Automatic identification of suicide notes with a transformer-based deep learning model

Zhang, Tianlin; Schoene, Annika Marie; Ananiadou, Sophia

doi:10.1016/j.invent.2021.100422

Cited by 33 publications

(12 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“… LSTM or GRU with multiple instance learning 145 , 146 Using multiple instance learning to get the possibility of post-level labels and improve the prediction of user-level labels. SISMO 139 An ordinal hierarchical LSTM attention model Transformer-based methods Self-attention models 148 , 149 Using the encoder structure of transformer which has self-attention module. BERT-based models (BERT 150 , 151 , DistilBERT 152 , RoBERTa 153 , ALBERT 150 , BioClinical BERT 31 , XLNET 154 , GPT-1 155 ) Different BERT-based pre-trained models.…”

Section: Resultsmentioning

confidence: 99%

“…Wang et al proposed the C-Attention network 148 by using a transformer encoder block with multi-head self-attention and convolution processing. Zhang et al also presented their TransformerRNN with multi-head self-attention 149 . Additionally, many researchers leveraged transformer-based pre-trained language representation models, including BERT 150 , 151 , DistilBERT 152 , Roberta 153 , ALBERT 150 , BioClinical BERT for clinical notes 31 , XLNET 154 , and GPT model 155 .…”

Section: Resultsmentioning

confidence: 99%

“…Evaluation metrics are used to compare the performance of different models for mental illness detection tasks. Some tasks can be regarded as a classification problem, thus the most widely used standard evaluation metrics are Accuracy (AC), Precision (P), Recall (R), and F1-score (F1) 149 , 168 – 170 . Similarly, the area under the ROC curve (AUC-ROC) 60 , 171 , 172 is also used as a classification metric which can measure the true positive rate and false positive rate.…”

Section: Resultsmentioning

confidence: 99%

See 2 more Smart Citations

Natural language processing applied to mental illness detection: a narrative review

et al. 2022

Self Cite

View full text Add to dashboard Cite

Mental illness is highly prevalent nowadays, constituting a major cause of distress in people’s life with impact on society’s health and well-being. Mental illness is a complex multi-factorial disease associated with individual risk factors and a variety of socioeconomic, clinical associations. In order to capture these complex associations expressed in a wide variety of textual data, including social media posts, interviews, and clinical notes, natural language processing (NLP) methods demonstrate promising improvements to empower proactive mental healthcare and assist early diagnosis. We provide a narrative review of mental illness detection using NLP in the past decade, to understand methods, trends, challenges and future directions. A total of 399 studies from 10,467 records were included. The review reveals that there is an upward trend in mental illness detection NLP research. Deep learning methods receive more attention and perform better than traditional machine learning methods. We also provide some recommendations for future studies, including the development of novel detection methods, deep learning paradigms and interpretable models.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Natural language processing applied to mental illness detection: a narrative review

et al. 2022

Self Cite

View full text Add to dashboard Cite

show abstract

“…A cross-sectional assessment of structural Magnetic Resonance Imaging (MRI) data with a support vector machine learning model for a sample of adolescents/young adults diagnosed with major depression disorder found a high-level of accuracy for predicting those with suicide ideation and/or attempts ( Hong et al, 2021 ). A transformer-based deep learning model sought suicide risk identification from social media sources – it was proposed as effective for classifying suicide notes (i.e., contextual and long-term dependency information determined from different datasets) ( Zhang et al, 2021 ). Machine learning helps analyze big data easier by automating processes – this helps support a better predictive potential of an individual’s suicide risk but there is yet to be accurate prediction of specific risks across populations.…”

Section: Current State Of the Art – Digital Tools And Technologymentioning

confidence: 99%

The Potential Impact of Adjunct Digital Tools and Technology to Help Distressed and Suicidal Men: An Integrative Review

Balcombe

Leo

2022

Front. Psychol.

View full text Add to dashboard Cite

Suicidal men feel the need to be self-reliant and that they cannot find another way out of relationship or socioeconomic issues. Suicide prevention is of crucial importance worldwide. The much higher rate of suicide in men engenders action. The prelude is a subjective experience that can be very isolating and severely distressing. Men may not realize a change in their thinking and behaviors, which makes it more difficult to seek and get help, thereby interrupting a “downward spiral”. Stoicism often prevents men from admitting to their personal struggle. The lack of “quality” connections and “non-tailored” therapies has led to a high number of men “walking out” on traditional clinical approaches. But there are complicated relationships in motivations and formative behaviors of suicide with regards to emotional state, psychiatric disorders, interpersonal life events and suicidal behavior method selection. Middle-aged and older men have alternated as the most at-risk of suicide. There is no one solution that applies to all men, but digital tools may be of assistance (e.g., video conferences, social networks, telephone calls, and emails). Digital interventions require higher levels of effectiveness for distress and suicidality but self-guided approaches may be the most suitable for men especially where linked with an integrated online suicide prevention platform (e.g., quick response with online chats, phone calls, and emails). Furthermore, technology-enabled models of care offer promise to advance appropriate linking to mental health services through better and faster understanding of the specific needs of individuals (e.g., socio-cultural) and the type and level of suicidality experienced. Long-term evidence for suicidality and its evaluation may benefit from progressing human computer-interaction and providing impetus for an eminent integrated digital platform.

show abstract

“…However, the corpus was later discontinued for usage due to privacy concerns. Other related corpora are either very small in size 42 , 43 or are not essentially developed from genuine suicide notes 44 , 45 . The Northern Ireland Suicide Study 42 comprises a compilation of data from a range of documentation sources, including coroners’ files, including suicide notes.…”

Section: Related Workmentioning

confidence: 99%

Deep cascaded multitask framework for detection of temporal orientation, sentiment and emotion from suicide notes

Ghosh

Ekbal

Bhattacharyya

2022

Sci Rep

View full text Add to dashboard Cite

With the upsurge in suicide rates worldwide, timely identification of the at-risk individuals using computational methods has been a severe challenge. Anyone presenting with suicidal thoughts, mainly recurring and containing a deep desire to die, requires urgent and ongoing psychiatric treatment. This work focuses on investigating the role of temporal orientation and sentiment classification (auxiliary tasks) in jointly analyzing the victims’ emotional state (primary task). Our model leverages the effectiveness of multitask learning by sharing features among the tasks through a novel multi-layer cascaded shared-private attentive network. We conducted our experiments on a diversified version of the prevailing standard emotion annotated corpus of suicide notes in English, CEASE-v2.0. Experiments show that our proposed multitask framework outperforms the existing state-of-the-art system by 3.78% in the Emotion task, with a cross-validation Mean Recall (MR) of 60.90%. From our empirical and qualitative analysis of results, we observe that learning the tasks of temporality and sentiment together has a clear correlation with emotion recognition.

show abstract

Automatic identification of suicide notes with a transformer-based deep learning model

Cited by 33 publications

References 35 publications

Natural language processing applied to mental illness detection: a narrative review

Natural language processing applied to mental illness detection: a narrative review

The Potential Impact of Adjunct Digital Tools and Technology to Help Distressed and Suicidal Men: An Integrative Review

Deep cascaded multitask framework for detection of temporal orientation, sentiment and emotion from suicide notes

Contact Info

Product

Resources

About