The detection of suicide risk in social media is a critical task with potential life-saving implications. This paper presents a study on leveraging state-of-the-art natural language processing solutions for identifying suicide risk in social media posts as a submission for the "IEEE BigData 2024 Cup: Detection of Suicide Risk on Social Media" conducted by the kubapok team. We experimented with the following configurations of transformer-based models: fine-tuned DeBERTa, GPT-4o with CoT and few-shot prompting, and fine-tuned GPT-4o. The task setup was to classify social media posts into four categories: indicator, ideation, behavior, and attempt. Our findings demonstrate that the fine-tuned GPT-4o model outperforms two other configurations, achieving high accuracy in identifying suicide risk. Notably, our model achieved second place in the competition. By demonstrating that straightforward, general-purpose models can achieve state-of-the-art results, we propose that these models, combined with minimal tuning, may have the potential to be effective solutions for automated suicide risk detection on social media.

Suicide is a pressing global issue, demanding urgent and effective preventive interventions. Among the various strategies in place, psychological support hotlines had proved as a potent intervention method. Approximately two million people in China attempt suicide annually, with many individuals making multiple attempts. Prompt identification and intervention for high-risk individuals are crucial to preventing tragedies. With the rapid advancement of artificial intelligence (AI), especially the development of large-scale language models (LLMs), new technological tools have been introduced to the field of mental health. This study included 1284 subjects, and was designed to validate whether deep learning models and LLMs, using audio and transcribed text from support hotlines, can effectively predict suicide risk. We proposed a simple LLM-based pipeline that first summarizes transcribed text from approximately one hour of speech to extract key features, and then predict suicidial bahaviours in the future. We compared our LLM-based method with the traditional manual scale approach in a clinical setting and with five advanced deep learning models. Surprisingly, the proposed simple LLM pipeline achieved strong performance on a test set of 46 subjects, with an F1 score of 76\% when combined with manual scale rating. This is 7\% higher than the best speech-based deep learning models and represents a 27.82\% point improvement in F1 score compared to using the manual scale apporach alone. Our study explores new applications of LLMs and demonstrates their potential for future use in suicide prevention efforts.

Psychological support hotlines are an effective suicide prevention measure that typically relies on professionals using suicide risk assessment scales to predict individual risk scores. However, the accuracy of scale-based predictive methods for suicide risk assessment can vary widely depending on the expertise of the operator. This limitation underscores the need for more reliable methods, prompting this research's innovative exploration of the use of artificial intelligence to improve the accuracy and efficiency of suicide risk prediction within the context of psychological support hotlines. The study included data from 1,549 subjects from 2015-2017 in China who contacted a psychological support hotline. Each participant was followed for 12 months to identify instances of suicidal behavior. We proposed a novel multi-task learning method that uses the large-scale pre-trained model Whisper for feature extraction and fits psychological scales while predicting the risk of suicide. The proposed method yields a 2.4\% points improvement in F1-score compared to the traditional manual approach based on the psychological scales. Our model demonstrated superior performance compared to the other eight popular models. To our knowledge, this study is the first to apply deep learning to long-term speech data to predict suicide risk in China, indicating grate potential for clinical applications. The source code is publicly available at: \url{https://github.com/songchangwei/Suicide-Risk-Prediction}.

Among young adults, suicide is India's leading cause of death, accounting for an alarming national suicide rate of around 16%. In recent years, machine learning algorithms have emerged to predict suicidal behavior using various behavioral traits. But to date, the efficacy of machine learning algorithms in predicting suicidal behavior in the Indian context has not been explored in literature. In this study, different machine learning algorithms and ensembles were developed to predict suicide behavior based on childhood trauma, different mental health parameters, and other behavioral factors. The dataset was acquired from 391 individuals from a wellness center in India. Information regarding their childhood trauma, psychological wellness, and other mental health issues was acquired through standardized questionnaires. Results revealed that cascade ensemble learning methods using a support vector machine, decision trees, and random forest were able to classify suicidal behavior with an accuracy of 95.04% using data from childhood trauma and mental health questionnaires. The study highlights the potential of using these machine learning ensembles to identify individuals with suicidal tendencies so that targeted interinterventions could be provided efficiently.

These are suicidal thoughts, anxiety, depressive symptoms, and self-esteem. AI identifies main predictors of suicidal behaviors.

This article presents a novel method for predicting suicidal ideation from Electronic Health Records (EHR) and Ecological Momentary Assessment (EMA) data using deep sequential models. Both EHR longitudinal data and EMA question forms are defined by asynchronous, variable length, randomly-sampled data sequences. In our method, we model each of them with a Recurrent Neural Network (RNN), and both sequences are aligned by concatenating the hidden state of each of them using temporal marks. Furthermore, we incorporate attention schemes to improve performance in long sequences and time-independent pre-trained schemes to cope with very short sequences. Using a database of 1023 patients, our experimental results show that the addition of EMA records boosts the system recall to predict the suicidal ideation diagnosis from 48.13% obtained exclusively from EHR-based state-of-the-art methods to 67.78%. Additionally, our method provides interpretability through the t-SNE representation of the latent space. Further, the most relevant input features are identified and interpreted medically.

The post caught the attention of Facebook's AI system, which is programmed to spot potential suicidal language. The system decided it was an emergency and passed it along to moderators for review, who then alerted authorities in Buenos Aires. Before long, first responders were on the scene. "Artificial intelligence can be a very powerful tool," says Enrique del Carril, the investigations director in the district attorney's office in Buenos Aires. "We saved a woman far away in remote Argentina before something terrible happened. Facebook's suicide-alert system is just one of many efforts to use artificial intelligence to help identify people at risk for suicide as early as possible. In these programs, researchers use computers to comb through massive amounts of data, such as electronic health records, social-media posts, and audio and video recordings of patients, to find common threads among people who attempted suicide. Then algorithms can start to predict which new patients are more ...

Living in a modern age, one would think that suicide would be a less common occurrence. Sadly, that isn't the case, and the World Health Organization (WHO) reports that worldwide suicide rates have increased by 60 percent in the last 45 years. Current statistics show that some one million people die from suicide each year, and the WHO anticipates that by 2020 global suicide rate will have increased from one every 40 seconds we see today to one every 20 seconds. That's why a team of researchers from several institutions including Carnegie Mellon University and Harvard University developed a machine learning algorithm trained to understand neural representations of suicidal behavior, and it works with a regular functional magnetic resonance imaging (fMRI). The researchers tested their technique in 17 patients with suicidal ideation and in 17 more that served as control.

A groundbreaking project led by a Florida State University researcher makes an exponential advance in suicide prediction, potentially giving clinicians the ability to predict who will attempt suicide up to two years in advance with 80 percent accuracy. FSU Psychology researcher Jessica Ribeiro feels an urgency to confront this relentless problem. Shadowing her research is the ever-present awareness that 120 Americans take their lives every day, nearly 45,000 a year. Ribeiro's paper, titled "Predicting Risk of Suicide Attempts over Time through Machine Learning," will be published by the journal Clinical Psychological Science. The study offers a fascinating finding: machine learning -- a future frontier for artificial intelligence -- can predict with 80-90 percent accuracy whether someone will attempt suicide as far off as two years into the future.

About 20 percent of youth in the United States live with a mental health condition, according to the National Institute of Mental Health. The good news is that mental health professionals have smarter tools than ever before, with artificial intelligence-related technology coming to the forefront to help diagnose patients, often with much greater accuracy than humans. A new study published in the journal Suicide and Life-Threatening Behavior, for example, showed that machine learning is up to 93 percent accurate in identifying a suicidal person. The research, led by John Pestian, a professor at Cincinnati Children's Hospital Medical Center, involved 379 teenage patients from three area hospitals. Each patient completed standardized behavioral rating scales and participated in a semi-structured interview, answering five open-ended questions such as "Are you angry?" to stimulate conversation, according to a press release from the university.