Topic Modeling for Analyzing Patients' Perceptions and Concerns of Hearing Loss on Social Q&A Sites: Incorporating Patients' Perspective

Abstract

Hearing loss is the most common human sensory deficit, affecting normal communication. Recently, patients with hearing loss or at risk of hearing loss are increasingly turning to the online health community for health information and support. Information on health-related topics exchanged on the Internet is a useful resource to examine patients' informational needs. The ability to understand the patients' perspectives on hearing loss is critical for health professionals to develop a patient-centered intervention. In this paper, we apply Latent Dirichlet Allocation (LDA) on electronic patient-authored questions on social question-and-answer (Q&A) sites to identify patients' perceptions, concerns, and needs on hearing loss. Our results reveal 21 topics, which are both representative and meaningful, and mostly correspond to sub-fields established in hearing science research. The latent topics are classified into five themes, which include "sudden hearing loss", "tinnitus", "noise-induced hearing loss", "hearing aids", "dizziness", "curiosity about hearing loss", "otitis media" and "complications of disease". Our topic analysis of patients' questions on the topic of hearing loss allows achieving a thorough understanding of patients' perspectives, thereby leading to better development of the patient-centered intervention.

Keywords: A; LDA; hearing loss; latent topic; social Q& topic modeling.

Figure 1

Overall research flow.

Figure 2

Plate model representation of Latent Dirichlet Allocation (LDA).