Objective We aimed to identify and understand risk and protective factors for suicide among South Korean females by linking survey and social media data and using interpretable machine learning approaches. Materials and Methods We collected a wide range of potential factors including the material, psychosocial, and behavioral data from a detailed survey, which we then linked to data from social media. In addition, we adopted interpretable machine learning approaches to (1) predict the suicide risk, (2) explain the relative importance of factors and their interactions regarding suicide, and (3) understand individual differences affecting suicide risk. Results The best‐performing machine learning model achieved an AUC of 0.737. Adverse childhood experiences, social connectedness, and mean positive sentiment score of social media posts were the three risk factors that had a monotonic or unimodal relationship with suicide, and satisfaction with life, narcissistic self‐presentation, and number of close friends on social media were the three protective factors that had a monotonic or unimodal relationship with suicide. We also found several meaningful interactions between specific psychiatric symptoms and narcissistic self‐presentation. Conclusions Our findings can help governmental organizations to better assess female suicide risk in South Korea and develop more informed and customized suicide prevention strategies.

IntroductionStudies have shown that suicide is closely related to various social factors. However, due to the restriction in the data scale, our understanding of these social factors is still limited. We propose a conceptual framework for understanding social determinants of suicide at the national level and investigate the relationships between structural determinants (i.e., gender, employment statuses, and occupation) and suicide outcomes (i.e., types of suicide, places of suicide, suicide methods, and warning signs) in South Korea.MethodsWe linked a national-level suicide registry from the Korea Psychological Autopsy Center with the Social Determinants of Health framework proposed by the World Health Organization's Commission on Social Determinants of Health.ResultsFirst, male and female suicide victims have clear differences in their typical suicide methods (fire vs. drug overdose), primary warning signs (verbal vs. mood), and places of death (suburb vs. home). Second, employees accounted for the largest proportion of murder-suicides (>30%). The proportion of students was much higher for joint suicides than for individual suicides and murder-suicides. Third, among individuals choosing pesticides as their suicide method, over 50% were primary workers. In terms of drug overdoses, professionals and laborers accounted for the largest percentage; the former also constituted the largest proportion in the method of jumping from heights.ConclusionA clear connection exists between the investigated structural factors and various suicide outcomes, with gender, social class, and occupation all impacting suicide.

Coauthorship prediction applies predictive analytics to bibliographic data to predict authors who are highly likely to be coauthors. In this study, we propose an approach for coauthorship prediction based on bibliographic network embedding through a graph‐based bibliographic data model that can be used to model common bibliographic data, including papers, terms, sources, authors, departments, research interests, universities, and countries. A real‐world dataset released by AMiner that includes more than 2 million papers, 8 million citations, and 1.7 million authors were integrated into a large bibliographic network using the proposed bibliographic data model. Translation‐based methods were applied to the entities and relationships to generate their low‐dimensional embeddings while preserving their connectivity information in the original bibliographic network. We applied machine learning algorithms to embeddings that represent the coauthorship relationships of the two authors and achieved high prediction results. The reference model, which is the combination of a network embedding size of 100, the most basic translation‐based method, and a gradient boosting method achieved an F1 score of 0.9 and even higher scores are obtainable with different embedding sizes and more advanced embedding methods. Thus, the strengths of the proposed approach lie in its customizable components under a unified framework.