Visualizing Evidence through Natural Language Interaction for Public Health Interventions

With the rapid growth of data and the increasing complexity of health information, there is a pressing need for advanced tools that facilitate data interpretation and support evidence-based decision-making. Visualizing scientific evidence is crucial for transforming complex data into actionable insights in public health. Natural Language Interfaces (NLIs) offer a promising approach, enabling users to efficiently navigate vast textual data, uncover hidden insights, and enhance information extraction (IE) processes. This study conceptualizes a prototype taxonomy for systematic review data, streamlining key processes like query interpretation, data transformation, and visual mapping to enhance evidence synthesis and decision-making, empowering decision-makers to make informed, evidence-based choices. We present a conceptual design that enhances user engagement and enables intuitive interactions with the visualization pipeline, simplifying the complexities of information extraction and improving data interpretability for effective decision-making in public health.