eprintid: 10074319 rev_number: 25 eprint_status: archive userid: 608 dir: disk0/10/07/43/19 datestamp: 2019-05-22 08:43:54 lastmod: 2021-10-10 22:43:26 status_changed: 2019-05-22 08:43:54 type: proceedings_section metadata_visibility: show creators_name: Zou, B creators_name: Lampos, V creators_name: Cox, I title: Transfer learning for unsupervised influenza-like illness models from online search data ispublished: pub divisions: UCL divisions: B04 divisions: C05 divisions: F48 note: This paper is published under the Creative Commons Attribution 4.0 International (CC-BY 4.0) license. Authors reserve their rights to disseminate the work on their personal and corporate Web sites with the appropriate attribution https://creativecommons.org/licenses/by/4.0/ abstract: A considerable body of research has demonstrated that online search data can be used to complement current syndromic surveillance systems. The vast majority of previous work proposes solutions that are based on supervised learning paradigms, in which historical disease rates are required for training a model. However, for many geographical regions this information is either sparse or not available due to a poor health infrastructure. It is these regions that have the most to benefit from inferring population health statistics from online user search activity. To address this issue, we propose a statistical framework in which we first learn a supervised model for a region with adequate historical disease rates, and then transfer it to a target region, where no syndromic surveillance data exists. This transfer learning solution consists of three steps: (i) learn a regularized regression model for a source country, (ii) map the source queries to target ones using semantic and temporal similarity metrics, and (iii) re-adjust the weights of the target queries. It is evaluated on the task of estimating influenza-like illness (ILI) rates. We learn a source model for the United States, and subsequently transfer it to three other countries, namely France, Spain and Australia. Overall, the transferred (unsupervised) models achieve strong performance in terms of Pearson correlation with the ground truth (> .92 on average), and their mean absolute error does not deviate greatly from a fully supervised baseline. date: 2019-05-12 date_type: published publisher: ACM official_url: https://doi.org/10.1145/3308558.3313477 oa_status: green full_text_type: pub language: eng primo: open primo_central: open_green verified: verified_manual elements_id: 1658259 doi: 10.1145/3308558.3313477 isbn_13: 978-1-4503-6674-8 lyricists_name: Cox, Ingemar lyricists_name: Lampos, Vasileios lyricists_id: IJCOX77 lyricists_id: VLAMP72 actors_name: Lampos, Vasileios actors_id: VLAMP72 actors_role: owner full_text_status: public series: The World Wide Web Conference publication: The World Wide Web Conference volume: 2019 place_of_pub: San Francisco, CA, USA pagerange: 2505-2516 event_title: WWW '19 The World Wide Web Conference event_location: San Francisco, CA, USA event_dates: 13 - 17 May 2019 book_title: Proceeding WWW '19 The World Wide Web Conference citation: Zou, B; Lampos, V; Cox, I; (2019) Transfer learning for unsupervised influenza-like illness models from online search data. In: Proceeding WWW '19 The World Wide Web Conference. (pp. pp. 2505-2516). ACM: San Francisco, CA, USA. Green open access document_url: https://discovery.ucl.ac.uk/id/eprint/10074319/1/p2505-zou.pdf