{"id":215393,"date":"2012-12-01T00:00:00","date_gmt":"2012-12-01T00:00:00","guid":{"rendered":"https:\/\/www.microsoft.com\/en-us\/research\/msr-research-item\/topic-partitioned-multinetwork-embeddings\/"},"modified":"2018-10-16T22:04:18","modified_gmt":"2018-10-17T05:04:18","slug":"topic-partitioned-multinetwork-embeddings","status":"publish","type":"msr-research-item","link":"https:\/\/www.microsoft.com\/en-us\/research\/publication\/topic-partitioned-multinetwork-embeddings\/","title":{"rendered":"Topic-Partitioned Multinetwork Embeddings"},"content":{"rendered":"<div class=\"asset-content\">\n<p>We introduce a new Bayesian<br \/>\nadmixture model intended for exploratory analysis of communication<br \/>\nnetworks\u2014specifically, the discovery and visualization of topic-specific<br \/>\nsubnetworks in email data sets. Our model produces principled visualizations of<br \/>\nemail networks, i.e., visualizations that have precise mathematical interpretations<br \/>\nin terms of our model and its relationship to the observed data. We validate<br \/>\nour modeling assumptions by demonstrating that our model achieves better link<br \/>\nprediction performance than three state-of-the-art network models and exhibits<br \/>\ntopic coherence comparable to that of latent Dirichlet allocation. We showcase<br \/>\nour model\u2019s ability to discover and visualize topic-specific communication patterns<br \/>\nusing a new email data set: the New Hanover County email network. We provide an<br \/>\nextensive analysis of these communication patterns, leading us to recommend our<br \/>\nmodel for any exploratory analysis of email networks or other similarly-structured<br \/>\ncommunication data. Finally, we advocate for principled visualization as a<br \/>\nprimary objective in the development of new network models.<\/p>\n<\/div>\n<p><!-- .asset-content --><\/p>\n","protected":false},"excerpt":{"rendered":"<p>We introduce a new Bayesian admixture model intended for exploratory analysis of communication networks\u2014specifically, the discovery and visualization of topic-specific subnetworks in email data sets. Our model produces principled visualizations of email networks, i.e., visualizations that have precise mathematical interpretations in terms of our model and its relationship to the observed data. We validate our [&hellip;]<\/p>\n","protected":false},"featured_media":0,"template":"","meta":{"msr-url-field":"","msr-podcast-episode":"","msrModifiedDate":"","msrModifiedDateEnabled":false,"ep_exclude_from_search":false,"footnotes":""},"msr-content-type":[3],"msr-research-highlight":[],"research-area":[13559],"msr-publication-type":[193716],"msr-product-type":[],"msr-focus-area":[],"msr-platform":[],"msr-download-source":[],"msr-locale":[268875],"msr-field-of-study":[],"msr-conference":[],"msr-journal":[],"msr-impact-theme":[],"msr-pillar":[],"class_list":["post-215393","msr-research-item","type-msr-research-item","status-publish","hentry","msr-research-area-social-sciences","msr-locale-en_us"],"msr_publishername":"","msr_edition":"Advances in Neural Information Processing Systems Twenty-Five","msr_affiliation":"","msr_published_date":"2012-12-01","msr_host":"","msr_duration":"","msr_version":"","msr_speaker":"","msr_other_contributors":"","msr_booktitle":"Advances in Neural Information Processing Systems Twenty-Five","msr_pages_string":"","msr_chapter":"","msr_isbn":"","msr_journal":"","msr_volume":"","msr_number":"","msr_editors":"","msr_series":"","msr_issue":"","msr_organization":"","msr_how_published":"","msr_notes":"Also presented at the Workshop on Information in Networks, 2012; the Third New Directions in Analyzing Text as Data Conference, 2012; the Fifth Annual Political Networks Conference, 2012","msr_highlight_text":"","msr_release_tracker_id":"","msr_original_fields_of_study":"","msr_download_urls":"","msr_external_url":"","msr_secondary_video_url":"","msr_longbiography":"","msr_microsoftintellectualproperty":1,"msr_main_download":"215557","msr_publicationurl":"","msr_doi":"","msr_publication_uploader":[{"type":"file","title":"krafft12topic-partitioned.pdf","viewUrl":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/04\/krafft12topic-partitioned.pdf","id":215557,"label_id":0}],"msr_related_uploader":"","msr_attachments":[{"id":215557,"url":"https:\/\/www.microsoft.com\/en-us\/research\/wp-content\/uploads\/2016\/04\/krafft12topic-partitioned.pdf"}],"msr-author-ordering":[{"type":"text","value":"P. Krafft","user_id":0,"rest_url":false},{"type":"text","value":"J. Moore","user_id":0,"rest_url":false},{"type":"text","value":"B. Desmarais","user_id":0,"rest_url":false},{"type":"text","value":"H. Wallach","user_id":0,"rest_url":false}],"msr_impact_theme":[],"msr_research_lab":[199571],"msr_event":[],"msr_group":[144903],"msr_project":[],"publication":[],"video":[],"download":[],"msr_publication_type":"inproceedings","_links":{"self":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/215393"}],"collection":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item"}],"about":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/types\/msr-research-item"}],"version-history":[{"count":2,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/215393\/revisions"}],"predecessor-version":[{"id":541813,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-item\/215393\/revisions\/541813"}],"wp:attachment":[{"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/media?parent=215393"}],"wp:term":[{"taxonomy":"msr-content-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-content-type?post=215393"},{"taxonomy":"msr-research-highlight","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-research-highlight?post=215393"},{"taxonomy":"msr-research-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/research-area?post=215393"},{"taxonomy":"msr-publication-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-publication-type?post=215393"},{"taxonomy":"msr-product-type","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-product-type?post=215393"},{"taxonomy":"msr-focus-area","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-focus-area?post=215393"},{"taxonomy":"msr-platform","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-platform?post=215393"},{"taxonomy":"msr-download-source","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-download-source?post=215393"},{"taxonomy":"msr-locale","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-locale?post=215393"},{"taxonomy":"msr-field-of-study","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-field-of-study?post=215393"},{"taxonomy":"msr-conference","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-conference?post=215393"},{"taxonomy":"msr-journal","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-journal?post=215393"},{"taxonomy":"msr-impact-theme","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-impact-theme?post=215393"},{"taxonomy":"msr-pillar","embeddable":true,"href":"https:\/\/www.microsoft.com\/en-us\/research\/wp-json\/wp\/v2\/msr-pillar?post=215393"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}