Background Ecological Momentary Assessments (EMA) offer an approach to understand the daily risk factors of suicide and self-harm of individuals through the use of self-monitoring techniques using mobile technologies. Objectives This systematic review aimed to examine the results of studies on suicidality risk factors and self-harm that used Ecological Momentary Assessments. Methods Pubmed and PsycINFO databases were searched up to April 2020. Bibliographies of eligible studies were hand-searched, and 744 abstracts were screened and double-coded for inclusion. Results The 49 studies using EMA included in the review found associations between daily affect, rumination and interpersonal interactions and daily non-suicidal self-injury (NSSI). Studies also found associations between daily negative affect and positive affect, social support, sleep, and emotions and a person’s history of suicide and self-harm. Associations between daily suicide thoughts and self-harm, and psychopathology factors measured at baseline were also observed. Conclusions Research using EMA has the potential to offer clinicians the ability to understand the daily predictors, or risk factors, of suicide and self-harm. However, there are no clear reporting standards for EMA studies on risk factors for suicide. Further research should utilise longitudinal study designs, harmonise datasets and use machine learning techniques to identify patterns of proximal risk factors for suicide behaviours.

This study found a small significant effect of EMI studies on reducing generalized anxiety. Studies on stress demonstrated EMI was effective compared to control, with the small number of studies on panic and social phobia demonstrating mixed results.

This review found no significant interventions in prisons. However, the qualitative findings showed evidence of best practice.

Background: Assisting moderators to triage harmful posts in Internet Support Groups is relevant to ensure its safe use. Automated text classification methods analysing the language expressed in posts of online forums is a promising solution.Methods: Natural Language Processing and Machine Learning technologies were used to build a triage post classifier using a dataset from Reachout.com mental health forum for young people.Results: When comparing with the state-of-the-art, a solution mainly based on features from lexical resources, received the best classification performance for the crisis posts (52%), which is the most severe class. Six salient linguistic characteristics were found when analysing the crisis post; (1) posts expressing hopelessness, (2) short posts expressing concise negative emotional responses, (3) long posts expressing variations of emotions, (4) posts expressing dissatisfaction with available health services, (5) posts utilising storytelling, and (6) posts expressing users seeking advice from peers during a crisis. Conclusion:It is possible to build a competitive triage classifier using features derived only from the textual content of the post. Further research needs to be done in order to translate our quantitative and qualitative findings into features, as it may improve overall performance.