{"id":1841,"date":"2015-07-29T11:10:45","date_gmt":"2015-07-29T11:10:45","guid":{"rendered":"http:\/\/blogs.kent.ac.uk\/sac-news-events\/?p=1841"},"modified":"2015-08-12T09:03:06","modified_gmt":"2015-08-12T09:03:06","slug":"kent-research-could-play-major-role-in-curbing-illegal-ivory-sales","status":"publish","type":"post","link":"https:\/\/blogs.kent.ac.uk\/sac-news-events\/2015\/07\/29\/kent-research-could-play-major-role-in-curbing-illegal-ivory-sales\/","title":{"rendered":"Kent research could play major role in curbing illegal ivory sales"},"content":{"rendered":"<p>A new automated data mining system researched and developed at the University of Kent could lead to a dramatic increase in the detection of potentially illegal online sales of elephant ivory through eBay.\u00a0Law enforcement agencies and conservationists are expected to make use of the system \u2013 developed by researchers from the University\u2019s <a href=\"http:\/\/www.cybersec.kent.ac.uk\/\">Centre for Cyber Security<\/a> &#8211; in their ongoing battle against illegal ivory sales.<\/p>\n<p>At the moment, identifying illegal elephant ivory being sold online is a laborious, tedious and expensive task, even for experts.\u00a0A search for items listed as \u2018ivory\u2019 throws up a multitude of items &#8211; including ivory-coloured wedding dresses &#8211; making the task of tracking down illegal products akin to finding a needle in a haystack. In addition, criminals usually avoid using the term \u2018ivory\u2019 to bypass online bans.<\/p>\n<p>But research from <a href=\"http:\/\/www.kent.ac.uk\/sac\/staff-profiles\/profiles\/conservation-biology\/academic-staff\/roberts_david.html\">Dr David Roberts<\/a>, Senior Lecturer in Biodiversity Conservation at DICE, and Dr Julio Hernandez-Castro, Lecturer in Computing at the University\u2019s School of Computing, shows how the automated system can mimic human expert classification of potentially illegal elephant ivory &#8211; but at a fraction of the cost and thousands of times faster.<\/p>\n<p>The research, published today\u00a0in the journal <em><a href=\"https:\/\/peerj.com\/computer-science\/\" target=\"_blank\">PeerJ Computer Science<\/a><\/em>, shows how the team utilised what is known as a \u2018high throughput machine learning algorithm\u2019 to \u2018read\u2019 the computer information behind eBay listings.<\/p>\n<p>As part of the study, two experts manually classified items on sale in the antiques section of eBay, looking at the type of ivory and whether it was potentially legal or illegal.\u00a0The classifications obtained by the experts were then compared against those achieved by the data mining system, which used less data than the experts, including not referencing item descriptions or associated images.<\/p>\n<p>The results showed the new automated system could replicate the success of the human experts with a 93% accuracy rate, and that this would be increased if it added more information, such as images.<\/p>\n<p>The team will now work to further develop the system for launch.<\/p>\n<p>Photo of African elephant courtesy of <a href=\"https:\/\/www.flickr.com\/photos\/berniedup\/16478278169\/in\/photolist-r78u1i-acE8yG-absTnr-crW47m-abnKXT-abqzK1-acE9kN-crW6MW-absRDT-abqAb3-abqB85-crW4Gf-221Cvf-acBjGc-abvH9W-2PGBgi-2PGDZz-s84NDK-spuueV-s7Voxo-hRR8nw-ruHTSx-sptppr-2PM5qj-spuNPk-rsFASe-spvfci-crVy8w-absTE2-crW68u-crW7ms-crVyPm-abvGth-abvFZA-abnKiM-abqzSf-abnKxD-s6bqW2-rtLv5V-dc4BQT-sncRvy-fC2o6P-fChuPh-sfisWV-rH6R4Y-atbhjv-rGiBrt-nz1cDr-avRfzG-aFeCaT\">Bernard Dupont<\/a>.\u00a0Licensed under <a href=\"https:\/\/creativecommons.org\/licenses\/ccby-sa3.0\/3.0\/\" target=\"_blank\">CCBY-SA3.0<\/a>.<\/p>\n","protected":false},"excerpt":{"rendered":"<p>A new automated data mining system researched and developed at the University of Kent could lead to a dramatic increase in the detection of potentially &hellip; <a href=\"https:\/\/blogs.kent.ac.uk\/sac-news-events\/2015\/07\/29\/kent-research-could-play-major-role-in-curbing-illegal-ivory-sales\/\">Read&nbsp;more<\/a><\/p>\n","protected":false},"author":40284,"featured_media":1866,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":[],"categories":[6599,124,6600],"tags":[],"_links":{"self":[{"href":"https:\/\/blogs.kent.ac.uk\/sac-news-events\/wp-json\/wp\/v2\/posts\/1841"}],"collection":[{"href":"https:\/\/blogs.kent.ac.uk\/sac-news-events\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/blogs.kent.ac.uk\/sac-news-events\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/blogs.kent.ac.uk\/sac-news-events\/wp-json\/wp\/v2\/users\/40284"}],"replies":[{"embeddable":true,"href":"https:\/\/blogs.kent.ac.uk\/sac-news-events\/wp-json\/wp\/v2\/comments?post=1841"}],"version-history":[{"count":5,"href":"https:\/\/blogs.kent.ac.uk\/sac-news-events\/wp-json\/wp\/v2\/posts\/1841\/revisions"}],"predecessor-version":[{"id":1868,"href":"https:\/\/blogs.kent.ac.uk\/sac-news-events\/wp-json\/wp\/v2\/posts\/1841\/revisions\/1868"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/blogs.kent.ac.uk\/sac-news-events\/wp-json\/wp\/v2\/media\/1866"}],"wp:attachment":[{"href":"https:\/\/blogs.kent.ac.uk\/sac-news-events\/wp-json\/wp\/v2\/media?parent=1841"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/blogs.kent.ac.uk\/sac-news-events\/wp-json\/wp\/v2\/categories?post=1841"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/blogs.kent.ac.uk\/sac-news-events\/wp-json\/wp\/v2\/tags?post=1841"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}