{"type":"ScholarlyArticle","title":"Psychiatric Scale Guided Risky Post Screening for Early Detection of Depression","authors":[{"name":"Zhiling Zhang","slug":"zhiling-zhang","given":"Zhiling","family":"Zhang","affiliation":"Shanghai Jiao Tong University"},{"name":"Siyuan Chen","slug":"siyuan-chen","given":"Siyuan","family":"Chen","affiliation":"Shanghai Jiao Tong University"},{"name":"Mengyue Wu","slug":"mengyue-wu","given":"Mengyue","family":"Wu","affiliation":"Shanghai Jiao Tong University"},{"name":"Kenny Q. Zhu","slug":"kenny-q-zhu","given":"Kenny Q.","family":"Zhu","affiliation":"Shanghai Jiao Tong University"}],"abstract":"Depression is a prominent health challenge to the world, and early risk detection (ERD) of depression from online posts can be a promising technique for combating the threat. Early depression detection faces the challenge of efficiently tackling streaming data, balancing the tradeoff between timeliness, accuracy and explainability. To tackle these challenges, we propose a psychiatric scale guided risky post screening method that can capture risky posts related to the dimensions defined in clinical depression scales, and providing interpretable diagnostic basis. A Hierarchical Attentional Network equipped with BERT (HAN-BERT) is proposed to further advance explainable predictions. For ERD, we propose an online algorithm based on an evolving queue of risky posts that can significantly reduce the number of model inferences to boost efficiency. Experiments show that our method outperforms the competitive feature-based and neural models under conventional depression detection settings, and achieves simultaneous improvement in both efficacy and efficiency for ERD.","doi":"10.24963/ijcai.2022/725","url":"https://ijcai.org/proceedings/2022/725","pdf":"https://ijcai.org/proceedings/2022/0725.pdf","markdown":"https://ijcai.org/proceedings/2022/725.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/725","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Research Papers","track":"AI for Good","number":725,"pages":{"first":5220,"last":5226},"keywords":["Multidisciplinary Topics and Applications: Web  and Social Networks","Natural Language Processing: Text Classification","Natural Language Processing: General","Multidisciplinary Topics and Applications: Health and Medicine","Machine Learning: Time-series; Data Streams","Machine Learning: Classification","Machine Learning: Attention Models","Multidisciplinary Topics and Applications: General","Humans and AI: Computational Sustainability and Human Well-Being","AI Ethics, Trust, Fairness: Ethical, Legal and Societal Issues","Multidisciplinary Topics and Applications: Sustainable Development Goals","Machine Learning: Sequence and Graph Learning","AI Ethics, Trust, Fairness: Explainability and Interpretability"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38987136","length_sec":79,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38985279","length_sec":705,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Beck et al., 1996] Aaron T Beck, Robert A Steer, and Gre- gory K Brown. Beck depression inventory (BDI-II). Pear- son, 1996.","title":"Beck depression inventory (BDI-II)","authors":"Aaron T Beck, Robert A Steer, Gregory K Brown","year":"1996","venue":null,"doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Blei et al., 2003] David M Blei, Andrew Y Ng, and Michael I Jordan. Latent dirichlet allocation. the Journal of machine Learning research, 2003.","title":"Latent dirichlet allocation","authors":"Andrew Y David M Blei, Michael I Ng, Jordan","year":"2003","venue":"the Journal of machine Learning research","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Devlin et al., 2018] Jacob Devlin, Ming-Wei Chang, Ken- ton Lee, and Kristina Toutanova. Bert: Pre-training of deep bidirectional transformers for language understand- ing. arXiv preprint arXiv:1810.04805, 2018.","title":"Bert: Pre-training of deep bidirectional transformers for language understanding","authors":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, Kristina Toutanova","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Eichstaedt et al., 2018] Johannes C Eichstaedt, Robert J Smith, Raina M Merchant, Lyle H Ungar, Patrick Crutch- ley, Daniel Preot ¸iuc-Pietro, David A Asch, and H Andrew Schwartz. Facebook language predicts depression in med- ical records. Proceedings of the National Academy of Sci- ences, 2018.","title":"Facebook language predicts depression in medical records","authors":"Robert J Johannes C Eichstaedt, Raina M Smith, Lyle H Merchant, Patrick Ungar, Daniel Crutchley, David A Preot ¸iuc-Pietro, H Andrew Asch, Schwartz","year":"2018","venue":"Proceedings of the National Academy of Sciences","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Ernala et al., 2019] Sindhu Kiranmai Ernala, Michael L Birnbaum, Kristin A Candan, Asra F Rizvi, William A Sterling, John M Kane, and Munmun De Choudhury. Methodological gaps in predicting mental health states from social media: triangulating diagnostic signals. In Proceedings of the 2019 chi conference on human factors in computing systems, 2019.","title":"Methodological gaps in predicting mental health states from social media: triangulating diagnostic signals","authors":"Kiranmai Sindhu, Ernala, L Michael, Kristin A Birnbaum, Candan, F Asra, William A Rizvi, John M Sterling, Munmun De Kane, Choudhury","year":"2019","venue":"Proceedings of the 2019 chi conference on human factors in computing systems","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Gratch et al., 2014] Jonathan Gratch, Ron Artstein, Gale Lucas, Giota Stratou, Stefan Scherer, Angela Nazarian, Rachel Wood, Jill Boberg, David DeVault, Stacy Marsella, et al. The distress analysis interview corpus of human and computer interviews. In Proc. of LREC, 2014.","title":"The distress analysis interview corpus of human and computer interviews","authors":"Jonathan Gratch, Ron Artstein, Gale Lucas, Giota Stratou, Stefan Scherer, Angela Nazarian, Rachel Wood, Jill Boberg, David Devault, Stacy Marsella","year":"2014","venue":"Proc. of LREC","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Gui et al., 2019] Tao Gui, Liang Zhu, Qi Zhang, Minlong Peng, Xu Zhou, Keyu Ding, and Zhigang Chen. Cooper- ative multimodal approach to depression detection in twit- ter. In Proc. of AAAI, 2019.","title":"Cooperative multimodal approach to depression detection in twitter","authors":"Tao Gui, Liang Zhu, Qi Zhang, Minlong Peng, Xu Zhou, Keyu Ding, Zhigang Chen","year":"2019","venue":"Proc. of AAAI","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Guntuku et al., 2019] Sharath Chandra Guntuku, Daniel Preotiuc-Pietro, Johannes C Eichstaedt, and Lyle H Un- gar. What twitter profile and posted images reveal about depression and anxiety. In Proc. of AAAI, 2019.","title":"What twitter profile and posted images reveal about depression and anxiety","authors":"Chandra Sharath, Daniel Guntuku, Johannes C Preotiuc-Pietro, Lyle H Eichstaedt, Ungar","year":"2019","venue":"Proc. of AAAI","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Harrigian et al., 2020] Keith Harrigian, Carlos Aguirre, and Mark Dredze. Do models of mental health based on social media data generalize? In Proc. of EMNLP, 2020.","title":"Do models of mental health based on social media data generalize?","authors":"Keith Harrigian, Carlos Aguirre, Mark Dredze","year":"2020","venue":"Proc. of EMNLP","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Kroenke et al., 2001] Kurt Kroenke, Robert L Spitzer, and Janet BW Williams. The phq-9: validity of a brief de- pression severity measure. Journal of general internal medicine, 2001.","title":"The phq-9: validity of a brief depression severity measure","authors":"Kroenke","year":"2001","venue":"Journal of general internal medicine","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Lewis et al., 2020] Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, and Luke Zettlemoyer. Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension. In Proc. of ACL, 2020.","title":"Bart: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","authors":"Mike Lewis, Yinhan Liu, Naman Goyal, Marjan Ghazvininejad, Abdelrahman Mohamed, Omer Levy, Veselin Stoyanov, Luke Zettlemoyer","year":"2020","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Losada and Crestani, 2016] David E Losada and Fabio Crestani. A test collection for research on depression and language use. In International Conference of the Cross- Language Evaluation Forum for European Languages, 2016. Losada et al., 2017]","title":"A test collection for research on depression and language use","authors":"E David, Fabio Losada, Crestani","year":"2016","venue":"International Conference of the Cross-Language Evaluation Forum for European Languages","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"David E Losada, Fabio Crestani, and Javier Parapar. erisk 2017: Clef lab on early risk prediction on the internet: experimental foundations. In International Conference of the Cross-Language Evaluation Forum for European Languages, 2017.","title":"erisk 2017: Clef lab on early risk prediction on the internet: experimental foundations","authors":"Fabio David E Losada, Javier Crestani, Parapar","year":"2017","venue":"International Conference of the Cross-Language Evaluation Forum for European Languages","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Losada et al., 2019] David E Losada, Fabio Crestani, and Javier Parapar. Overview of erisk 2019 early risk pre- diction on the internet. In International Conference of the Cross-Language Evaluation Forum for European Lan- guages, 2019.","title":"Overview of erisk 2019 early risk prediction on the internet","authors":"Fabio David E Losada, Javier Crestani, Parapar","year":"2019","venue":"International Conference of the Cross-Language Evaluation Forum for European Languages","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Mowery et al., 2017] Danielle Mowery, Hilary Smith, Tyler Cheney, Greg Stoddard, Glen Coppersmith, Craig Bryan, and Mike Conway. Understanding depressive symptoms and psychosocial stressors on twitter: a corpus-based study. Journal of medical Internet research, 2017.","title":"Understanding depressive symptoms and psychosocial stressors on twitter: a corpus-based study","authors":"Danielle Mowery, Hilary Smith, Tyler Cheney, Greg Stoddard, Glen Coppersmith, Craig Bryan, Mike Conway","year":"2017","venue":"Journal of medical Internet 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: Liwc 2001. Mahway: Lawrence Erlbaum Asso- ciates, 2001.","title":"Linguistic inquiry and word count: Liwc 2001","authors":"Martha E James W Pennebaker, Roger J Francis, Booth","year":"2001","venue":null,"doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Reimers and Gurevych, 2019] Nils Reimers and Iryna Gurevych. Sentence-bert: Sentence embeddings using siamese bert-networks. In Proc. of EMNLP, 2019.","title":"Sentence-bert: Sentence embeddings using siamese bert-networks","authors":"Gurevych Reimers, Nils Reimers, Iryna Gurevych","year":"2019","venue":"Proc. of EMNLP","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Ribeiro et al., 2020] Marco Tulio Ribeiro, Tongshuang Wu, Carlos Guestrin, and Sameer Singh. Beyond accuracy: Be- havioral testing of nlp models with checklist. In Proc. of ACL, 2020.","title":"Beyond accuracy: Behavioral testing of nlp models with checklist","authors":"Marco Tulio Ribeiro, Tongshuang Wu, Carlos Guestrin, Sameer Singh","year":"2020","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Shen et al., 2017] Guangyao Shen, Jia Jia, Liqiang Nie, Fuli Feng, Cunjun Zhang, Tianrui Hu, Tat-Seng Chua, and Wenwu Zhu. Depression detection via harvesting social media: A multimodal dictionary learning solution. In Proc. of IJCAI, 2017.","title":"Depression detection via harvesting social media: A multimodal dictionary learning solution","authors":"Guangyao Shen, Jia Jia, Liqiang Nie, Fuli Feng, Cunjun Zhang, Tianrui Hu, Tat-Seng Chua, Wenwu Zhu","year":"2017","venue":"Proc. of IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2017/536"},{"position":20,"raw":"[Trotzek et al., 2018] Marcel Trotzek, Sven Koitka, and Christoph M Friedrich. Utilizing neural networks and lin- guistic metadata for early detection of depression indica- tions in text sequences. IEEE Transactions on Knowledge and Data Engineering, 2018.","title":"Utilizing neural networks and linguistic metadata for early detection of depression indications in text sequences","authors":"Trotzek","year":"2018","venue":"IEEE Transactions on Knowledge and Data Engineering","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Yang et al., 2016] Zichao Yang, Diyi Yang, Chris Dyer, Xi- aodong He, Alex Smola, and Eduard Hovy. Hierarchical attention networks for document classification. In Proc. of ACL, 2016.","title":"Hierarchical attention networks for document classification","authors":"Yang","year":"2016","venue":"Proc. of ACL","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Yates et al., 2017] Andrew Yates, Arman Cohan, and Nazli Goharian. Depression and self-harm risk assessment in online forums. In Proc. of EMNLP, 2017.","title":"Depression and self-harm risk assessment in online forums","authors":"Andrew Yates, Arman Cohan, Nazli Goharian","year":"2017","venue":"Proc. of EMNLP","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Zogan et al., 2021a] Hamad Zogan, Imran Razzak, Shoaib Jameel, and Guandong Xu. Depressionnet: A novel sum- marization boosted deep framework for depression detec- tion on social media. arXiv preprint arXiv:2105.10878, 2021.","title":"Depressionnet: A novel summarization boosted deep framework for depression detection on social media","authors":"Zogan","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Zogan et al., 2021b] Hamad Zogan, Imran Razzak, Xianzhi Wang, Shoaib Jameel, and Guandong Xu. Explainable depression detection with multi-modalities using a hy- brid deep learning model on social media. arXiv preprint arXiv:2007.02847, 2021.","title":"Explainable depression detection with multi-modalities using a hybrid deep learning model on social media","authors":"Zogan","year":"2021","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}