{"id":35949,"date":"2017-04-07T00:24:21","date_gmt":"2017-04-07T07:24:21","guid":{"rendered":"http:\/\/lifeboat.com\/blog\/2017\/04\/unsupervised-sentiment-neuron"},"modified":"2017-06-04T07:05:49","modified_gmt":"2017-06-04T14:05:49","slug":"unsupervised-sentiment-neuron","status":"publish","type":"post","link":"https:\/\/lifeboat.com\/blog\/2017\/04\/unsupervised-sentiment-neuron","title":{"rendered":"Unsupervised sentiment neuron"},"content":{"rendered":"<p><a class=\"aligncenter blog-photo\" href=\"https:\/\/lifeboat.com\/blog.images\/unsupervised-sentiment-neuron.jpg\"><\/a><\/p>\n<p>We\u2019ve <a href=\"https:\/\/arxiv.org\/abs\/1704.01444\">developed<\/a> an <a href=\"https:\/\/blog.openai.com\/unsupervised-sentiment-neuron\/#unsupervisedlearning\">unsupervised<\/a> system which learns an excellent representation of sentiment, despite being trained only to predict the next character in the text of Amazon reviews.<\/p>\n<p>A <a href=\"https:\/\/blog.openai.com\/unsupervised-sentiment-neuron\/#methodology\">linear model<\/a> using this representation achieves state-of-the-art sentiment analysis accuracy on a small but extensively-studied dataset, the Stanford Sentiment Treebank (we get 91.8% accuracy versus the previous best of 90.2%), and can match the performance of previous supervised systems using 30-100x fewer labeled examples. Our representation also contains a distinct \u201c<a href=\"https:\/\/blog.openai.com\/unsupervised-sentiment-neuron\/#sentimentneuron\">sentiment neuron<\/a>\u201d which contains almost all of the sentiment signal.<\/p>\n<p><!-- Link: <a href=\"https:\/\/blog.openai.com\/unsupervised-sentiment-neuron\/\">https:\/\/blog.openai.com\/unsupervised-sentiment-neuron\/<\/a> --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>We\u2019ve developed an unsupervised system which learns an excellent representation of sentiment, despite being trained only to predict the next character in the text of Amazon reviews. A linear model using this representation achieves state-of-the-art sentiment analysis accuracy on a small but extensively-studied dataset, the Stanford Sentiment Treebank (we get 91.8% accuracy versus the previous [\u2026]<\/p>\n","protected":false},"author":423,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[47],"tags":[],"class_list":["post-35949","post","type-post","status-publish","format-standard","hentry","category-neuroscience"],"_links":{"self":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/35949","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/users\/423"}],"replies":[{"embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/comments?post=35949"}],"version-history":[{"count":2,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/35949\/revisions"}],"predecessor-version":[{"id":58144,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/posts\/35949\/revisions\/58144"}],"wp:attachment":[{"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/media?parent=35949"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/categories?post=35949"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/lifeboat.com\/blog\/wp-json\/wp\/v2\/tags?post=35949"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}