{"id":58,"date":"2017-10-12T12:16:57","date_gmt":"2017-10-12T09:16:57","guid":{"rendered":"https:\/\/coursepages.uta.fi\/tiets43\/?page_id=58"},"modified":"2019-10-03T12:48:17","modified_gmt":"2019-10-03T09:48:17","slug":"projects","status":"publish","type":"page","link":"https:\/\/coursepages2.tuni.fi\/tiets43\/projects\/","title":{"rendered":"Projects"},"content":{"rendered":"<p>Here you can find some <em>recommendations<\/em> for your project topic. These topics can act as examples. Feel free to propose your own topic!<\/p>\n<ul>\n<li><b>Sequential recommendations:<\/b> Recommendations should not be considered as a stand-alone process. A real world system requires access to history logs, i.e., to know what items the system previously had recommended, how well were these items received by the users, so as to take these factors into account when producing recommendations.<\/li>\n<li><b>Sequential fair recommendations for groups:<\/b><span style=\"font-size: 16px\"> Use the notion of satisfaction, that describes how relevant are the recommended items to each member of the group, to ensure high satisfaction for all group members.<\/span><\/li>\n<li><b>Interactive sequential (group) recommendations:<\/b><span style=\"font-size: 16px\"> Users provide feedback of several forms to the system, which is used for improving the quality of recommendations.\u00a0<\/span><\/li>\n<li><b>Visualisation \/ Explanation of sequential recommendations:<\/b><span style=\"font-size: 16px\"> I suggest \u201cA\u201d, which is \u201cexcellent\u201d for \u201cX\u201d, because he\/she was not satisfied in the previous round of suggestions.\u00a0<\/span><\/li>\n<li><b>Chart-like explanations \/\u00a0visualisations\u00a0for recommendations:<\/b><span style=\"font-size: 16px\"> I suggest \u201cA\u201d because 90% of your \u201cfriends\u201d, aka. similar user, like it.\u00a0<\/span><\/li>\n<li><b>Natural Language Explanations for Recommendations<\/b><\/li>\n<li><b>Explaining recommendation via why-not queries:<\/b> Understand why certain items are no recommended. For example, an explanation for not obtaining Titanic as recommended movie could be a very low rating of a very similar user. In this project, we are aiming to\u00a0formalise\u00a0the problem of Why-Not queries in recommendation systems, and propose ways to compute them, either in the source data or the filtering function itself.<\/li>\n<li><b>Recommendation summaries:<\/b><span style=\"font-size: 16px\"> Use the notion of coverage or diversity to report representative recommendations.\u00a0<\/span><\/li>\n<li><b>Recommendation summaries:<\/b><span style=\"font-size: 16px\"> Use the notion of coverage or diversity to report textual summaries of recommendations.\u00a0<\/span><\/li>\n<li><b>Education and emotion based group recommendations for health:<\/b><span style=\"font-size: 16px\"> Existing systems recommend to groups of persons health documents selected by caregivers, by incorporating the notion of fairness. This project focuses on adapting recommendations considering the educational level of the end-users and their psycho-emotional status.\u00a0<\/span><\/li>\n<li><b>Recommend product packets to customers:<\/b><span style=\"font-size: 16px\"> E.g., a mobile phone along with its case and headphones.\u00a0<\/span><\/li>\n<li><b>Recommendations by example:<\/b><span style=\"font-size: 16px\"> Introduce a novel paradigm that considers a user query as an example of the data in which the user is interested.\u00a0<\/span><\/li>\n<li><b>Recommend (representative) reviews to users\u00a0<\/b><\/li>\n<li><b>Recommendations based on User Reviews<\/b><\/li>\n<li><b>Recommendation on a map: E.g., hotels\u00a0<\/b><\/li>\n<li><em><strong>Survey on sequential recommendations\u00a0<\/strong><\/em><\/li>\n<li><em><strong>Survey on example-driven search\u00a0<\/strong><\/em><\/li>\n<li><em><strong>Survey on fairness in recommender systems<\/strong><\/em><\/li>\n<\/ul>\n<p><em><b>Projects examples from the previous year:\u00a0<\/b><\/em><\/p>\n<ul>\n<li>Courses recommendations<\/li>\n<li><span style=\"font-size: 16px\">Board-game recommendations<\/span><\/li>\n<li><a href=\"https:\/\/people.uta.fi\/~kostas.stefanidis\/docs\/qauca19.pdf\"><span style=\"font-size: 16px\">Video games recommendations<\/span><\/a><\/li>\n<li><span style=\"font-size: 16px\">Recommend applications in Play Store<\/span><\/li>\n<li>Steam games\u00a0<span style=\"font-size: 16px\">recommendations<\/span><\/li>\n<li><span style=\"font-size: 16px\">Movies recommendations<\/span><\/li>\n<li><span style=\"font-size: 16px\">Images recommendations<\/span><\/li>\n<li><span style=\"font-size: 16px\">Programming languages recommendations<\/span><\/li>\n<li><a href=\"https:\/\/people.uta.fi\/~kostas.stefanidis\/docs\/tpdl18.pdf\">Open source software recommendations\u00a0<\/a><\/li>\n<li><span style=\"font-size: 16px\">Album recommendations based on Rolling Stones top-500 list<\/span><\/li>\n<li><span style=\"font-size: 16px\">Music recommendations<\/span><\/li>\n<li><span style=\"font-size: 16px\">Book recommendations<\/span><\/li>\n<li><span style=\"font-size: 16px\">Style and products recommendations<\/span><\/li>\n<li><span style=\"font-size: 16px\">Beers recommendations<\/span><\/li>\n<li><span style=\"font-size: 16px\">Hockey players recommendations<\/span><\/li>\n<li><a href=\"https:\/\/people.uta.fi\/~kostas.stefanidis\/docs\/BIoBD19.pdf\">Recommendations for FIFA18<\/a><\/li>\n<li><span style=\"font-size: 16px\">E-commerce product recommender<\/span><\/li>\n<li>Personalised\u00a0news recommendations<\/li>\n<li><a href=\"https:\/\/people.uta.fi\/~kostas.stefanidis\/docs\/adbis19.pdf\"><span style=\"font-size: 16px\">User reviews in recommender systems<\/span><\/a><\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Here you can find some recommendations for your project topic. These topics can act as examples. Feel free to propose your own topic! Sequential recommendations: Recommendations should not be considered as a stand-alone process. A real world system requires access to history logs, i.e., to know what items the system previously had recommended, how well &hellip; <a href=\"https:\/\/coursepages2.tuni.fi\/tiets43\/projects\/\" class=\"more-link\">Continue reading <span class=\"screen-reader-text\">Projects<\/span><\/a><\/p>\n","protected":false},"author":33,"featured_media":0,"parent":0,"menu_order":2,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-58","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/coursepages2.tuni.fi\/tiets43\/wp-json\/wp\/v2\/pages\/58","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/coursepages2.tuni.fi\/tiets43\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/coursepages2.tuni.fi\/tiets43\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/coursepages2.tuni.fi\/tiets43\/wp-json\/wp\/v2\/users\/33"}],"replies":[{"embeddable":true,"href":"https:\/\/coursepages2.tuni.fi\/tiets43\/wp-json\/wp\/v2\/comments?post=58"}],"version-history":[{"count":8,"href":"https:\/\/coursepages2.tuni.fi\/tiets43\/wp-json\/wp\/v2\/pages\/58\/revisions"}],"predecessor-version":[{"id":240,"href":"https:\/\/coursepages2.tuni.fi\/tiets43\/wp-json\/wp\/v2\/pages\/58\/revisions\/240"}],"wp:attachment":[{"href":"https:\/\/coursepages2.tuni.fi\/tiets43\/wp-json\/wp\/v2\/media?parent=58"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}