{"id":348,"date":"2019-08-20T18:16:36","date_gmt":"2019-08-20T22:16:36","guid":{"rendered":"http:\/\/www.cs.fsu.edu\/vipra\/?page_id=348"},"modified":"2019-09-10T19:38:59","modified_gmt":"2019-09-10T23:38:59","slug":"high-resolution-home-location-prediction-from-tweets-using-deep-learning-with-dynamic-structure","status":"publish","type":"page","link":"https:\/\/www.cs.fsu.edu\/vipra\/?page_id=348","title":{"rendered":"High-Resolution Vector-Borne Disease Risk Assessment"},"content":{"rendered":"

Goal<\/h3>\n

We wish to identify the risk of vector-borne diseases at the resolution of a neighborhood. This will enable effective and targeted public health interventions, such as integrated vector control measures.<\/p>\n

Challenges<\/h3>\n

Human mobility plays a critical role in the spread of vector-borne diseases. Conventional data sources do not have the required spatial and temporal resolution. Furthermore, traditional models have difficulty accounting for demographic heterogeneity.<\/p>\n

Approach<\/h3>\n

We use social media data to model human mobility. In particular, we use Twitter data to identify locations visited by people who have recently been to a disease-affected region.<\/p>\n

    \n
  1. We first compute the flux of such persons into different counties using Natural Language Processing techniques on tweet content.<\/li>\n
  2. We input this population flux into a meta-population model to identify counties at risk of disease importation.<\/li>\n
  3. We then target high-risk counties for a fine-scale model. We leverage our novel deep learning workflow on Twitter metadata for determining home-locations of users to identify high-risk neighborhoods.<\/li>\n<\/ol>\n
    \n
    \n\"\"
    Flowchart of our approach<\/figcaption><\/figure>\n
    \n\"\"
    Identify home location of a user (red) <\/figcaption><\/figure>\n<\/div>\n

    Results<\/h3>\n
    \n
    \n
    Zika risk map at the county level (2016 outbreak)<\/figcaption><\/figure>\n<\/div>\n\n\n\n\n\n
    Predicted high-risk neighborhoods<\/th>\nActual high-risk neighborhoods<\/th>\n<\/tr>\n
    Miami Beach<\/td>\nMiami Beach<\/td>\n<\/tr>\n
    Wynwood<\/td>\nWynwood<\/td>\n<\/tr>\n
    Miami Airport<\/td>\nLittle River<\/td>\n<\/tr>\n
    Neighborhood level Zika risk prediction for Miami (2016 outbreak)<\/caption>\n<\/table>\n

    References<\/h3>\n
      \n
    1. High-resolution Twitter home location prediction<\/a>\n
    2. Detailed version of ASONAM 2019 paper on Zika risk assessment<\/a>\n<\/ol>\n","protected":false},"excerpt":{"rendered":"

      Goal We wish to identify the risk of vector-borne diseases at the resolution of a neighborhood. This will enable effective and targeted public health interventions, such as integrated vector control measures. Challenges Human mobility plays a critical role in the spread of vector-borne diseases. Conventional data sources do not have the required spatial and temporal resolution. Furthermore, traditional models have […]<\/p>\n","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":[],"_links":{"self":[{"href":"https:\/\/www.cs.fsu.edu\/vipra\/index.php?rest_route=\/wp\/v2\/pages\/348"}],"collection":[{"href":"https:\/\/www.cs.fsu.edu\/vipra\/index.php?rest_route=\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.cs.fsu.edu\/vipra\/index.php?rest_route=\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.cs.fsu.edu\/vipra\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.cs.fsu.edu\/vipra\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=348"}],"version-history":[{"count":98,"href":"https:\/\/www.cs.fsu.edu\/vipra\/index.php?rest_route=\/wp\/v2\/pages\/348\/revisions"}],"predecessor-version":[{"id":466,"href":"https:\/\/www.cs.fsu.edu\/vipra\/index.php?rest_route=\/wp\/v2\/pages\/348\/revisions\/466"}],"wp:attachment":[{"href":"https:\/\/www.cs.fsu.edu\/vipra\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=348"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}