible video. But these scores are not normative measures, they are predictions. So No No No No Cat<\/a> is not the funniest video ever [well, it might be, it’s pretty hilarious actually]<\/em>, it is Google’s safest bet that the video would be considered funny.<\/p>\n

The story is worth mentioning not only because it exposes yet another case of gross misinterpretation of a scientific project in the news, but because it nicely illustrates the differences between measurement, prediction, and explanation. The newspapers have taken Google’s project to be an exercise in measurement<\/strong>. As explained above, the goal is actually predictive<\/strong>\u00a0in nature. But even if the algorithm has 100% success rate in identifying potentially funny videos, that would still not count as an explanation<\/strong> of what makes a video funny. Just think about it – would a boring video become funny if we just put funny tags, background laughter, and plenty of \u00a0loools in the comments? Not really. In that respect Brent Coker’s approach<\/a>, which I mentioned in a previous post, has real explanatory potential (although I doubt whether it has any explanatory power).<\/p>\n

So, no need to panic, the formula for something being funny<\/em> is as distant as ever.<\/p>\n

P.S.<\/em> In an ironic turn of events, now that\u00a0 No No No No Cat<\/a> has<\/strong> gone viral, Google would never know whether the algorithm was very good, or just everyone wanted to see the video Google declared the funnies ever. Ah, the joys of social science research!<\/p>\n","protected":false},"excerpt":{"rendered":"

Following my recent post on the project which tries to explain why some video clips go viral, here is a report on Google’s efforts to find the funniest videos: You\u2019d think the reasons for something being funny were beyond the reach of science \u2013 but Google\u2019s brain-box researchers have managed to come up with a formula for working out which YouTube video clips are the funniest. The Google researcher behind the project is quoted saying: \u2018If a user uses an \u201cloooooool\u201d vs an \u201cloool\u201d, does it mean they were more amused? We designed features to quantify the degree of emphasis on words associated with amusement in viewer comments.\u2019 Other factors taken into account are tags, descriptions, and ‘whether audible laughter can be heard in the background‘. Ultimately, the algorithm gives a ranking of the funniest videos \u00a0(with No No No No Cat on top, since you asked). Now I usually have high respect for all things Google, but this ‘research’ at first appeared to be a total piece of junk. Of course, it turned out that it is just the way it is reported by the Daily Mail (cited above), New Scientist and countless other more or less reputable outlets. Google’s new algorithm does not provide a normative ranking\u00a0of the funniest videos ever based on some objective criteria; it is a\u00a0predictive score about the video’s comedic potential. Google trained the algorithm on a bunch of videos (it’s unclear from the original source what the external ‘fun’ measure used for the…<\/p>\n

Continue readingGoogle tries to find the funniest videos<\/span><\/a><\/div>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"spay_email":"","jetpack_publicize_message":"","jetpack_is_tweetstorm":false},"categories":[3,8,20],"tags":[137,284,513,516,534,576,583,680,698],"jetpack_featured_media_url":"","jetpack_publicize_connections":[],"jetpack_sharing_enabled":true,"jetpack_shortlink":"https:\/\/wp.me\/p7g3hj-5e","jetpack-related-posts":[{"id":177,"url":"http:\/\/re-design.dimiter.eu\/?p=177","url_meta":{"origin":324,"position":0},"title":"What makes a video go viral?","date":"November 28, 2011","format":false,"excerpt":"Internet Marketing expert Dr Brent Coker\u00a0claims to have developed an\u00a0algorithm that can predict which ad movies will go viral on YouTube. I don't plan a career move to advertising but was nevertheless intrigued by the claim\u00a0from a research methods & design perspective. Unfortunately, there is very little information available (yet?)\u00a0and\u2026","rel":"","context":"In "Advertising research"","img":{"alt_text":"","src":"https:\/\/i2.wp.com\/img.youtube.com\/vi\/YRRK3zIW9x0\/0.jpg?resize=350%2C200","width":350,"height":200},"classes":[]},{"id":662,"url":"http:\/\/re-design.dimiter.eu\/?p=662","url_meta":{"origin":324,"position":1},"title":"Hyperlinks","date":"January 30, 2013","format":false,"excerpt":"After a not-so-short hiatus during which I visited friends and family in Bulgaria, went through a couple of seasonal colds, and got a new workstation up and running (MacBook Pro with W7), I am finally back to the blog. As a warm-up, a bunch of interesting links you might have\u2026","rel":"","context":"In "Hyperlinks"","img":{"alt_text":"","src":"https:\/\/i2.wp.com\/re-design.dimiter.eu\/wp-content\/uploads\/2013\/01\/coral-2.jpg?resize=350%2C200","width":350,"height":200},"classes":[]},{"id":666,"url":"http:\/\/re-design.dimiter.eu\/?p=666","url_meta":{"origin":324,"position":2},"title":"Discretion is Fractal","date":"February 1, 2013","format":false,"excerpt":"Last week, I made a presentation at the Leiden University conference 'Political Legitimacy and the Paradox of Regulation' under the admittedly esoteric title 'Discretion is Fractal'. Despite the title, my point is actually quite simple: one cannot continue to model,\u00a0conceptualize and measure (administrative or legal) discretion as a linear\u00a0phenomenon\u00a0because of\u2026","rel":"","context":"In "Measurement"","img":{"alt_text":"","src":"","width":0,"height":0},"classes":[]},{"id":377,"url":"http:\/\/re-design.dimiter.eu\/?p=377","url_meta":{"origin":324,"position":3},"title":"Visualizing left-right government positions","date":"March 19, 2012","format":false,"excerpt":"How does the political landscape of Europe change over time? One way to approach this question is to map the socio-economic left-right positions of the governments in power. So let's plot the changing ideological \u00a0positions of the governments using data from the Manifesto project! As you will see below, this\u2026","rel":"","context":"In "Data visualization"","img":{"alt_text":"","src":"https:\/\/i0.wp.com\/re-design.dimiter.eu\/wp-content\/uploads\/2012\/03\/rplot2.png?resize=350%2C200","width":350,"height":200},"classes":[]},{"id":24,"url":"http:\/\/re-design.dimiter.eu\/?p=24","url_meta":{"origin":324,"position":4},"title":"The present and the future of academic publishing","date":"October 10, 2011","format":false,"excerpt":"Academic publishing remains one of the most mysterious industries to me even after being caught in its web for a while. I have found no better presentation of the idiocy of the whole system than this video: more here Unfortunately, recent development (at least in social science journals) do not\u2026","rel":"","context":"In "Academic publishing"","img":{"alt_text":"","src":"https:\/\/i0.wp.com\/img.youtube.com\/vi\/GMIY_4t-DR0\/0.jpg?resize=350%2C200","width":350,"height":200},"classes":[]},{"id":346,"url":"http:\/\/re-design.dimiter.eu\/?p=346","url_meta":{"origin":324,"position":5},"title":"Creating Data Maps","date":"March 5, 2012","format":false,"excerpt":"There are several online tools for data visualization including IBM's ManyEyes and Google's Chart Tools. For a recent post on the other blog to which I contribute I wanted to map the distribution of a variable on a geographical map of Europe. I decided that's a good opportunity to try\u2026","rel":"","context":"In "Data visualization"","img":{"alt_text":"","src":"http:\/\/eurosearch.files.wordpress.com\/2012\/02\/exportmap.png?w=350&h=200&crop=1","width":350,"height":200},"classes":[]}],"_links":{"self":[{"href":"http:\/\/re-design.dimiter.eu\/index.php?rest_route=\/wp\/v2\/posts\/324"}],"collection":[{"href":"http:\/\/re-design.dimiter.eu\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/re-design.dimiter.eu\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/re-design.dimiter.eu\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/re-design.dimiter.eu\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=324"}],"version-history":[{"count":0,"href":"http:\/\/re-design.dimiter.eu\/index.php?rest_route=\/wp\/v2\/posts\/324\/revisions"}],"wp:attachment":[{"href":"http:\/\/re-design.dimiter.eu\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=324"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/re-design.dimiter.eu\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=324"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/re-design.dimiter.eu\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=324"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}