{"id":5104,"date":"2016-09-24T12:46:57","date_gmt":"2016-09-24T12:46:57","guid":{"rendered":"http:\/\/www.garysieling.com\/blog\/?p=5104"},"modified":"2016-09-24T12:46:57","modified_gmt":"2016-09-24T12:46:57","slug":"comparing-lecture-search-youtube","status":"publish","type":"post","link":"https:\/\/www.garysieling.com\/blog\/comparing-lecture-search-youtube\/","title":{"rendered":"Comparing &#8220;lecture search&#8221; and Youtube"},"content":{"rendered":"<p><a href=\"https:\/\/news.ycombinator.com\/item?id=12568477#12569087\">From a discussion on Hacker news:<\/a><\/p>\n<p>Youtube does have automatic transcription for videos. It&#8217;s not too hard to link this to a topic hierarchy (maybe they already do this).  It seems like a hard problem at their scale, since unlike Spotify, the list of genres isn&#8217;t knowable.<\/p>\n<p>I&#8217;ve been building a search engine for lectures as a research project. For a small list of videos I find that browsing topic taxonomy is really nice compared to the recommenders that try to guess your intent.<\/p>\n<p>https:\/\/www.findlectures.com<\/p>\n<p>There are commercial systems for automatically tagging the text (e.g. Watson) which  hierarchies which don&#8217;t go into niche areas &#8211; e.g. the Watson taxonomy tagger does 1,000 tags.<\/p>\n<p>For more niche topics, I&#8217;ve explored Watson&#8217;s entity recognition system, e.g. to recognize the names of diseases. The advantage is it picks up terms it hasn&#8217;t seen- The problem is you can only identify entities that someone has trained a system to recognize.<\/p>\n<p>The UI challenges are interesting as well. If spotified identified 100 genres that interested me, they could pick any arbitrary subset of playlists and I&#8217;d be pretty happy. If I used youtube to get home repair videos, and then they showed me videos about repairing parts of my house that aren&#8217;t broken, it&#8217;d get pretty irritating.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Comparing the challenges of exploring videos on youtube, vs a more targeted system<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"om_disable_all_campaigns":false,"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0,"footnotes":""},"categories":[29],"tags":[570,607],"aioseo_notices":[],"amp_enabled":true,"_links":{"self":[{"href":"https:\/\/www.garysieling.com\/blog\/wp-json\/wp\/v2\/posts\/5104"}],"collection":[{"href":"https:\/\/www.garysieling.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.garysieling.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.garysieling.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.garysieling.com\/blog\/wp-json\/wp\/v2\/comments?post=5104"}],"version-history":[{"count":0,"href":"https:\/\/www.garysieling.com\/blog\/wp-json\/wp\/v2\/posts\/5104\/revisions"}],"wp:attachment":[{"href":"https:\/\/www.garysieling.com\/blog\/wp-json\/wp\/v2\/media?parent=5104"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.garysieling.com\/blog\/wp-json\/wp\/v2\/categories?post=5104"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.garysieling.com\/blog\/wp-json\/wp\/v2\/tags?post=5104"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}