Unsupervised Machine Learning to Identify Positive and Negative Themes in Jordanian mHealth Apps

Unsupervised Machine Learning to Identify Positive and Negative Themes in Jordanian mHealth Apps

Mohammad Salem Alhur, Shaher Alshamari, Judit Oláh, Hanadi Aldreabi
Copyright: © 2022 |Pages: 21
DOI: 10.4018/IJESMA.313950
Article PDF Download
Open access articles are freely available for download

Abstract

User opinions are crucial in the development of mobile health (mHealth) applications (apps). This study aimed to investigate and qualitatively assess consumer attitudes toward mHealth apps and the main aspects of their design. The methodology was divided into four steps: (1) data collection, (2) preprocessing, (3) sentiment analysis by valence-aware dictionary and sentiment reasoner (VADER), and (4) thematic analysis by the latent Dirichlet allocation (LDA) algorithm. These steps were implemented in 836 reviews of eight mHealth apps on app stores in Jordan. The current study offers healthcare stakeholders insight into the positive and negative aspects of mHealth apps by identifying user-preferred features and recommending improvements. The findings indicate several aspects of design that mHealth app developers may use to improve overall efficacy, including user experience, client services, usability, and adherence.
Article Preview
Top

Introduction

There are more than three billion smartphone users. Mobile devices, therefore, interconnect roughly two-thirds of the world’s population (Davis et al., 2020), leading to advancements in mobile software and technology (Hentzen et al., 2022).

Mobile applications (apps) have become an integral part of users’ daily lives. There is an opportunity for mobile app developers to provide mobile health (mHealth) apps that enable the public to secure desired medical information (Ming et al., 2020).

mHealth refers to the provision of general medical and health support to healthcare customers through mobile phones, laptops, and personal digital assistants (Kernebeck et al., 2020). This mobile technology has the potential to enhance the healthcare system by increasing efficiency, communication, cost, and quality of services (Stewart, 2021). An mHealth app may help providers cure clinical diseases and educate patients on self-monitoring practices. It may minimize unnecessary hospital visits or focus visits to high-risk areas and populations (Akbar et al., 2020; Alghamdi & Alfalqi, 2015).

From the first quarter of 2015 through the first quarter of 2021, 107,033 mHealth apps in the health and fitness category were available via the Apple Store and Google Play, an increase of 11.37% from the previous quarter (Statista, 2021; Stewart, 2021). In 2019, the global market for mHealth apps was estimated at US$17.92 billion, with a compound annual growth rate of 45% predicted from 2020 to 2027 (Wang & Qi, 2021). These numbers indicate the importance of the mHealth sector. Moreover, there is a growing demand in the developing world and Middle East for smartphone technologies to search and share health information, access health resources, and promote wellness (Qan’ir et al., 2021).

Research on user experience is essential to the success of mHealth apps as developers better understand barriers to digital adherence and engage with user motivation. For example, researchers can perform online reviews to identify themes (Liew et al., 2019). Furthermore, understanding patient experience, a pillar in the foundation of quality, is critical to the delivery of care. Surveys and structured patient-reported outcome measures serve as traditional processes to study patient experience. However, these methods ask specific and limited questions, are performed infrequently, and are often expensive to administer. Patients are now going online to discuss their healthcare experiences through blogs, social networks, wikis, and healthcare-rating Websites. Unfortunately, this information is not recorded systematically because it is often unstructured, non-standardized, and free text. This is, therefore, a lost opportunity to capture patient experiences in an unconnected society (Greaves et al., 2013).

Content analysis of user reviews and comments has been adopted by researchers as they assess the benefits and challenges of mHealth apps (Oyebode et al., 2020). According to Thach (2019), thematic analysis permits the researcher to devise a quantitative abstract of the primary opinion topics and obtain insights into users’ attitudes through qualitative analysis. This approach has been popularized in the mHealth literature (Islam, 2019; Nicholas et al., 2017; Oyebode et al., 2020; Zou & Hou, 2014).

Complete Article List

Search this Journal:
Reset
Volume 16: 1 Issue (2024)
Volume 15: 1 Issue (2023)
Volume 14: 4 Issues (2022): 1 Released, 3 Forthcoming
Volume 13: 4 Issues (2021)
Volume 12: 4 Issues (2020)
Volume 11: 4 Issues (2019)
Volume 10: 4 Issues (2018)
Volume 9: 4 Issues (2017)
Volume 8: 4 Issues (2016)
Volume 7: 4 Issues (2015)
Volume 6: 4 Issues (2014)
Volume 5: 4 Issues (2013)
Volume 4: 4 Issues (2012)
Volume 3: 4 Issues (2011)
Volume 2: 4 Issues (2010)
Volume 1: 4 Issues (2009)
View Complete Journal Contents Listing