Public Surveillance of Social Media for Suicide Using Advanced Deep Learning Models in Japan: Time Series Study From 2012 to 2022

Siqin Wang   ^{1, 2, 3 *} , DPhil ;   Huan Ning   ^{4 *} , MSc ;   Xiao Huang   ⁵ , DPhil ;   Yunyu Xiao   ⁶ , DPhil ;   Mengxi Zhang   ⁷ , DPhil ;   Ellie Fan Yang   ⁸ , DPhil ;   Yukio Sadahiro   ¹ , DPhil ;   Yan Liu   ⁹ , DPhil ;   Zhenlong Li   ⁴ , DPhil ;   Tao Hu   ¹⁰ , DPhil ;   Xiaokang Fu   ¹¹ , DPhil ;   Zi Li   ¹² , MSc ;   Ye Zeng   ¹³ , BSc

¹ Graduate School of Interdisciplinary Information Studies, University of Tokyo, Tokyo, Japan

² School of Earth and Environmental Sciences, The University of Queensland, Brisbane, Australia

³ School of Science, RMIT University, Melbourne, Australia

⁴ Department of Geography, University of South Carolina, Columbia, SC, United States

⁵ Department of Geosciences, University of Arkansas, Fayetteville, AR, United States

⁶ Department of Population Health Sciences, Weill Cornell Medicine, New York, NY, United States

⁷ Carilion School of Medicine, Virginia Tech, Blacksburg, VA, United States

⁸ School of Communication and Mass Media, Northwest Missouri State University, Maryville, MO, United States

⁹ School of Earth and Environmental Sciences, University of Queensland, Brisbane, Australia

¹⁰ Department of Geography, Oklahoma State University, Stillwater, OK, United States

¹¹ Centre for Geographic Analysis, Harvard University, Cambridge, MA, United States

¹² Graduate School of Medicine, Juntendo University, Tokyo, Japan

¹³ Department of Medical Business, Nihon Pharmaceutical University, Tokyo, Japan

*these authors contributed equally