{"type":"ScholarlyArticle","title":"Depression Detection via Harvesting Social Media: A Multimodal Dictionary Learning Solution","authors":[{"name":"Guangyao Shen","slug":"guangyao-shen","given":"Guangyao","family":"Shen","affiliation":"Department of Computer Science and Technology , Tsinghua University ; TNList"},{"name":"Jia Jia","slug":"jia-jia","given":"Jia","family":"Jia","affiliation":"Department of Computer Science and Technology , Tsinghua University ; TNList"},{"name":"Liqiang Nie","slug":"liqiang-nie","given":"Liqiang","family":"Nie","affiliation":"Department of Computer Science and Technology , Shandong University"},{"name":"Fuli Feng","slug":"fuli-feng","given":"Fuli","family":"Feng","affiliation":"School of Computing , National University of Singapore"},{"name":"Cunjun Zhang","slug":"cunjun-zhang","given":"Cunjun","family":"Zhang","affiliation":"Department of Computer Science and Technology , Tsinghua University ; TNList"},{"name":"Tianrui Hu","slug":"tianrui-hu","given":"Tianrui","family":"Hu","affiliation":"School of Information and Communication Engineering , Beijing University of Posts and Telecommunications"},{"name":"Tat-Seng Chua","slug":"tat-seng-chua","given":"Tat-Seng","family":"Chua","affiliation":"School of Computing , National University of Singapore"},{"name":"Wenwu Zhu","slug":"wenwu-zhu","given":"Wenwu","family":"Zhu","affiliation":"Department of Computer Science and Technology , Tsinghua University ; TNList"}],"abstract":"Depression is a major contributor to the overall global burden of diseases. Traditionally, doctors diagnose depressed people face to face via referring to clinical depression criteria. However, more than 70% of the patients would not consult doctors at early stages of depression, which leads to further deterioration of their conditions. Meanwhile, people are increasingly relying on social media to disclose emotions and sharing their daily lives, thus social media have successfully been leveraged for helping detect physical and mental diseases. Inspired by these, our work aims to make timely depression detection via harvesting social media data. We construct well-labeled depression and non-depression dataset on Twitter, and extract six depression-related feature groups covering not only the clinical depression criteria, but also online behaviors on social media. With these feature groups, we propose a multimodal depressive dictionary learning model to detect the depressed users on Twitter. A series of experiments are conducted to validate this model, which outperforms (+3% to +10%) several baselines. Finally, we analyze a large-scale dataset on Twitter to reveal the underlying online behaviors between depressed and non-depressed users.","doi":"10.24963/ijcai.2017/536","url":"https://ijcai.org/proceedings/2017/536","pdf":"https://ijcai.org/proceedings/2017/0536.pdf","markdown":"https://ijcai.org/proceedings/2017/536.md","bibtex":"https://ijcai.org/proceedings/2017/bibtex/536","volume":{"slug":"2017","title":"Proceedings of the Twenty-Sixth International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2017","url":"https://ijcai.org/proceedings/2017/","year":2017,"location":"Melbourne, Australia","dates":"19-25 August 2017","editors":"Carles Sierra","isbn":"978-0-9992411-0-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2017"},"section":"Multidisciplinary Topics and Applications","track":"Main track","number":536,"pages":{"first":3838,"last":3844},"keywords":["Multidisciplinary Topics and Applications: AI and Social Sciences","Multidisciplinary Topics and Applications: Personalization and User Modeling"],"videos":[],"references":[{"position":1,"raw":"[Aharon and Elad, 2008] Michal Aharon and Michael Elad. Sparse and redundant modeling of image content using an image-signature-dictionary. Siam Journal on Imaging Sci- ences, 1(3):228-247, 2008.","title":"Sparse and redundant modeling of image content using an image-signature-dictionary","authors":"Aharon, Elad, Michal Aharon, Michael Elad","year":"2008","venue":"Siam Journal on Imaging Sciences","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Akbari et al., 2016] Mohammad Akbari, Xia Hu, Liqiang Nie, and Tat-Seng Chua. From tweets to wellness: Well- ness event detection from twitter streams. In Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, pages 87-93, 2016.","title":"From tweets to wellness: Wellness event detection from twitter streams","authors":"Mohammad Akbari, Xia Hu, Liqiang Nie, Tat-Seng Chua","year":"2016","venue":"Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Baldwin et al., 2015] Timothy Baldwin, Marie Cather- ine De Marneffe, Bo Han, Young Bum Kim, Alan Rit- ter, and Wei Xu. Shared tasks of the 2015 workshop on noisy user-generated text: Twitter lexical normalization and named entity recognition. In Proceedings of the ACL 2015 Workshop on Noisy User-generated Text, pages 126- 135, 2015.","title":"Shared tasks of the 2015 workshop on noisy user-generated text: Twitter lexical normalization and named entity recognition","authors":"Timothy Baldwin, Marie, Catherine De Marneffe, Bo Han, Young Bum Kim, Alan Ritter, Wei Xu","year":"2015","venue":"Proceedings of the ACL 2015 Workshop on Noisy User-generated Text","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Beck et al., 1961] Aaron Beck, Martin Mendelson, J Mock, and J Erbaugh. An inventory for measuring depression. Archives of General Psychiatry, 4(6):561-571, 1961.","title":"An inventory for measuring depression","authors":"Aaron Beck, Martin Mendelson, J Mock, Erbaugh","year":"1961","venue":"Archives of General Psychiatry","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Bird, 2006] Steven Bird. Nltk: the natural language toolkit. In Proceedings of the COLING/ACL on Interactive presen- tation sessions, pages 69-72, 2006.","title":"Nltk: the natural language toolkit","authors":"Steven Bird","year":"2006","venue":"Proceedings of the COLING/ACL on Interactive presentation sessions","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Bradley and Lang, 1999] Margaret M Bradley and Peter J Lang. Affective norms for english words (anew): In- struction manual and affective ratings. Technical report, Technical report C-1, the center for research in psycho- physiology, University of Florida, 1999.","title":"Affective norms for english words (anew): Instruction manual and affective ratings","authors":"M Margaret, Peter J Bradley, Lang","year":"1999","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Choudhury et al., 2013] Munmun De Choudhury, Michael Gamon, Scott Counts, and Eric Horvitz. Predicting depres- sion via social media. In Proceedings of the International Conference on Weblogs and Social Media, pages 128-137, 2013.","title":"Predicting depression via social media","authors":"Munmun De Choudhury, Michael Gamon, Scott Counts, Eric Horvitz","year":"2013","venue":"Proceedings of the International Conference on Weblogs and Social Media","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Coppersmith et al., 2014] Glen Coppersmith, Mark Dredze, and Craig Harman. Quantifying mental health signals in twitter. In The Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal To Clin- ical Reality, pages 51-60, 2014.","title":"Quantifying mental health signals in twitter","authors":"Coppersmith","year":"2014","venue":"The Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal To Clinical Reality","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Farseev et al., 2016] Aleksandr Farseev, Ivan Samborskii, and Tat-Seng Chua. bbridge: A big data platform for social multimedia analytics. In Proceedings of the 2016 ACM on Multimedia Conference, pages 759-761. ACM, 2016.","title":"bbridge: A big data platform for social multimedia analytics","authors":"Aleksandr Farseev, Ivan Samborskii, Tat-Seng Chua","year":"2016","venue":"Proceedings of the 2016 ACM on Multimedia Conference","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Lin et al., 2016] Huijie Lin, Jia Jia, Liqiang Nie, Guangyao Shen, and Tat-Seng Chua. What does social media say about your stress? In Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence, pages 3775-3781, 2016.","title":"What does social media say about your stress?","authors":"Huijie Lin, Jia Jia, Liqiang Nie, Guangyao Shen, Tat-Seng Chua","year":"2016","venue":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2016/531"},{"position":11,"raw":"[Miller, 1995] George A. Miller. Wordnet: A lexical database for english. Communications of the ACM, 38(11):39-41, 1995.","title":"Wordnet: A lexical database for english","authors":"George A Miller","year":"1995","venue":"Communications of the ACM","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Parikh and Boyd, 2014] Neal Parikh and Stephen Boyd. Proximal algorithms. Foundations & Trends in Optimiza- tion, 1(3):127-239, 2014.","title":"Proximal algorithms","authors":"Neal Parikh, Stephen Boyd","year":"2014","venue":"Foundations & Trends in Optimization","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Park et al., 2012] Minsu Park, Chiyoung Cha, and Meey- oung Cha. Depressive moods of users portrayed in twitter. In Proceedings of the ACM SIGKDD Workshop on health- care informatics, pages 1-8, 2012.","title":"Minsu Park, Chiyoung Cha, and Meeyoung Cha. Depressive moods of users portrayed in twitter","authors":"Park","year":"2012","venue":"Proceedings of the ACM SIGKDD Workshop on healthcare informatics","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Park et al., 2013] Minsu Park, David W. McDonald, and Meeyoung Cha. Perception differences between the de- pressed and non-depressed users in twitter. In Proceed- ings of the International Conference on Weblogs and So- cial Media, pages 476-485, 2013.","title":"Perception differences between the depressed and non-depressed users in twitter","authors":"Minsu Park, David W Mcdonald, Meeyoung Cha","year":"2013","venue":"Proceedings of the International Conference on Weblogs and Social Media","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Pedregosa et al., 2011] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, P. Pretten- hofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Cournapeau, M. Brucher, M. Perrot, and E. Duchesnay. Scikit-learn: Machine learning in Python. Journal of Machine Learning Research, 12:2825-2830, 2011.","title":"Scikit-learn: Machine learning in Python","authors":"F Pedregosa, G Varoquaux, A Gramfort, V Michel, B Thirion, O Grisel, P Prettenhofer, R Weiss, V Dubourg, J Vanderplas, A Passos, D Cournapeau, M Brucher, M Perrot, E Duchesnay","year":"2011","venue":"Journal of Machine Learning Research","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Pennebaker et al., 2001] James W. Pennebaker, Martha E. Francis, and Roger J. Booth. Linguistic inquiry and word count. Psychosomatic Medicine, 63:517-522, 2001.","title":"Linguistic inquiry and word count","authors":"James W Pennebaker, Martha E Francis, Roger J Booth","year":"2001","venue":"Psychosomatic Medicine","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Porter, 2001] Martin F Porter. Snowball: A language for stemming algorithms. Retrieved March, 1:2014, 2001.","title":"Snowball: A language for stemming algorithms","authors":"F Martin, Porter","year":"2001","venue":"Retrieved","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Radloff, 1977] Lenore Sawyer Radloff. The ces-d scale: A self-report depression scale for research in the gen- eral population. Applied Psychological Measurement, 1(3):385-401, 1977.","title":"The ces-d scale: A self-report depression scale for research in the general population","authors":"Lenore Radloff, Radloff Sawyer","year":"1977","venue":"Applied Psychological Measurement","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Resnik et al., 2015] Philip Resnik, William Armstrong, Leonardo Claudino, Thang Nguyen, Viet An Nguyen, and Jordan Boyd-Graber. Beyond lda: Exploring supervised topic modeling for depression-related language in twitter. In Proceedings of the 2nd Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Sig- nal to Clinical Reality, pages 99-107, 2015.","title":"Beyond lda: Exploring supervised topic modeling for depression-related language in twitter","authors":"Philip Resnik, William Armstrong, Leonardo Claudino, Thang Nguyen, An Viet, Jordan Nguyen, Boyd-Graber","year":"2015","venue":"Proceedings of the 2nd Workshop on Computational Linguistics and Clinical Psychology: From Linguistic Signal to Clinical Reality","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Rolet et al., 2016] Antoine Rolet, Marco Cuturi, and Gabriel Peyre. Fast Dictionary Learning with a Smoothed Wasserstein Loss. In International Conference on Artifi- cial Intelligence and Statistics, pages 630-638, 2016.","title":"Fast Dictionary Learning with a Smoothed Wasserstein Loss","authors":"Rolet","year":"2016","venue":"International Conference on Artificial Intelligence and Statistics","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Song et al., 2015] Xuemeng Song, Nie Liqiang, Luming Zhang, Mohammad Akbari, and Chua Tat-Seng. Multi- ple Social Network Learning and Its Application in Vol- unteerism Tendency Prediction. In The International ACM SIGIR Conference, pages 213-222, 2015.","title":"Multiple Social Network Learning and Its Application in Volunteerism Tendency Prediction","authors":"Song","year":"2015","venue":"The International ACM SIGIR Conference","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wang et al., 2015] Xiaohui Wang, Jia Jia, Jie Tang, Boya Wu, Lianhong Cai, and Lexing Xie. Modeling emotion influence in image social networks. IEEE Trans. Affective Computing, 6(3):286-297, 2015.","title":"Modeling emotion influence in image social networks","authors":"Xiaohui Wang, Jia Jia, Jie Tang, Boya Wu, Lianhong Cai, Lexing Xie","year":"2015","venue":"IEEE Trans. Affective Computing","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Whooley and Owen, 2014] Whooley and Owen. Diagnostic and Statistical Manual of Mental Disorders (DSM). John Wiley & Sons, Ltd, 2014.","title":"Whooley and Owen. Diagnostic and Statistical Manual of Mental Disorders","authors":"Owen Whooley","year":"2014","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Xu and Zhang, 2016] Ronghua Xu and Qingpeng Zhang. Understanding online health groups for depression: Social network and linguistic perspectives. Journal of Medical Internet Research, 18(3):e63, 2016.","title":"Understanding online health groups for depression: Social network and linguistic perspectives","authors":"Zhang Xu, Ronghua Xu, Qingpeng Zhang","year":"2016","venue":"Journal of Medical Internet Research","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zhang et al., 2016] Hanwang Zhang, Xindi Shang, Huan- Bo Luan, Meng Wang, and Tat-Seng Chua. Learning from collective intelligence: Feature learning using social im- ages and tags. TOMCCAP, 13(1):1:1-1:23, 2016.","title":"Learning from collective intelligence: Feature learning using social images and tags","authors":"Hanwang Zhang, Xindi Shang, Huan-Bo Luan, Meng Wang, Tat-Seng Chua","year":"2016","venue":"TOMCCAP","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}