⚡ Quick Summary
This study developed an explainable predictive model to detect suicidal ideation during the COVID-19 pandemic by analyzing social media discourse. Utilizing a hybrid deep learning approach, the model achieved impressive metrics, including a precision of 94% and an accuracy of 93.65%.
🔍 Key Details
- 📊 Dataset: 348,110 social media records analyzed
- 🧩 Features used: Textual content from social media posts
- ⚙️ Technology: Hybrid model combining BERT, CNN, and LSTM
- 🏆 Performance: Precision 94%, Recall 95%, F1-score 94%, Accuracy 93.65%
🔑 Key Takeaways
- 📊 Social media analysis provides a novel approach to understanding mental health trends.
- 💡 Natural Language Processing (NLP) techniques were effectively utilized to classify posts.
- 👩🔬 The model identified 1,338 suicidal and 1,816 nonsuicidal instances from the dataset.
- 🏆 The hybrid model outperformed traditional methods in detecting suicidal ideation.
- 🌍 The study highlights the evolving language patterns associated with suicidal thoughts during the pandemic.
- 🔍 Explainable AI techniques like LIME and SHAP were used to interpret model predictions.
- 🆔 Future strategies are needed to address the mental health crisis exacerbated by COVID-19.
📚 Background
The COVID-19 pandemic has significantly impacted mental health globally, leading to increased rates of depression and suicidal ideation. Traditional methods of assessing mental health often involve clinical assessments, which can be limited in scope. This study explores the potential of social media as a rich source of data to understand and detect suicidal thoughts, thereby addressing the stigma surrounding mental health issues.
🗒️ Study
Conducted by researchers Bouktif et al., this study aimed to leverage social media discourse to identify and classify posts related to suicidal ideation during the pandemic. The research was divided into two phases: classifying posts as suicidal or nonsuicidal and extracting factors contributing to suicidal ideation. A hybrid deep learning model combining BERT, convolutional neural networks (CNN), and long short-term memory (LSTM) networks was employed for this purpose.
📈 Results
Out of the analyzed records, the model successfully identified 1,338 suicidal and 1,816 nonsuicidal posts. The hybrid model demonstrated exceptional performance, achieving a precision of 94%, a recall of 95%, and an accuracy of 93.65%. These results underscore the model’s effectiveness in detecting nuanced expressions of suicidal ideation in social media content.
🌍 Impact and Implications
The findings of this study have significant implications for mental health monitoring and intervention strategies. By utilizing social media data, healthcare providers can gain insights into the evolving language patterns associated with suicidal thoughts, enabling timely interventions. This approach not only enhances our understanding of mental health trends during crises but also paves the way for developing targeted strategies to combat the mental health challenges exacerbated by the pandemic.
🔮 Conclusion
This research highlights the transformative potential of machine learning and natural language processing in understanding and addressing mental health issues. The hybrid model developed in this study offers a promising tool for detecting suicidal ideation, emphasizing the need for ongoing research and innovative strategies to support mental health during and beyond the COVID-19 pandemic. The future of mental health monitoring looks promising with the integration of AI technologies!
💬 Your comments
What are your thoughts on using social media data to monitor mental health trends? We’d love to hear your insights! 💬 Leave your comments below or connect with us on social media:
Explainable Predictive Model for Suicidal Ideation During COVID-19: Social Media Discourse Study.
Abstract
BACKGROUND: Studying the impact of COVID-19 on mental health is both compelling and imperative for the health care system’s preparedness development. Discovering how pandemic conditions and governmental strategies and measures have impacted mental health is a challenging task. Mental health issues, such as depression and suicidal tendency, are traditionally explored through psychological battery tests and clinical procedures. To address the stigma associated with mental illness, social media is used to examine language patterns in posts related to suicide. This strategy enhances the comprehension and interpretation of suicidal ideation. Despite easy expression via social media, suicidal thoughts remain sensitive and complex to comprehend and detect. Suicidal ideation captures the new suicidal statements used during the COVID-19 pandemic that represents a different context of expressions.
OBJECTIVE: In this study, our aim was to detect suicidal ideation by mining textual content extracted from social media by leveraging state-of-the-art natural language processing (NLP) techniques.
METHODS: The work was divided into 2 major phases, one to classify suicidal ideation posts and the other to extract factors that cause suicidal ideation. We proposed a hybrid deep learning-based neural network approach (Bidirectional Encoder Representations from Transformers [BERT]+convolutional neural network [CNN]+long short-term memory [LSTM]) to classify suicidal and nonsuicidal posts. Two state-of-the-art deep learning approaches (CNN and LSTM) were combined based on features (terms) selected from term frequency-inverse document frequency (TF-IDF), Word2vec, and BERT. Explainable artificial intelligence (XAI) was used to extract key factors that contribute to suicidal ideation in order to provide a reliable and sustainable solution.
RESULTS: Of 348,110 records, 3154 (0.9%) were selected, resulting in 1338 (42.4%) suicidal and 1816 (57.6%) nonsuicidal instances. The CNN+LSTM+BERT model achieved superior performance, with a precision of 94%, a recall of 95%, an F1-score of 94%, and an accuracy of 93.65%.
CONCLUSIONS: Considering the dynamic nature of suicidal behavior posts, we proposed a fused architecture that captures both localized and generalized contextual information that is important for understanding the language patterns and predict the evolution of suicidal ideation over time. According to Local Interpretable Model-Agnostic Explanations (LIME) and Shapley Additive Explanations (SHAP) XAI algorithms, there was a drift in the features during and before COVID-19. Due to the COVID-19 pandemic, new features have been added, which leads to suicidal tendencies. In the future, strategies need to be developed to combat this deadly disease.
Author: [‘Bouktif S’, ‘Khanday AMUD’, ‘Ouni A’]
Journal: J Med Internet Res
Citation: Bouktif S, et al. Explainable Predictive Model for Suicidal Ideation During COVID-19: Social Media Discourse Study. Explainable Predictive Model for Suicidal Ideation During COVID-19: Social Media Discourse Study. 2025; 27:e65434. doi: 10.2196/65434