Review Of Apps Research Articles

Mobile health applications for individuals with psoriatic arthritis

Abstract Objectives Mobile health applications (Apps) hold promise as tools for symptom tracking and management of chronic rheumatic diseases, such as psoriatic arthritis (PsA). Apps for PsA have not been systematically evaluated. We conducted a comprehensive review of Apps designed for patients with PsA. Methods The iOS and Android App stores were searched for the term “arthritis”, and individual App descriptions were reviewed for “psoriatic arthritis”. Apps were downloaded and rated using the MARS standardized quality rating tool. Additionally, the Apps were evaluated to determine functionality, use of symptom scales, and potential for integration within clinical care. Results The search was conducted in Spring 2024 and 130 Apps were found that mentioned “arthritis”. Seven had specific mentions of psoriatic arthritis in their description. We found several other relevant Apps by following recommendations on the App stores. In total, 10 Apps for patients with PsA were identified. MARS scores suggest they were moderate to excellent in quality. The functionality of the 10 Apps differed: 7 allowed for symptom tracking; 3 allowed for data export to health records; 2 allowed for medication tracking; and 1 contained a patient community platform. The symptom tracking capabilities varied widely, and we could find only one published study of any of the Apps. Conclusions We analyzed Apps for PsA to identify potential unmet needs and found that there are few Apps publicly available, their functionality varies tremendously, and testing of these Apps is almost non-existent. There appears to be room for improvement of Apps for PsA.

Usability Testing of the PACE-App to Support Family Caregivers in Managing Pain for People with Dementia.

Pain management is often suboptimal in individuals with dementia, and their family caregivers are tasked with supporting pain management despite limited preparation. The web-based PACE-app (PAin Control Enhancement) was designed to assist caregivers in managing pain for individuals with dementia. This study aimed to evaluate the usability of the PACE-app. A convergent parallel mixed-methods design was used to evaluate the PACE-app's usability with 16 family caregivers and 6 healthcare professionals. Quantitative data were collected using the Post-Study System Usability Questionnaire (PSSUQ), while qualitative data were gathered through guided app reviews and semi-structured interviews. Quantitative data were analyzed descriptively, and qualitative data were thematically coded. The PSSUQ results indicated that both family caregivers and healthcare professionals had a highly positive experience with the PACE-app: overall scores (2.01 vs. 1.68), system usefulness (1.76 vs. 1.68), information quality (1.98 vs. 1.80), interface quality (2.30 vs. 1.60), and satisfaction (2.00 vs. 1.60) were rated on a 1-7 scale (with lower scores indicating better usability). Qualitative findings supported these results, with participants endorsing the PACE-app's usefulness, ease of use, learnability, effective information presentation, aesthetics, clear layout, and overall satisfaction. Participants also provided valuable feedback for improving information quality (enhancing clarity) and interface quality (real-time coaching on pain management). The study demonstrated favorable usability and strong satisfaction among family caregivers and healthcare professionals using the PACE-app. Incorporating participants' suggestions will guide enhancements to the app's information and interface, ensuring it better meets users' needs.

Filtering Useful App Reviews Using Naïve Bayes—Which Naïve Bayes?

App reviews provide crucial feedback for software maintenance and evolution, but manually extracting useful reviews from vast volumes is time-consuming and challenging. This study investigates the effectiveness of six Naïve Bayes variants for automatically filtering useful app reviews. We evaluated these variants on datasets from five popular apps, comparing their performance in terms of accuracy, precision, recall, F-measure, and processing time. Our results show that Expectation Maximization-Multinomial Naïve Bayes with Laplace smoothing performed best overall, achieving up to 89.2% accuracy and 0.89 F-measure. Complement Naïve Bayes with Laplace smoothing demonstrated particular effectiveness for imbalanced datasets. Generally, incorporating Laplace smoothing and Expectation Maximization improved performance, albeit with increased processing time. This study also examined the impact of data imbalance on classification performance. Our findings suggest that these advanced Naïve Bayes variants hold promise for filtering useful app reviews, especially when dealing with limited labeled data or imbalanced datasets. This research contributes to the body of evidence around app review mining and provides insights for enhancing software maintenance and evolution processes.

Mobile app review analysis for crowdsourcing of software requirements: a mapping study of automated and semi-automated tools

Mobile app reviews are valuable for gaining user feedback on features, usability, and areas for improvement. Analyzing these reviews manually is difficult due to volume and structure, leading to the need for automated techniques. This mapping study categorizes existing approaches for automated and semi-automated tools by analyzing 180 primary studies. Techniques include topic modeling, collocation finding, association rule-based, aspect-based sentiment analysis, frequency-based, word vector-based, and hybrid approaches. The study compares various tools for analyzing mobile app reviews based on performance, scalability, and user-friendliness. Tools like KEFE, MERIT, DIVER, SAFER, SIRA, T-FEX, RE-BERT, and AOBTM outperformed baseline tools like IDEA and SAFE in identifying emerging issues and extracting relevant information. The study also discusses limitations such as manual intervention, linguistic complexities, scalability issues, and interpretability challenges in incorporating user feedback. Overall, this mapping study outlines the current state of feature extraction from app reviews, suggesting future research and innovation opportunities for extracting software requirements from mobile app reviews, thereby improving mobile app development.

Smartphone Apps for Pulmonary Hypertension: Systematic Search and Content Evaluation.

Pulmonary hypertension (PH) is a chronic and complex condition, requiring consistent management and education. The widespread use of smartphones has opened possibilities for mobile health apps to support both patients and health care professionals in monitoring and managing PH more effectively. This study aimed to identify and assess the quality of free smartphone apps for PH targeted at either patients or health care professionals. A systematic search was conducted on freely available apps for patients with PH and health care professionals, accessed from a Spanish IP address, on Android (Google Play) and iOS (App Store) platforms. Searches were performed in October 2022 and 2023. Apps were independently analyzed by two reviewers, focusing on general characteristics. Quality assessment was based on the Mobile Application Rating Scale (MARS) framework, and Mann-Whitney U tests compared mean MARS scores against specific variables. In the overall study, 21 apps were identified. In the 2022 search, 19 apps were listed (9 iOS, 7 Android, 3 available on both platforms). In the subsequent 2023 search, 16 apps were identified (6 Android, 7 iOS, 3 available on both platforms). Of those identified in 2022, 14 remained available in 2023, with only 7 updated since 2022. In addition, 12 apps targeted patients or the general population, while 9 targeted health care professionals; none involved patients in the development or design. Conversely, 13 apps involving health care professionals were identified. There were 10 apps that received pharmaceutical industry funding. The primary goal for 81% (17/21) of the apps was to disseminate general information about PH. The overall mean MARS quality was acceptable in 2022 and 2023, with mean ratings of 3.1 (SD 0.6) and 3.3 (SD 0.5), respectively. The functionality category achieved the highest scores in both years, indicating ease of use and intuitive navigation. In contrast, the subjective quality domain consistently received the lowest ratings in the MARS assessment across both years. None of the apps underwent clinical testing themselves; however, 2 incorporated tools or algorithms derived from trials. The overall quality of iOS apps statistically outperformed that of Android apps in both years (P<.05). Furthermore, the involvement of health care professionals in app development was associated with enhanced quality, a trend observed in both years (P=.003 for both years). This review of mobile health apps for PH reveals their emergent development stage, with generally acceptable quality but lacking refinement. It highlights the critical role of health care professionals in app development, as they contribute significantly to quality and reliability. Despite this, a notable stagnation in app quality and functionality improvement over 2 years points to a need for continuous innovation and clinical validation for effective clinical integration. This research advocates for future app developers to actively engage with health care professionals, integrate patient insights, and mandate rigorous clinical validation for PH management.

Unveiling User Sentiment: Aspect-Based Analysis and Topic Modeling of Ride-Hailing and Google Play App Reviews

Background: Mobile app usage is increasing in the digital age, with Ride-Hailing app becoming the primary example of this trend. To obtain valuable understanding of how people perceive and interact with mobile app, user reviews on platforms such as Google Play are usually analyzed. This analysis can assist developers to identify areas for improvement in both Ride-hailing and Google Play App. A promising method that can be used to analyze user perception in this instance is Aspect-Based Sentiment Analysis (ABSA). Objective: This research aimed to apply ABSA to user reviews using Bidirectional Encoder Representations from Transformers (BERT) models. In this context, aspect identification and topic modeling were performed by using Latent Dirichlet Allocation (LDA). The model extracted topics from the reviews and used Generative Artificial Intelligence (GenAI) to define the aspects of the topics to further enhance the analysis. For consistency and accuracy, the method included sentiment annotation by a human annotator. Methods: A total of two datasets were used in this research, with the first collected by scraping user reviews of Ride-Hailing App while the second was obtained from Kaggle, and to identify relevant topics, modeling was performed using LDA. These topics were then categorized into aspects using GenAI, covering areas, such as customer experience, service, payment, app features, task management, and event management. Subsequently, sentiment labeling was conducted using human annotators to provide a reliable baseline. BERT model was then used to classify sentiment with aspect hints, and the evaluation included calculations of accuracy, precision, recall, and F1-score. Results: The results showed that BERT model achieved the highest accuracy of 97% in sentiment analysis across all datasets. Conclusion: This research provided valuable understanding of user experience and established a strong ABSA framework for analyzing user reviews using LDA, Aspect Annotation, GenAI, and BERT sentiment models. Future research could expand this method to other app categories and incorporate real-time ABSA for continuous monitoring and dynamic feedback. Keywords: User Reviews, Aspect-Based Sentiment Analysis (ABSA), Sentiment Analysis, Topic Modeling, Generative Artificial Intelligence (GenAI)

Mining User Reviews for Key Design Features in Cognitive Behavioral Therapy-Based Mobile Mental Health Apps.

Background: Cognitive behavioral therapy (CBT)-based mobile apps have been shown to improve CBT-based interventions effectiveness. Despite the proliferation of these apps, user-centered guidelines pertaining to their design remain limited. The study aims to identify design features of CBT-based apps using online app reviews. Methods: We used 4- and 5-star reviews, preprocessed the reviews, and represented the reviews using word-level bigrams. Then, we leveraged latent Dirichlet allocation (LDA) and visualization techniques using python library for interactive topic model visualization to analyze the review and identify design features that contribute to the success and effectiveness of the app. Results: A total of 24,902 reviews were analyzed. LDA optimization resulted in 86 topics that were labeled by two independent researchers, with an interrater Cohen's kappa value of 0.86. The labeling and grouping process resulted in a total of six main design features for effective CBT-based mobile apps, namely, mental health management and support, credibility support, self-understanding and personality insights, therapeutic approaches and tools, beneficial rescue sessions, and personal growth and development. Conclusions: The high-level design features identified in this study could evidently serve as the backbone of successful CBT-based mobile apps for mental health.

Digital Storytelling for People With Cognitive Impairment Using Available Mobile Apps: Systematic Search in App Stores and Content Analysis.

Growing evidence suggests cognitive and social health benefits can be derived from digital storytelling for older adults with cognitive impairment. Digital storytelling apps offer the potential to serve as an on-demand, easy-to-access platform for enhancing cognitive abilities and promoting social well-being. Yet, despite the increasing quantity of such apps being available on the market, there is a gap in research investigating their quality. This app review aims to assess the digital storytelling apps available in the Chinese market and evaluate them in accordance with the Mobile Application Rating Scale (MARS). The goal was to identify key features and evaluate the overall quality in the context of cognitively impaired users. A systematic search was conducted in both the Google Play store (Google LLC) and iTunes store (Apple Inc), using English and Chinese keywords. Apps were chosen according to specific criteria that included features, including (but not limited to) memory capture, story saving, cue-based reminiscing, and the ability to share stories or memories with others. The MARS was used by 3 individual researchers to independently assess app quality across several domains, such as engagement, functionality, aesthetics, and information quality, for both Android and iOS apps. From an initial screening of 297 apps, only 9 (3%) met the criteria for detailed evaluation using MARS. The reviewed apps featured capture memory, save, reminisce, and share functions, which are critical in supporting cognitive functions and enhancing user engagement. The analysis revealed patterns in platform diversity and geographical distribution of developers, with apps available on both iOS and Android. Memoirs of Life and Memorize: Diaries, Memories, Notes, Ideas, Timelines, Categories (Fair Apps Mobile) had the highest mean MARS scores of 3.35, indicating strong engagement, functionality, and information quality, while the lowest score was 2.33. The overall mean score across all apps was only 3.03 (SD 0.60), highlighting significant variation, particularly in information quality. User feedback also showed considerable variability, ranging from 0 comments for apps such as Grand Storyteller (VarIT Inc) and PWI Storyteller (Project World Impact, LLC) to as many as 5361 comments for FamilySearch, which received extensive positive reviews. This wide range of user feedback underscores the importance of continuous improvement and user-centered design, particularly in enhancing information quality and content accuracy. The systematic search and evaluation highlight the diverse capabilities yet variable quality of digital storytelling apps available within the Chinese market, reflecting user experiences, satisfaction levels, and efficacy in supporting cognitively impaired users. While some apps excel in engagement and functionality, others need significant improvements in information quality and user interface design to better serve those with cognitive impairments. Future research is recommended to investigate regional limitations and features that would result in more inclusive and effective digital storytelling apps.

Better together: Automated app review analysis with deep multi-task learning

Context:User reviews of mobile apps provide an important communication channel between developers and users. Existing approaches to automated app review analysis mainly focus on one task (e.g., bug classification task, information extraction task, etc.) at a time, and are often constrained by the manually defined patterns and the ignorance of the correlations among the tasks. Recently, multi-task learning (MTL) has been successfully applied in many scenarios, with the potential to address the limitations associated with app review mining tasks. Objective:In this paper, we propose MABLE, a deep MTL-based and semantic-aware approach, to improve app review analysis by exploiting task correlations. Methods:MABLE jointly identifies the types of involved bugs reported in the review and extracts the fine-grained features where bugs might occur. It consists of three main phases: (1) data preparation phase, which prepares data to allow data sharing beyond single task learning; (2) model construction phase, which employs a BERT model as the shared representation layer to capture the semantic meanings of reviews, and task-specific layers to model two tasks in parallel; (3) model training phase, which enables eavesdropping by shared loss function between the two related tasks. Results:Evaluation results on six apps show that MABLE outperforms ten commonly-used and state-of-the-art baselines, with the precision of 79.76% and the recall of 79.24% for classifying bugs, and the precision of 79.83% and the recall of 80.33% for extracting problematic app features. The MTL mechanism improves the F-measure of two tasks by 3.80% and 4.63%, respectively. Conclusion:The proposed approach provides a novel and effective way to jointly learn two related review analysis tasks, and sheds light on exploring other review mining tasks.

Unveiling User Perspectives: Exploring Themes in Femtech Mobile App Reviews for Enhanced Usability and Privacy

Femtech, a growing sector in mobile healthcare technology, caters to women's needs across various life stages with digital solutions like period tracking and pregnancy management apps. Maintaining robust data privacy is crucial due to the sensitive nature of the information involved, such as menstrual cycles and pregnancy status. Our research analyzes user feedback from platforms like the Apple App Store and Google Play Store to understand perceptions of femtech apps, covering accessibility, interface, features, and privacy concerns. Understanding user perspectives helps developers enhance usability and trust, driving further adoption. Prioritizing privacy also fosters industry advancement. This paper stresses the importance of dialogue among developers, users, and policymakers in femtech. Our findings aim to facilitate positive change within the femtech sector, leading to more inclusive, user-centric, and ethically driven advancements, benefiting both the industry and its users.

The Influence of Mobile App Store Ratings and Reviews on Download Intentions: A Study of Sri Lankan Consumers

Purpose: This study aims to understand the impact of user reviews and ratings on mobile app download intention and the moderating impact of perceived usefulness on the strength of this relationship. Design/methodology/approach: A scenario-based survey method was selected following the positivism research paradigm. For this purpose, 304 responses were collected using different versions of the same scenario. Findings: The statistical results show that 37.5% of Sri Lankan consumers' mobile app download intention is explained by mobile app ratings and reviews, which have been found to be a significant influencing factor in potential users' intentions to download the app. However, perceived usefulness does not significantly moderate this relationship. Originality: This study is the first attempt to understand the impact of user reviews and ratings on mobile app download intention in the Sri Lankan context. Implications: The findings encourage Sri Lankan mobile app developers and owners to closely monitor and respond to user reviews and ratings to better meet user expectations and improve app ratings.

Mapping the Online Reviews Sentiment Landscape: An Exploration of Emotion Spectrum in User Reviews of Mobile Apps

Mobile applications have emerged as powerful platforms for consumers and understanding the attitudes and reactions of users by content and emotional sides in a mobile context becomes crucial for marketing decision-making. The study with comprehensive approach aims to analyze the emotion spectrum in mobile applications user reviews context by examining specific emotions (anger, disgust, fear, joy, neutral, sadness, surprise). Sentiment analysis methodology (through "Emotion English DistilRoBERTa-base" transformers-model) is employed on the dataset of 302.647 reviews from 34 mobile application categories. Categorical examination of emotions indicates that neutrality is the dominant emotion category, followed by joy, sadness, disgust, surprise, and anger emotion categories, while the fear category is the least dominant category. According to polarity examination; negative polarity reviews are associated with neutral, sadness and disgust emotions; neutral polarity reviews are associated with neutral and sadness; positive polarity reviews are associated with neutral and joy emotion categories. Final part of analysis includes examination of emotions individually and mobile app categories which each emotion with the highest frequency of dominance are presented. The distribution rates of emotions and the individual relationships of emotions with different application categories can shed light on future academic research and marketing decision-making.

Impact of Feature Extraction on Multi-Aspect Sentiment Classification for Livin'byMandiri Using BiLSTM

Mobile applications are currently experiencing very rapid development including applications in the financial sector. Livin'byMandiri is one of the mobile applications used to transact online without the need to go to the bank. This makes it very easy for customers to transact anywhere and anytime. Application reviews are user reviews that reflect the reputation of the application among the community, these application reviews can be found anywhere, so many companies use application reviews as a reference in developing their applications in the future. However, people's opinions on apps can vary and are influenced by many aspects. Therefore, aspect-based sentiment analysis can be applied to app reviews to get better results. This research focuses on analyzing the sentiment of Livin'byMandiri app reviews on the Google Play Store. In this research, the Bidirectional LSTM (Bi-LSTM) method is combined with TF-IDF and Word2Vec feature extraction. From the results of the experiments that have been carried out, the best accuracy results for the access aspect are 81.18% and F1-Score of 81.03%, the service aspect produces an accuracy of 82.82% and F1-Score of 82.74%, and for the convenience aspect produces an accuracy of 77.28% and F1-Score of 77.19%. In this experiment, it is also found that feature extraction has an effect on sentiment analysis, this is evidenced by an increase in accuracy of more than 1% for each aspect when TF-IDF feature extraction is added and also the combination of TF-IDF and Word2vec in the initial model built using only the Neural Network embedding layer.

Fairness Concerns in App Reviews: A Study on AI-based Mobile Apps

Fairness Concerns in App Reviews: A Study on AI-based Mobile Apps

The best ends by the best means: ethical concerns in app reviews

This work analyzes ethical concerns found in users’ app store reviews. We performed this study because ethical concerns in mobile applications (apps) are widespread, pose severe threats to end users and society, and lack systematic analysis and methods for detection and classification. In addition, app store reviews allow practitioners to collect users’ perspectives, crucial for identifying software flaws, from a geographically distributed and large-scale audience. For our analysis, we collected five million user reviews, developed a set of ethical concerns representative of user preferences, and manually labeled a sample of these reviews. We found that (1) users highly report ethical concerns about censorship, identity theft, and safety (2) user reviews with ethical concerns are longer, more popular, and lowly rated, and (3) there is high automation potential for the classification and filtering of these reviews. Our results highlight the relevance of using app store reviews for the systematic consideration of ethical concerns during software evolution.

Ranking English Apps From the Google Play Store Based on Customer Reviews Analysis

Nowadays, several educational technology and English learning apps on the Google Play Store cater to various learning levels and objectives. However, the parents had difficulty finding an appropriate app for their kids. It is challenging when there is a diversity of English learning apps in the market. Not only product brands but also prices affect the customer‘s choice behavior. A good product will achieve customer satisfaction. And the praise of experienced customers will be a suggestion for potential customers. This paper uses sentiment analysis as a factor of criteria set for evaluating English learning Apps from Vietnamese companies. The Python language was used in all the analysis processes, and the sentiment score of 8,756 reviews for English learning apps was calculated. The criteria to evaluate the App include overall rating, sentiment scores, and number of downloads. The results will be a suggestion for improving the quality of companies‘ products and a recommendation for users when choosing a suitable Edtech product.

Effectiveness of Mobile App Interventions to Improve Periodontal Health: Protocol for a Systematic Review and Meta-Analysis.

Periodontal health plays a key role as a shared reference point for evaluating periodontal diseases and identifying significant treatment outcomes. Providing adequate instruction and enhancing the motivation of patients to maintain proper oral hygiene are crucial factors for successful periodontal treatment, with self-performed regular oral hygiene identified as a critical factor in improving the outcomes of treatment for periodontal diseases. Recently, mobile health (mHealth) solutions, especially mobile apps, have emerged as valuable tools for self-management in chronic diseases such as periodontal disease, providing essential health education and monitoring capabilities. However, the use of mHealth apps for periodontal health is complex owing to various interacting components such as patient behavior, socioeconomic status, and adherence to oral hygiene practices. Existing literature has indicated positive effects of mHealth on oral health behaviors, knowledge, attitude, practice, plaque index score, and gingivitis reduction. However, there has been no systematic review of mobile apps specifically targeting patients with periodontal disease. Understanding the design and impact of mHealth apps is crucial for creating high-quality apps. The aim of this systematic review and meta-analysis is to evaluate the effectiveness of existing mobile apps in promoting periodontal health. A comprehensive search strategy will be performed in multiple electronic databases (PubMed, EBSCOhost, CINAHL Plus, Dentistry & Oral Sciences, ScienceDirect, Scopus, and Cochrane Central Register of Controlled Trials) with the following keywords in the title/abstract: "mobile application," "mobile health," "mHealth," "telemedicine," "periodontal health," "periodontitis," and "text message." Only randomized controlled trials will be included that assessed the following outcomes to measure periodontal health improvement: gingival index, bleeding index, periodontal pocket depth, and clinical attachment loss. Covidence will be used for data collection, and a PRISMA (Preferred Reporting Items for Systematic reviews and Meta-Analyses) flowchart will be used to describe the selection process of the included, identified, and excluded studies. The Confidence in Network Meta-Analysis approach will be used for meta-analysis of the extracted data from the included studies. This review will not require ethical approval since no primary data will be included. As of July 2024, a total of 83 articles retrieved from various databases have been imported to Covidence with 13 articles deemed eligible for inclusion in the review. The review is currently ongoing and is expected to be complete by the end of 2024 with the results published in early 2025. This systematic review and meta-analysis will contribute to developing mobile apps with enhanced criteria to improve periodontal clinical outcomes. The review emphasizes the importance of mHealth and preventing periodontal disease, which can set the stage for informed global health care strategies. PROSPERO CRD42022340827; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=340827. DERR1-10.2196/50479.

Customers’ emotional impact on star rating and thumbs-up behavior towards food delivery service Apps

This study explores the intricate relationship between emotional cues present in food delivery app reviews, normative ratings, and reader engagement. Utilizing lexicon-based unsupervised machine learning, our aim is to identify eight distinct emotional states within user reviews sourced from the Google Play Store. Our primary goal is to understand how reviewer star ratings impact reader engagement, particularly through thumbs-up reactions. By analyzing the influence of emotional expressions in user-generated content on review scores and subsequent reader engagement, we seek to provide insights into their complex interplay. Our methodology employs advanced machine learning techniques to uncover subtle emotional nuances within user-generated content, offering novel insights into their relationship. The findings reveal an inverse correlation between review length and positive sentiment, emphasizing the importance of concise feedback. Additionally, the study highlights the differential impact of emotional tones on review scores and reader engagement metrics. Surprisingly, user-assigned ratings negatively affect reader engagement, suggesting potential disparities between perceived quality and reader preferences. In summary, this study pioneers the use of advanced machine learning techniques to unravel the complex relationship between emotional cues in customer evaluations, normative ratings, and subsequent reader engagement within the food delivery app context.

The Acceptability, Engagement, and Feasibility of Mental Health Apps for Marginalized and Underserved Young People: Systematic Review and Qualitative Study.

Smartphone apps may provide an opportunity to deliver mental health resources and interventions in a scalable and cost-effective manner. However, young people from marginalized and underserved groups face numerous and unique challenges to accessing, engaging with, and benefiting from these apps. This study aims to better understand the acceptability (ie, perceived usefulness and satisfaction with an app) and feasibility (ie, the extent to which an app was successfully used) of mental health apps for underserved young people. A secondary aim was to establish whether adaptations can be made to increase the accessibility and inclusivity of apps for these groups. We conducted 2 sequential studies, consisting of a systematic literature review of mental health apps for underserved populations followed by a qualitative study with underserved young male participants (n=20; age: mean 19). Following the PRISMA (Preferred Reporting Items for Systematic Reviews and Meta-Analyses) guidelines, an electronic search of 5 databases was conducted in 2021. The search yielded 18,687 results, of which 14 articles met the eligibility criteria. The included studies comprised a range of groups, including those affected by homelessness, having physical health conditions, living in low- and middle-income countries, and those with sexual and gender minority identities. Establishing and maintaining user engagement was a pervasive challenge across mental health apps and populations, and dropout was a reported problem among nearly all the included studies. Positive subjective reports of usability, satisfaction, and acceptability were insufficient to determine users' objective engagement. Despite the significant amount of funding directed to the development of mental health apps, juxtaposed with only limited empirical evidence to support their effectiveness, few apps have been deliberately developed or adapted to meet the heterogeneous needs of marginalized and underserved young people. Before mental health apps are scaled up, a greater understanding is needed of the types of services that more at-risk young people and those in limited-resource settings prefer (eg, standard vs digital) followed by more rigorous and consistent demonstrations of acceptability, effectiveness, and cost-effectiveness. Adopting an iterative participatory approach by involving young people in the development and evaluation process is an essential step in enhancing the adoption of any intervention, including apps, in "real-world" settings and will support future implementation and sustainability efforts to ensure that marginalized and underserved groups are reached. PROSPERO CRD42021254241; https://www.crd.york.ac.uk/prospero/display_record.php?RecordID=254241.

Sentiment Analysis of Bali Calendar Application Reviews using K-Nearest Neighbor

The Bali Calendar application received various responses from its users, comprising both positive accolades and negative critiques. This study employs the K-Nearest Neighbor (KNN) method to categorize sentiments into positive and negative, gauging public satisfaction with the Bali Calendar app. Additionally, the Tomek Links method is implemented to enhance the KNN classification code's performance in scrutinizing app reviews. The research distinguishes data timelines into pre and post-Covid periods due to an elevated number of negative reviews post-update during the pandemic.Pre-Covid results reveal KNN accuracy peaked at 93.7% and 94.3% without or with Tomek Links with parameter K=5 and K=3. Post-Covid, KNN accuracy reached 86.0% and 87.2% without or with Tomek Links with parameter K=9. Notably, Tomek Links yield a higher accuracy boost in post-Covid data (1.2%) compared to pre-Covid (0.6%). This underscores Tomek Links' impact on KNN accuracy amid unbalanced datasets.