{"id":6752,"date":"2015-02-10T09:53:05","date_gmt":"2015-02-10T17:53:05","guid":{"rendered":"http:\/\/blogs.ufv.ca\/announce\/?p=6752"},"modified":"2015-02-20T12:51:17","modified_gmt":"2015-02-20T20:51:17","slug":"plentyoffish-plentyofdata-talk-by-thomas-levi","status":"publish","type":"post","link":"https:\/\/blogs.ufv.ca\/announce\/2015\/02\/10\/plentyoffish-plentyofdata-talk-by-thomas-levi\/","title":{"rendered":"PlentyOfFish = PlentyOfData (talk by Thomas Levi) &#8212; Feb 19"},"content":{"rendered":"<p>Thurs, Feb 19, 2:30\u20134 pm, Abby B121<\/p>\n<p style=\"text-align: left\">Abstract: As the world\u2019s largest free dating site, Plenty Of Fish would<br \/>\nlike to be able to match with and allow users to search for people with<br \/>\nsimilar interests. However, we allow our users to enter their interests as<br \/>\nfree text on their profiles. This presents a difficult problem in<br \/>\nclustering, search and machine learning if we want to move beyond simple<br \/>\n\u2018exact match\u2019 solutions to a deeper archetypal user profiling and thematic<br \/>\nsearch system. Some of the common issues that arise are misspellings,<br \/>\nsynonyms (e.g. biking, cycling and bicycling) and similar interests (e.g.<br \/>\nsnowboarding and skiing) on a several million user scale. In this talk I<br \/>\nwill demonstrate how we built a system utilizing topic modelling with<br \/>\nLatent Dirichlet Allocation (LDA) on a several hundred thousand word<br \/>\nvocabulary over ten million+ North American users and explore its<br \/>\napplications at POF.<\/p>\n<p><a href=\"http:\/\/www.ufv.ca\/math\/math-club-talks\/\" target=\"_blank\">http:\/\/www.ufv.ca\/math\/math-club-talks\/<\/a><\/p>\n<p>For more information, contact Gabriel Murray at <a href=\"mailto:gabriel.murray@ufv.ca\">gabriel.murray@ufv.ca<\/a><\/p>\n<p style=\"color: #fff\">02\/20\/2015<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Thurs, Feb 19, 2:30\u20134 pm, Abby B121 Abstract: As the world\u2019s largest free dating site, Plenty Of Fish would like to be able to match with and allow users to search for people with similar interests. However, we allow our users to enter their interests as free text on their profiles. This presents a difficult &#8230; <a title=\"PlentyOfFish = PlentyOfData (talk by Thomas Levi) &#8212; Feb 19\" class=\"read-more\" href=\"https:\/\/blogs.ufv.ca\/announce\/2015\/02\/10\/plentyoffish-plentyofdata-talk-by-thomas-levi\/\">Read more<\/a><\/p>\n","protected":false},"author":13,"featured_media":0,"comment_status":"closed","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"generate_page_header":"","footnotes":""},"categories":[12,1],"tags":[],"class_list":["post-6752","post","type-post","status-publish","format-standard","hentry","category-calendar","category-uncategorized"],"_links":{"self":[{"href":"https:\/\/blogs.ufv.ca\/announce\/wp-json\/wp\/v2\/posts\/6752","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blogs.ufv.ca\/announce\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blogs.ufv.ca\/announce\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blogs.ufv.ca\/announce\/wp-json\/wp\/v2\/users\/13"}],"replies":[{"embeddable":true,"href":"https:\/\/blogs.ufv.ca\/announce\/wp-json\/wp\/v2\/comments?post=6752"}],"version-history":[{"count":7,"href":"https:\/\/blogs.ufv.ca\/announce\/wp-json\/wp\/v2\/posts\/6752\/revisions"}],"predecessor-version":[{"id":6998,"href":"https:\/\/blogs.ufv.ca\/announce\/wp-json\/wp\/v2\/posts\/6752\/revisions\/6998"}],"wp:attachment":[{"href":"https:\/\/blogs.ufv.ca\/announce\/wp-json\/wp\/v2\/media?parent=6752"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blogs.ufv.ca\/announce\/wp-json\/wp\/v2\/categories?post=6752"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blogs.ufv.ca\/announce\/wp-json\/wp\/v2\/tags?post=6752"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}