ConVIScope: Visual Analytics for Exploring Patient Conversations



Raymond Li, Enamul Hoque, Giuseppe Carenini, Richard Lester, Raymond Chau

 External link (DOI) 

 View presentation:2021-10-28T17:50:00ZGMT-0600Change your timezone on the schedule page
2021-10-28T17:50:00Z

Exemplar figure, described by caption below — The ConVIScope interface combines: the Topic View for displaying the discussion topics along with their frequency in a hierarchy (B), and the Analysis View of conversations that encodes the distributions of sentiments and topics (C). Here, the user filters conversations by different dimensions in the Metadata View (A) followed by selecting a conversation which is shown in details in the Conversation View (D).

Keywords

Life Sciences, Health, Medicine, Biology, Bioinformatics, Genomics, Multi-Resolution and Level of Detail Techniques, Task Abstractions & Application Domains, Text/Document Data

Abstract

The proliferation of text messaging for mobile health is generating a large amount of doctor patient conversations that can be extremely valuable to health care professionals.We present ConVIScope, a visual text analytic system that tightly integrates interactive visualization with natural language processing in analyzing doctor-patient conversations. ConVIScope was developed in collaboration with health-care professionals following a user-centered iterative design. Case studies with six domain experts suggest the potential utility of ConVIScope and reveal lessons for further developments.