Back to results

Generating actionable insights from the analysis of free-text comments from the National Care Experience Programme using Qualitative and Computational Text Analytics methods

Background: Over 70,000 free-text comments have been collected through the National Care Experience Programme (NCEP) surveys to date. Evidence from literature shows that free-text comments provide significantly deeper insights into patient experiences. However, obtaining rich and actionable insights from free text data is both resource and time-intensive and requires automated analysis underpinned by an effective analytical framework. This barrier has prevented the free-text data from the NCEP survey to be fully harnessed.
Aims of the work: We address the above challenge by using computational text analytics methods to analyse NCEP free-text data to investigate 1) what are the key care activities, resources, and contextual factors that are associated with both positive and negative experiences of patients and care service user across demographics; and 2) what should be the priority areas for improvement, policy development, regulation and monitoring based on reported experiences. We also explore 3) design options to effectively present results to stakeholders to enable actions towards improvements in specific care, hospital, and practice contexts.
Plan for investigation: To address the above questions, we propose a research design that employs 1) a comprehensive analytical framework grounded in both Service Management literature and the NCEP data as a coding framework; to underpin 2) the automated analyses of the data using text analytics and deep learning techniques; and 3) scenario-based designs to determine effective ways of presenting insights to knowledge users to address their key information and decisionmaking needs. Contribution to policy and practice: We envisage that results from the research will yield important, in-depth actionable insights into areas requiring improvement across acute hospital and maternity services, based on secondary analysis of detailed first-hand accounts from participants in the surveys. It will also provide knowledge users with information to determine the required interventions for addressing the identified issues.