A Data-driven Approach for Mining Software Features based on Similar App Descriptions and User Reviews Analysis

Due to the rapid growth and strong competition of mobile application (app) market, app developers should not only offer users with attractive new features, but also carefully maintain and improve existing features based on users' feedbacks. User reviews indicate a rich source of information to plan such feature maintenance activities, and it could be of great benefit for developers to evaluate and magnify the contribution of specific features to the overall success of their apps. In this study, we refer to the features that are highly correlated to app ratings as key features, and we present KEFE, a novel approach that leverages app description and user reviews to identify key features of a given app. The application of KEFE especially relies on natural language processing, deep machine learning classifier, and regression analysis technique, which involves three main steps: 1) extracting feature-describing phrases from app description; 2) matching each app feature with its relevant user reviews; and 3) building a regression model to identify features that have significant relationships with app ratings. To train and evaluate KEFE, we collect 200 app descriptions and 1,108,148 user reviews from Chinese Apple App Store. Experimental results demonstrate the effectiveness of KEFE in feature extraction, where an average F-measure of 78.13% is achieved. The key features identified are also likely to provide hints for successful app releases, as for the releases that receive higher app ratings, 70% of features improvements are related to key features.

A feature-oriented analysis of developers’ descriptions and user reviews of top mHealth applications for diabetes and hypertension

BackgroundPersonal safety is a widespread public health issue that affects people of all demographics. There is a growing interest in the use of mobile apps for enhancing personal safety, particularly for children and youth at risk, who are among the most vulnerable groups in society.ObjectiveThis study aims to explore what is known about the use of mobile apps for personal safety among children and youth identified to be “at risk.”MethodsA scoping review following published methodological guidelines was conducted. In total, 5 databases (Scopus, SocINDEX, PsycINFO, Compendex, and Inspec Archive) were searched for relevant scholarly articles published between January 2005 and October 2023. The gray literature was searched using Google and Google Scholar search engines. The results were reported using the PRISMA-ScR (Preferred Reporting Items for Systematic Reviews and Meta-Analyses Extension for Scoping Reviews) guidelines. For summarizing the features and users’ experiences of the apps, a published framework for evaluating the quality of mobile health apps for youth was used.ResultsA total of 1986 articles were identified, and 41 (2.1%) were included in the review. Nine personal safety apps were captured and categorized into 4 groups based on the goals of the apps, as follows: dating and sexual violence prevention (n=4, 44% of apps), bullying and school violence prevention (n=2, 22% of apps), self-harm and suicide prevention (n=2, 22% of apps), and homeless youth support (n=1, 11% of apps). Of the 41 articles, 25 (61%) provided data solely on app descriptions and features, while the remaining 16 (39%) articles provided data on app evaluations and descriptions. Outcomes focused on app engagement, users’ experiences, and effectiveness. Four articles reported on app use, 3 (75%) of which reported relatively high app use. Data on users’ experience were obtained from 13 studies. In general, participants found the app features to be easy to use and useful as educational resources and personal safety tools. Most of the views were positive. Negative perceptions included redundancy of app features and a lack of usefulness. Five apps were evaluated for effectiveness (n=2, 40% dating and sexual violence prevention; n=2, 40% self-harm and suicide prevention; and n=1, 20% bullying and school violence prevention) and were all associated with a statistically significant reduction (P=.001 to .048) in harm or risk to participants at the 95% CI.ConclusionsAlthough many personal safety apps are available, few studies have specifically evaluated those designed for youth. However, the evidence suggests that mobile safety apps generally appear to be beneficial for reducing harm to at-risk children and youth without any associated adverse events. Recommendations for future research have been made to strengthen the evidence and increase the availability of effective personal safety apps for children and youth.

Mental health screening and diagnostic apps can provide an opportunity to reduce strain on mental health services, improve patient well-being, and increase access for underrepresented groups. Despite promise of their acceptability, many mental health apps on the market suffer from high dropout due to a multitude of issues. Understanding user opinions of currently available mental health apps beyond star ratings can provide knowledge which can inform the development of future mental health apps. This study aimed to conduct a review of current apps which offer screening and/or aid diagnosis of mental health conditions on the Apple app store (iOS), Google Play app store (Android), and using the m-health Index and Navigation Database (MIND). In addition, the study aimed to evaluate user experiences of the apps, identify common app features and determine which features are associated with app use discontinuation. The Apple app store, Google Play app store, and MIND were searched. User reviews and associated metadata were then extracted to perform a sentiment and thematic analysis. The final sample included 92 apps. 45.65% (n = 42) of these apps only screened for or diagnosed a single mental health condition and the most commonly assessed mental health condition was depression (38.04%, n = 35). 73.91% (n = 68) of the apps offered additional in-app features to the mental health assessment (e.g., mood tracking). The average user rating for the included apps was 3.70 (SD = 1.63) and just under two-thirds had a rating of four stars or above (65.09%, n = 442). Sentiment analysis revealed that 65.24%, n = 441 of the reviews had a positive sentiment. Ten themes were identified in the thematic analysis, with the most frequently occurring being performance (41.32%, n = 231) and functionality (39.18%, n = 219). In reviews which commented on app use discontinuation, functionality and accessibility in combination were the most frequent barriers to sustained app use (25.33%, n = 19). Despite the majority of user reviews demonstrating a positive sentiment, there are several areas of improvement to be addressed. User reviews can reveal ways to increase performance and functionality. App user reviews are a valuable resource for the development and future improvements of apps designed for mental health diagnosis and screening.

Today, plenty of apps are released to enable users to make the best use of their cell phones. Facing the large amount of apps, app retrieval and app recommendation become important, since users can easily use them to acquire their desired apps. To obtain high-quality retrieval and recommending results, it needs to obtain the precise app relationship calculating results. Unfortunately, the recent methods are conducted mostly relying on user's log or app's description, which can only detect whether two apps are downloaded, installed meanwhile or provide similar functions or not. In fact, apps contain many general relationships other than similarity, such as one app needs another app as its tool. These relationships cannot be dug via user's log or app's description. Reviews contain user's viewpoint and judgment to apps, thus they can be used to calculate relationship between apps. To use reviews, this paper proposes an iterative process by combining review similarity and app relationship together. Experimental results demonstrate that via this iterative process, relationship between apps can be calculated exactly. Furthermore, this process is improved in two aspects. One is to obtain excellent results even with weak initialization. The other is to apply matrix product to reduce running time.

RoseMatcher: Identifying the impact of user reviews on app updates

A number of on-demand platforms have arisen with the goal of making the delivery of products easier for all members of society, and Lalamove is one of them. Technological improvements have been a big driver in the growth of the logistics business. The study's overarching goal is to investigate users' impressions and thoughts about the Lalamove app via an exploratory lens. To have a better grasp of the topic at hand, this descriptive qualitative study used a content analysis strategy, which entails reducing the amount of data collected. This study's sample was chosen using a non-probability sampling approach, with a focus on user reviews of the Lalamove app located on the Google Play Store marketplace. Based on the TAM, which centres on the two primary components of perceived utility and perceived ease of use, this model attempts to explain why people adopt new technologies. Based on these findings, it seems that the app is still not as user-friendly as it might be. Despite the app's usefulness in enhancing delivery effectiveness, customers still face hurdles such as connecting couriers with users, registration issues, order cancellation, a tracking system that isn't up to par, and payment options that don't fulfil their expectations. Because of this, the Lalamove app's general usefulness and convenience are diminished due to persistent issues.

BackgroundPhysical inactivity remains a leading risk factor for mortality worldwide. Owing to increasing sedentary behavior (activities in a reclining, seated, or lying position with low-energy expenditures), vehicle-based transport, and insufficient physical workload, the prevalence of physical activity decreases significantly with age. To promote sufficient levels of participation in physical activities, the research prototype Fit-mit-ILSE was developed with the goal of making adults aged ≥55 years physically fit and fit for the use of assistive technologies. The system combines active and assisted living technologies and smart services in the ILSE app.ObjectiveThe clustering of health and fitness app user types, especially in the context of active and assisted living projects, has been mainly defined by experts through 1D cluster thresholds based on app usage frequency. We aimed to investigate and present data-driven methods for clustering app user types and to identify usage patterns based on the ILSE app function Fit at home.MethodsDuring the 2 phases of the field trials, ILSE app log data were collected from 165 participants. Using this data set, 2 data-driven approaches were applied for clustering to group app users who were similar to each other. First, the common approach of user-type clustering based on expert-defined thresholds was replaced by a data-driven derivation of the cluster thresholds using the Jenks natural breaks algorithm. Second, a multidimensional clustering approach using the Partitioning Around Medoids algorithm was explored to consider the detailed app usage pattern data.ResultsApplying the Jenks clustering algorithm to the mean usage per day and clustering the users into 4 groups showed that most of the users (63/165, 38.2%) used the Fit at home function between once a week and every second day. More men were in the low usage group than women. In addition, the younger users were more often identified as moderate or high users than the older users, who were mainly classified as low users; moreover, the regional differences between Vienna and Salzburg were identified. In addition, the multidimensional approach identified 4 different user groups that differed mainly in terms of time of use, gender, and region. Overall, the younger women living in Salzburg were the users with highest average app usage.ConclusionsThe application of different clustering approaches showed that data-driven calculations of user groups can complement expert-based definitions, provide objective thresholds for the analysis of app usage data, and identify groups that can be targeted individually based on their specific group characteristics.

BackgroundDespite the popularity of maternal and infant health mobile apps, ongoing consumer engagement and sustained app use remain barriers. Few studies have examined user experiences or perceived benefits of maternal and infant health app use from consumer perspectives.ObjectiveThis study aims to assess users’ self-reported experiences with maternal and infant health apps, perceived benefits, and general feedback by analyzing publicly available user reviews on two popular app stores—Apple App Store and Google Play Store.MethodsWe conducted a qualitative assessment of publicly available user reviews (N=2422) sampled from 75 maternal and infant health apps designed to provide health education or decision-making support to pregnant women or parents and caregivers of infants. The reviews were coded and analyzed using a general inductive qualitative content analysis approach.ResultsThe three major themes included the following: app functionality, where users discussed app features and functions; technical aspects, where users talked about technology-based aspects of an app; and app content, where users specifically focused on the app content and the information it provides. The six minor themes included the following: patterns of use, where users highlighted the frequency and type of use; social support, where users talked about receiving social support from friends, family and community of other users; app cost, where users talked about the cost of an app within the context of being cost-effective or a potential waste of money; app comparisons, where users compared one app with others available in app stores; assistance in health care, where users specifically highlighted the role of an app in offering clinical assistance; and customer care support, where users specifically talked about their interaction with the app customer care support team.ConclusionsUsers generally tend to value apps that are of low cost and preferably free, with high-quality content, superior features, enhanced technical aspects, and user-friendly interfaces. Users also find app developer responsiveness to be integral, as it offers them an opportunity to engage in the app development and delivery process. These findings may be beneficial for app developers in designing better apps, as no best practice guidelines currently exist for the app environment.

With the vast number of apps and the complexity of their features, it is becoming challenging for teachers to select a suitable learning app for their courses. Several evaluation frameworks have been proposed in the literature to assist teachers with this selection. The iPAC framework is a well-established mobile learning framework highlighting the learners' experience of personalization, authenticity, and collaboration (iPAC). In this article, we introduce an approach to automate the identification and comparison of iPAC relevant apps. We experiment with natural language processing and machine learning techniques, using data from the app description and app reviews publicly available in app stores. We further empirically validate the keyword base of the iPAC framework based on the app users' language in app reviews. Our approach automatically identifies iPAC relevant apps with promising results (F1 score ~ 72%) and evaluates them similarly as domain experts (Spearman's rank correlation 0.54). We discuss how our findings can be useful for teachers, students, and app vendors.

Medical consultation applications (apps) have rapidly proliferated globally. One type of app is the psychological consultation app, which has made visiting doctors more convenient, particularly for individuals who feel embarrassed about consulting a psychiatrist. However, only a few researchers have examined the usability or user experience of such apps. This study aims to evaluate the user experience of psychological consultation apps in Saudi Arabia, specifically focusing on the usability aspects and user satisfaction of the apps "Labayh," "Estenarah," and "Mind." The research employs two methodologies: First, an expert evaluation using the SMART heuristic framework, developed to assess the usability of mobile apps by identifying usability issues based on established principles. Results from this method revealed that all three apps faced challenges, particularly in SMART 5 (Each interface should focus on one task) and SMART 10 (Cater for diverse mobile environments). Second, a sentiment analysis of user reviews from app stores was conducted, categorizing feedback into positive and negative reviews. User reviews were collected using Heedzy, an online tool designed for extracting reviews from mobile apps. Data cleaning was performed using Python libraries, which handled missing data and removed duplicate entries. Out of 459 reviews analyzed, 51% were negative, focusing primarily on general dissatisfaction and functionality issues, while 49% were positive, highlighting user appreciation and the innovative concept of online consultations. Specific findings indicated that the "Mind" app had significant usability concerns, receiving a severity rating of 70, with notable issues in error prevention and interface clarity. Recommendations for improvement include enhancing task-focused design, increasing adaptability for diverse mobile environments, and addressing user feedback to refine app functionalities. This research contributes valuable insights for designers aiming to improve the usability of psychological consultation apps in the region.

Medical consultation applications (apps) have rapidly proliferated globally. One type of app is the psychological consultation app, which has made visiting doctors more convenient, particularly for individuals who feel embarrassed about consulting a psychiatrist. However, only a few researchers have examined the usability or user experience of such apps. This study aims to evaluate the user experience of psychological consultation apps in Saudi Arabia, specifically focusing on the usability aspects and user satisfaction of the apps “Labayh,” “Estenarah,” and “Mind.” The research employs two methodologies: First, an expert evaluation using the SMART heuristic framework, developed to assess the usability of mobile apps by identifying usability issues based on established principles. Results from this method revealed that all three apps faced challenges, particularly in SMART 5 (Each interface should focus on one task) and SMART 10 (Cater for diverse mobile environments). Second, a sentiment analysis of user reviews from app stores was conducted, categorizing feedback into positive and negative reviews. User reviews were collected using Heedzy, an online tool designed for extracting reviews from mobile apps. Data cleaning was performed using Python libraries, which handled missing data and removed duplicate entries. Out of 459 reviews analyzed, 51% were negative, focusing primarily on general dissatisfaction and functionality issues, while 49% were positive, highlighting user appreciation and the innovative concept of online consultations. Specific findings indicated that the “Mind” app had significant usability concerns, receiving a severity rating of 70, with notable issues in error prevention and interface clarity. Recommendations for improvement include enhancing task-focused design, increasing adaptability for diverse mobile environments, and addressing user feedback to refine app functionalities. This research contributes valuable insights for designers aiming to improve the usability of psychological consultation apps in the region.

A systematic literature review: Opinion mining studies from mobile app store user reviews

Although mobile apps are already an influential medium in the new media industry as a whole, these apps have received little academic attention within the communication and marketing literature. This study develops and tests a hypothesized model to explain antecedents affecting app usage among smartphone users. The analysis of the structural equation model determined a final model with four significant factors (perceived informative and entertaining usefulness, perceived ease of use, and user review). Cost-effectiveness, a key variable of this study due to the particularity of 99-cent app price, had no influence on app usage. This study not only includes marketing implications but also offers insight into various theoretical applications to the field of mobile communication research by suggesting a conceptual model for the acceptance of mobile apps.

Mental illness substantially contributes to the global burden of disease, with anxiety high in prevalence. The increase of mobile technology, mental health apps have potential to lessen this burden. However, within apps, the use of evidence-based interventions, such as cognitive behavioural therapy (CBT) are limited. Regardless, many commercially available mental health apps are highly rated by users, highlighting the need to understand what makes mental health apps valuable to the user. The contribution of this study was to uncover apps that support generalised anxiety disorder (GAD) and worry with a CBT basis, explore app functionality, and user experience. Firstly, by identifying apps that support GAD and worry and included CBT. Secondly, by identifying and analysing therapeutic and engagement functions within the apps, and finally, by thematically analysing user reviews. Six apps were identified to support GAD and worry that purported to be CBT-based. However, CBT therapeutic features and engagement features were minimally present in the apps. User reviews yielded 112 comments about the apps and key themes were identified about the app users’ global experiences with the app, and about the combination of technological (e.g., useability, reliability) and therapeutic experiences (e.g., learning and using skills). Future development of quality apps to support GAD and worry must consider the empirical standing of both therapeutic and technology aspects, to provide efficacious and engaging interventions.