Findings of empirical studies of spatial memory using maps are direct responses to the successful transfer and processing of map information. The memory performance of map users is an important indication of the quality of a map design. Studies of spatial memory have mainly relied on recall performances, but maps can be used in various ways depending on the map user's task and applied strategy. Therefore, one memory paradigm does not cover the entire spectrum of options for examining the retrieval of map information. Three different experiments were designed to analyze and compare memory performances using different map information in recall and recognition (combining episodic and semantic memory) paradigms. The results demonstrate that map complexity, as varied by the amount of displayed map detail, contributes significantly to memory performance. Moreover, memory enhancement affected by map-structuring elements (grids) depends on the respective paradigm and also on the visual appearance of the structuring elements. Both paradigms for examining the influence of map information on cognitive processing can be applied specifically to analyze the efficiency of map designs. On the basis of the different effects of map information, a reasoned application of these paradigms to test map designs is indispensable.

Background: Suicide represents a critical public health concern, and machine learning (ML) models offer the potential for identifying at-risk individuals. Recent studies using benchmark datasets and real-world social media data have demonstrated the capability of pretrained large language models in predicting suicidal ideation and behaviors (SIB) in speech and text. Objective: This study aimed to (1) develop and implement ML methods for predicting SIBs in a real-world crisis helpline dataset, using transformer-based pretrained models as a foundation; (2) evaluate, cross-validate, and benchmark the model against traditional text classification approaches; and (3) train an explainable model to highlight relevant risk-associated features. Methods: We analyzed chat protocols from adolescents and young adults (aged 14-25 years) seeking assistance from a German crisis helpline. An ML model was developed using a transformer-based language model architecture with pretrained weights and long short-term memory layers. The model predicted suicidal ideation (SI) and advanced suicidal engagement (ASE), as indicated by composite Columbia-Suicide Severity Rating Scale scores. We compared model performance against a classical word-vector-based ML model. We subsequently computed discrimination, calibration, clinical utility, and explainability information using a Shapley Additive Explanations value-based post hoc estimation model. Results: The dataset comprised 1348 help-seeking encounters (1011 for training and 337 for testing). The transformer-based classifier achieved a macroaveraged area under the curve (AUC) receiver operating characteristic (ROC) of 0.89 (95% CI 0.81-0.91) and an overall accuracy of 0.79 (95% CI 0.73-0.99). This performance surpassed the word-vector-based baseline model (AUC-ROC=0.77, 95% CI 0.64-0.90; accuracy=0.61, 95% CI 0.61-0.80). The transformer model demonstrated excellent prediction for nonsuicidal sessions (AUC-ROC=0.96, 95% CI 0.96-0.99) and good prediction for SI and ASE, with AUC-ROCs of 0.85 (95% CI 0.97-0.86) and 0.87 (95% CI 0.81-0.88), respectively. The Brier Skill Score indicated a 44% improvement in classification performance over the baseline model. The Shapley Additive Explanations model identified language features predictive of SIBs, including self-reference, negation, expressions of low self-esteem, and absolutist language. Conclusions: Neural networks using large language model–based transfer learning can accurately identify SI and ASE. The post hoc explainer model revealed language features associated with SI and ASE. Such models may potentially support clinical decision-making in suicide prevention services. Future research should explore multimodal input features and temporal aspects of suicide risk.

Map-based navigation is a diverse task that stands in contradiction to the goal of completeness of web mapping services. As each navigation task is different, it also requires and can dispense with different map information to support effective and efficient wayfinding. Task-oriented reduction of the elements displayed in a map may therefore support navigation. In order to investigate effects of map reduction on route recognition and visual attention towards specific map elements, we created maps in which areas offside an inserted route were displayed as transparent. In a route memory experiment, where participants had to memorize routes and match them to routes displayed in following stimuli, these maps were compared to unmodified maps. Eye movement analyses revealed that in the reduced maps, areas offside the route were fixated less often. Route recognition performance was not affected by the map reduction. Our results indicate that task-oriented map reduction may direct visual attention towards relevant map elements at no cost for route recognition.