Google Play Store Research Articles

Internet platforms in the open educational environment in a foreign language for organising independent student work

Relevance. The relevance of investigating web resources for learning in a globalised world in an open educational environment is due to the need to understand modern technical mechanisms involved in the educational process, their achievements and impact on learning. Purpose. The purpose of this study was to form an idea about the educational platforms of Kazakhstan and the world in general, examine the impact of the platforms under consideration on the educational process during the student�s independent work. Methodology. The following methods were used in a complex to solve the tasks and to implement the purpose of the study: analytical-synthetic, comparative, graphical, and statistical. Results. In this study, the following educational resources were compared: Duolingo, Samsung Global Goals, Google Classroom, AnkiDroid Flashcards, Coursera, TED-Ed, EdApp. They were considered in terms of the following parameters: interface and technical capabilities, availability of scientific materials, functionality and scope of application, achievements when used in the course of independent work. The rating of open educational resources is presented in tabular form according to the Google Play Store for the following countries: Kazakhstan, Great Britain, France, USA, Germany, Italy, Spain, Canada, Mexico, Japan, Egypt, and Malaysia. The platforms for teaching students that are actively gaining popularity were also considered: Coursera, TED-Ed, EdApp, Udemy, WizIQ, Blackboard Learn. Conclusions. This study allows for an examination of the modern educational paradigm by comparing different countries worldwide. It highlights the development of Internet technologies in the face of globalisation challenges and provides insights into the main strategies for enhancing the effectiveness of the educational process through the implementation of Internet technologies and new methodological innovations. Keywords: web resource; online training; conventional methods; courses; professional and communicative competence

Analisis Sentimen Ulasan Aplikasi Smart Campus Unisbank di Google Playstore Menggunakan Algoritma Naive Bayes

This study explores sentiment analysis on SmartCampus Unisbank application reviews on Google Play Store using the Naive Bayes classification method. Through Python programming language and web scraping techniques employing the google-play-scraper library, review data was automatically obtained and organized in CSV format. Text preprocessing techniques such as case folding, stopwords removal, tokenization, and stemming were applied to ensure accurate analysis. The data was divided into training and testing sets, and TF-IDF (Term Frequency-Inverse Document Frequency) was used for feature extraction. A Naive Bayes model was constructed and evaluated, achieving an accuracy of 84.6%. While the model demonstrated proficiency in identifying negative sentiments with 100% precision, it requires refinement for recognizing positive sentiments. These findings provide valuable insights for SmartCampus Unisbank developers to understand user perspectives and improve application quality

Klasifikasi Sentimen Terhadap Kualitas Aplikasi Bahan Ajar Digital Akademik Universitas Terbuka di Google Play

Terbuka University is a leading institution that implements the optimization of digital transformation, especially in distance learning systems. To improve the quality of service to students and stakeholders, Terbuka University has developed the Terbuka University Digital Learning Materials application. This application offers several learning modules that can be accessed through the Google Play Store. This research aims to classify data using different labels related to reviews of the Terbuka University Digital Learning Materials application using the Long Short-Term Memory classification algorithm. Evaluation is conducted to find accuracy, f1-score, precision, and recall values. The research results show that classification with Long Short-Term Memory achieves an accuracy of 76.72% with the Vader label, and the accuracy with the TextBlob label reaches 74.21%. Confusion matrix evaluation shows precision results of 0.91 and recall of 0.78, with an f1-score of 0.84 for the Vader label. For the TextBlob label, the precision is 0.96, recall is 0.45, and the f1-score is 0.61. This research contributes positively to understanding the evaluation and classification of reviews of the Terbuka University Digital Learning application. Implementing the Long Short-Term Memory algorithm with the Vader label can be an effective choice to improve service and learning quality through the application.

Sentiment Analysis of Mobile Provider Application Reviews Using Naive Bayes Algorithm and Support Vector Machine

To choose a mobile provider to use, prospective users often rely on reviews left by previous users of the mobile provider application. One source of information for finding reviews of cellular provider applications is the Google Play Store. The purpose of this research is to analyze user reviews of cellular provider applications and find out the comparison of the accuracy levels of the two algorithms to be used, namely the Naïve Bayes Classification (NBC) and Support Vector Machine (SVM) algorithms. The object of this research is focused on the three most popular applications in Indonesia, according to the Goodstate website, namely Telkomsel, IM3, and XL Axiata. After testing using the Naïve Bayes Clasification method, the accuracy value obtained in the MyTelkomsel application is 75%, MyIM3 is 80%, and MyXL is 72%. While the Support Vector Machine method obtained an accuracy value of 77% for MyTelkomsel, 80% for MyIM3, and 76% for MyXL.

Comparison of Naive Bayes Classifier and K-Nearest Neighbor Algorithms with Information Gain and Adaptive Boosting for Sentiment Analysis of Spotify App Reviews

Abstract. At this time, the development of technology are increase rapidly. One of the issue that appear with advance technology is data volume in the world has increase too. With the large data volumes that exist in the world it can be used to some purpose in many field. Entertainment is one of the field that have many interest from user in this world. Spotify is the example of entertainment apps that provided by Google Play Store to give online music streams to their users. Because that apps is provided by Google Play Store, many reviews of the user about the apps it can be classified to know the positive, negative, or neutral. One way to classified the review of user is make sentiment analysis. In this paper, to classify the review we use naïve Bayes classifier and k-nearest neighbors that will be compared with adding Information gain as feature selection and adaptive boosting as boosting algorithm of each classification algorithm that we used. The result of classification using naïve Bayes classifier with adding Information gain and adaptive boosting is 87.28% and k-nearest neighbor with adding information gain and adaptive boosting can perform accuracy of 80.35%. Purpose: Knowing the result each of accuracy from the naïve Bayes classifier and k-nearest neighbor algorithm with adding information gain and adaptive boosting that we used and know how to doing the sentiment analysis step by step with the methods that chosen in this study. Methods/Study design/approach: This study applied data preprocessing, lexicon based labelling with TextBlob, Normalization, Word Vectorization using TF-IDF, and classification with naïve Bayes classifier and k-nearest neighbor, information gain as feature selection, and adaptive boosting as boosting algorithm to boost the accuracy of classification result. Result/Findings: The accuracy of naïve Bayes classifier with adding information gain and adaptive boosting is 87.28%. Meanwhile, by k-nearest neighbor with adding information gain and adaptive boosting reach the accuracy of 80.35%. This result obtained by using 60.000 dataset with data splitting 80% as data training and 20% as data testing. Novelty/Originality/Value: Implementing information gain as feature selection and adaptive boosting as boosting algorithm to naïve Bayes classifier is prove that it can be increase the accuracy of classification, but not same when implementing in k-nearest neighbor. So, for the future research can applied another classification algorithm or feature selection to get better result.

Analisis Faktor-Faktor yang Berpengaruh terhadap Customer Satisfaction pada Aplikasi Mobile Health

The COVID-19 pandemic has brought positive changes to the digital health industry in Indonesia. Kimia Farma Mobile is a mobile health application that offers comprehensive features for its users. The difference in ratings on Google Play Store and Apple App Store can influence trust (brand trust) and customer satisfaction with this application. The quality of electronic services, such as application interface, delivery quality, and transaction security, is increasingly crucial in influencing customer evaluations and ratings. Therefore, this research aims to analyze the factors influencing customer satisfaction with this application. The research was conducted quantitatively online through Google Form. The sampling method used convenience sampling and was analyzed using Structural Equation Modeling-Analysis Moment of Structural (SEM-AMOS). The research findings indicate that e-service quality significantly affects brand trust and customer satisfaction. This suggests that to improve brand trust and customer satisfaction, the mobile health application should be user-friendly and secure. Furthermore, brand trust significantly influences customer satisfaction. This implies that to enhance customer satisfaction, the mobile health application should provide educational and accurate information and offer customer guarantees.

Analysis of LazLive Utilization in Mobile Applications Lazada at Sahoor Time

Live streaming is becoming a global trend that is popularly used in many sectors, including e-commerce. Lazada, as one of the largest app-based e-commerce in Southeast Asia, also utilizes the use of live streaming by initiating LazLive (Lazada Live Streaming) as one of the featured features in their mobile application. Unlike most e-commerce such as Tokopedia and Shopee, Lazada as a brand also creates official live stream content from the company through a series of special programs, which are actual features as well as customized marketing messages. This study aims to examine Lazada's strategy of creating a new live streaming method in its mobile application (LazLive). Based on the view of the social construction theory of technology, this study analyzed 23 Lazada live streams held from March 23 to April 24, 2023, during sahoor time. Using a descriptive qualitative approach, this study used content analysis techniques. The results found that (1) Lazada personalized several of its live streaming features to match the feel of the program, and (2) Lazada continues to update its features according to customer needs and feedback. (3) LazLive received a positive response from Lazada app users and contributed to the number of reviews received by the Lazada mobile app in the Google Play Store. All the innovations that Lazada provides through LazLive are expected to increase application consumers and the welfare of sellers.

Sentiment Analysis of e-Government Service Using the Naive Bayes Algorithm

A digital platform called the Alpukat Population Application is used to handle statistics and information regarding DKI Jakarta's population. Using the Naive Bayes Classifier (NBC) approach, sentiment analysis for applications using satellite placement. The Nave Bayes Classifier technique is utilized for sentiment analysis because of its benefits in modeling and categorizing complicated data. The user reviews and comments gathered from the Google Play Store were the source of the data utilized in this research. Feature extraction using methods like TF-IDF, sentiment labeling on data, and the development of Nave Bayes Classifier models for sentiment classification were all part of the research project. It is anticipated that the study's findings would help us better understand how users interact with the Alpukat population app. This sentiment analysis may assist app administrators and developers in identifying the positives and negatives of applications and planning updates and advancements based on user feedback. It is anticipated that the sentiment classification model created using the Naive Bayes Classifier approach would be able to classify user evaluations into positive, negative, or neutral sentiment categories with a high degree of accuracy. The creation of improved alpukat positioning apps and decision-making may both benefit from this emotive analysis.

Sentiment Analysis on ChatGPT App Reviews on Google Play Store Using Random Forest Algorithm, Support Vector Machine and Naïve Bayes

This study aims to conduct a Sentiment Analysis on ChatGPT App reviews on the Google Play Store using three classification methods: Random Forest Algorithm, Support Vector Machine (SVM), and Naïve Bayes. The main purpose of this study is to detail and understand user sentiment towards the application. From a total of 2652 review data regarding ChatGPT performance from July 28, 2023, to January 28, 2024, the results were 2326 (87.71%) positive reviews and 326 (12.29%) negative reviews, which means that the public is more dominant in responding positively to the use of ChatGPT based on Google Play Store ratings. In this study, researchers used the f1-score to see which method works best because the data has an imbalance of data, so the f1-score is the best way to provide information about how well the model handles minority classes. Through the classification of three different algorithms with testing data taken from 796 (30%) from a total of 2652 rating reviews, it was found that Random Forest got an f1-score of 90% with positive correct data as much as 87.43% and negative accurate data as much as 0.75%, Support Vector Machine got an f1-score value of 90% with positive valid data as much as 86.80% and negative correct data as much as 0.13%, and Naïve Bayes received an f1-score of 87% with positive, accurate data of 88.06% and negative valid data of 0.12%. Therefore, it can be concluded from this study that users who experienced the development of the ChatGPT application felt a more striking positive impact, and the Support Vector Machine and Random Forest methods became the most effective methods in this study, proven by the highest f1-score value.

Patient-Centered Chronic Wound Care Mobile Apps: Systematic Identification, Analysis, and Assessment.

The prevalence of chronic wounds is predicted to increase within the aging populations in industrialized countries. Patients experience significant distress due to pain, wound secretions, and the resulting immobilization. As the number of wounds continues to rise, their adequate care becomes increasingly costly in terms of health care resources worldwide. eHealth support systems are being increasingly integrated into patient care. However, to date, no systematic analysis of such apps for chronic wounds has been published. The aims of this study were to systematically identify and subjectively assess publicly available German- or English-language mobile apps for patients with chronic wounds, with quality assessments performed by both patients and physicians. Two reviewers independently conducted a systematic search and assessment of German- or English-language mobile apps for patients with chronic wounds that were available in the Google Play Store and Apple App Store from April 2022 to May 2022. In total, 3 apps met the inclusion and exclusion criteria and were reviewed independently by 10 physicians using the German Mobile App Rating Scale (MARS) and the System Usability Scale (SUS). The app with the highest mean MARS score was subsequently reviewed by 11 patients with chronic wounds using the German user version of the MARS (uMARS) and the SUS. Additionally, Affinity for Technology Interaction (ATI) scale scores were collected from both patients and physicians. This study assessed mobile apps for patients with chronic wounds that were selected from a pool of 118 identified apps. Of the 73 apps available in both app stores, 10 were patient oriented. After excluding apps with advertisements or costs, 3 apps were evaluated by 10 physicians. Mean MARS scores ranged from 2.64 (SD 0.65) to 3.88 (SD 0.65) out of 5, and mean SUS scores ranged from 50.75 (SD 27) to 80.5 (SD 17.7) out of 100. WUND APP received the highest mean MARS score (mean 3.88, SD 0.65 out of 5) among physicians. Hence, it was subsequently assessed by 11 patients and achieved a similar rating (uMARS score: mean 3.89, SD 0.4 out of 5). Technical affinity, as measured with the ATI scale, was slightly lower in patients (score: mean 3.62, SD 1.35 out of 6) compared to physicians (score: mean 3.88, SD 1.03 out 6). The quality ratings from physicians and patients were comparable and indicated mediocre app quality. Technical affinity, as assessed by using the ATI scale, was slightly lower for patients. Adequate apps for patients with chronic wounds remain limited, emphasizing the need for improved app development to meet patient needs. The ATI scale proved valuable for assessing technical affinity among different user groups.

Improved playstore review sentiment classification accuracy with stacking ensemble

In today's digital era, user reviews on the Playstore platform are an invaluable source of information for developers, offering insights that are critical for service improvement. Previous research has explored the application of stacking ensemble methods, such as in the context of predicting depression among university students, to enhance prediction accuracy. However, these studies often do not explicitly detail the data acquisition process, leaving a gap in understanding the applicability of these methods to different domains. This research aims to bridge this gap by applying the stacking ensemble approach to improve the accuracy of sentiment classification in Playstore reviews, with a clear exposition of the data collection method. Utilizing Logistic Regression as the meta classifier, this methodology is executed in several stages. Initially, data was collected from user reviews of online loan applications on Google Playstore, ensuring transparency in the data acquisition process. The data is then classified using three basic models: Random Forest, Naive Bayes, and SVM. The outputs of these models serve as inputs to the Logistic Regression meta model. A comparison of each base model output with the meta model was subsequently carried out. The test results on the Playstore review dataset demonstrated an increase in accuracy, precision, recall, and F1 score compared to using a single model, achieving an accuracy of 87.05%, which surpasses Random Forest (85.6%), Naive Bayes (85.55%), and SVM (86.5%). This indicates the effectiveness of the stacking ensemble method in providing deeper and more accurate insights into user sentiment, overcoming the limitations of single models and previous research by explicitly addressing data acquisition methods.

Assessing the Quality and Behavior Change Potential of Vaping Cessation Apps: Systematic Search and Assessment.

An increasing number of people are using vapes (e-cigarettes), and with growing evidence of associated harms, there is a need for acceptable cessation support and interventions. Smartphone apps for health and well-being have increased in popularity and use. Limited published literature assesses the potential of apps to support vaping cessation. A systematic search of vaping cessation apps currently available in Australia for iOS and Android platforms was conducted. Apps were assessed against established health app assessment tools for quality and behavior change potential. A systematic search through the Australian Apple iTunes and Google Play stores was conducted using the search terms "vape"; "vaping"; "e-cigarette"; and "cessation," "quit," or "quitting" in May 2023. Only apps that encouraged the cessation of vaping were included. App descriptions were reviewed to determine if they were relevant for inclusion in this study, and relevant apps were downloaded onto the appropriate mobile device for review. The Mobile App Rating Scale (MARS) was used to rate the quality (engagement, functionality, aesthetics, and information) of the apps using an overall score out of 5. The App Behavior Change Scale (ABACUS) was used to assess the behavior change potential of each app using a score out of 21. An initial search of the app stores yielded 220 Android apps and 124 iOS apps. Screening against the inclusion criteria left 20 iOS apps and 10 Android apps for review. Six apps were available on both operating systems, and these were downloaded, reviewed, and reported separately for each operating system. The average MARS score for all apps assessed in this review was 3.1 (SD 0.41) out of 5. The reviewed apps overall performed well for the MARS elements relating to functionality, such as ease of use and navigation, but had the lowest scores for information-related elements, such as credibility. The number of ABACUS behavior change features per app ranged from 0 to 19 out of 21, with a mean of 8.9 (SD 4.51). The apps commonly included information-related features, such as requesting baseline information. The least common behavior change features were those relating to goal-setting, such as asking about the user's willingness for behavior change and providing feedback on current actions in comparison to future goals. The identified vaping cessation apps had moderate levels of quality and some behavior change components. Future vaping cessation apps could benefit from including more features that are known to support behavior change, such as goal-setting, to improve the potential benefit of these apps to support people to stop vaping. As guidelines for vaping cessation continue to be established, future apps need to reference these in their development.

Mobile Apps for Common Noncommunicable Disease Management: Systematic Search in App Stores and Evaluation Using the Mobile App Rating Scale.

The success of mobile apps in improving the lifestyle of patients with noncommunicable diseases through self-management interventions is contingent upon the emerging growth in this field. While users of mobile health (mHealth) apps continue to grow in number, little is known about the quality of available apps that provide self-management for common noncommunicable diseases such as diabetes, hypertension, and obesity. We aimed to investigate the availability, characteristics, and quality of mHealth apps for common noncommunicable disease health management that included dietary aspects (based on the developer's description), as well as their features for promoting health outcomes and self-monitoring. A systematic search of English-language apps on the Google Play Store (Google LLC) and Apple App Store (Apple Inc) was conducted between August 7, 2022, and September 13, 2022. The search terms used included weight management, obesity, diabetes, hypertension, cardiovascular diseases, stroke, and diet. The selected mHealth apps' titles and content were screened based on the description that was provided. Apps that were not designed with self-management features were excluded. We analyzed the mHealth apps by category and whether they involved health care professionals, were based on scientific testing, and had self-monitoring features. A validated and multidimensional tool, the Mobile App Rating Scale (MARS), was used to evaluate each mHealth app's quality based on a 5-point Likert scale from 1 (inadequate) to 5 (excellent). Overall, 42 apps were identified. Diabetes-specific mHealth apps accounted for 7% (n=3) of the market, hypertension apps for 12% (n=5), and general noncommunicable disease management apps for 21% (n=9). About 38% (n=16) of the apps were for managing chronic diseases, while 74% (n=31) were for weight management. Self-management features such as weight tracking, BMI calculators, diet tracking, and fluid intake tracking were seen in 86% (n=36) of the apps. Most mHealth apps (n=37, 88%) did not indicate whether there was involvement of health professionals in app development. Additionally, none of the apps reported scientific evidence demonstrating their efficacy in managing health. The overall mean MARS score was 3.2 of 5, with a range of 2.0 to 4.1. Functionality was the best-rated category (mean score 3.9, SD 0.5), followed by aesthetics (mean score 3.2, SD 0.9), information (mean score 3.1, SD 0.7), and engagement (mean score 2.9, SD 0.6). The quality of mHealth apps for managing chronic diseases was heterogeneous, with roughly half of them falling short of acceptable standards for both quality and content. The majority of apps contained scant information about scientific evidence and the developer's history. To increase user confidence and accomplish desired health outcomes, mHealth apps should be optimized with the help of health care professionals. Future studies on mHealth content analysis should focus on other diseases as well.

Mobile Applications to Support Multiple Sclerosis Communities: The Post-COVID-19 Scenario.

Introduction: The increase in the use of mobile apps since the COVID-19 pandemic, even among people with multiple sclerosis (PwMS) and health care providers (HCPs), has enabled access to reliable information, symptoms monitoring and management, and social connections. The pandemic has undoubtedly contributed to the acceleration of the "digital revolution." But how far has it progressed for the MS communities? Methods: Italian Google Play and App Store were queried, selecting MS-specific apps in English or Italian language and usable by a wide public. Results: Fifty-four (n = 54) MS-specific apps were identified; most were PwMS-oriented (83%), free of charge (94%), and in English language (76%). The 45 PwMS-oriented apps focused on increasing MS knowledge (71%), tracking symptoms (33%), and promoting networking with peers or HCPs (38%). The 13 HCPs-oriented tools addressed education and updates on MS (62%), disease assessment and management (54%), and research (15%). Google Search tool was also queried to find non-MS-specific apps to fulfill some unmet domains (as sleep, pain, sexual or mental health). Twenty-four additional apps were listed to provide a valuable contribution. Conclusion: The "digital revolution" led to increasingly customized tools for PwMS, especially as m-health or social-networking apps. However, apps to support other specific MS-relevant domains, appealing HCPs-oriented apps, and specific mobile tools for MS caregivers are still lacking. The absence of data assessing the usability and quality of MS apps in ecologically contexts leads to not reliable conclusions about potential benefits. A strong dialogue between MS communities and the digital industry is encouraged to fill this gap.

Mobile Health Applications (mHealth apps) for breastfeeding: a qualitative review using the Mobile Application Rating Scale.

mHealth apps are the most commonly used applications by women for seeking information and support for breastfeeding. The primary goal of this study is to provide a quality assessment of Italian-language mHealth apps for breastfeeding using the Italian version of the Mobile App Rating Scale (I-MARS). A systematic search was conducted on the Apple App Store, Google Play Store, and Windows Store. Inclusion criteria were: mHealth apps available in Italian, free of charge, and focused on the theme of breastfeeding. The quality assessment of the eligible mHealth apps was carried out on the latest available version using the I-MARS, by two authors independently. A total of 381 mHealth apps were identified, of which 38 mHealth apps were included and evaluated (n=9 on Google Play Store, n=29 on Apple App Store). The average total score of the objective dimension of I-MARS was found to be adequate, equal to 3,07±0,75, with a Cohen's Kappa score of 65,8%. The subjective dimension of the I-MARS, however, achieved a low average total score of 2,44±1,03, with a Cohen's Kappa score of 60,5%. In this regard, the subjective dimension of the I-MARS shows lower values compared to the subjective evaluation of the users (3,28±1,95). The informational quality dimension of mHealth apps was found to be lacking and/or inadequate in 80% of cases. 53% of the selected mHealth apps presented average quality scores that were adequate. The results of this study thus lay the groundwork for future recommendations for the development and proper use of mHealth apps for the protection, promotion, and support of breastfeeding.

WARNE: A stalkerware evidence collection tool

Intimate partner violence (IPV) is a form of abuse in romantic relationships, more frequently, against the female partner. IPV can vary in severity and frequency, ranging from emotional abuse or stalking to recurring and severe violent episodes over a long period. Easy access to stalkerware apps helps foster such behaviors by allowing non-tech-savvy individuals to spy on their victims. These apps offer features for discreetly monitoring and remotely controlling compromised mobile devices, thereby infringing the victim's privacy and the security of their data. In this work, we investigate methods for gathering evidence about an abuser and the stalkerware they employ on a victim's device. We develop a semi-automated tool intended for use by investigators, helping them to analyze Android phones for potential threats in cases of IPV stalkerware. As a first step towards this goal, we perform an experimental privacy and security study to investigate currently available stalkerware apps. We specifically study the vectors through which vulnerabilities found in stalkerware apps could be exploited by investigators, allowing them to gather information about the IPV services, IPV abusers, and the victims' stolen data. We then design and implement a tool called WARNE, leveraging the identified flaws to facilitate the information and evidence collection process. In our experiments, we identified 50 unique stalkerware apps and their corresponding download websites that are still reachable, including one available on the Google Play Store. Among these apps, we found 30 that were free or offered a free trial. We enumerated and experimentally verified several invasive capabilities offered by these apps to clearly identify the severe privacy risks posed by them. We also found that most stalkerware apps store private information locally on the compromised device, potentially giving away information about the abuser. Our evidence-gathering tool found data related to the abuser and/or the stalkerware company, such as account credentials, dashboard URLs, and API tokens in 20 apps out of 30 tested apps. We hope our tool will help IPV victims and investigators against the growing threat of stalkerware abuse.

Sentiment Analysis of DANA Application Reviews on Google Play Store Using Naïve Bayes Classifier Algorithm Based on Information Gain

DANA is a digital payment platform that provides various features to make it easier for users to make payments, transfers, and balance replenishment online. DANA application users provide a variety of reviews that include both constructive and critical opinions, which can be valuable input for DANA application developers. The purpose of this research is to evaluate the results of sentiment classification of DANA application user reviews on the Google Play Store service using the Naïve Bayes Classifier method and Information Gain feature selection. In addition, this study aims to assess the effect of applying IG feature selection on the performance of the resulting model. In this study, reviews are divided into two categories, namely positive and negative based on lexicon-based labeling. Furthermore, data weighting, feature selection, and data division are carried out with a proportion of 80% train data and 20% test data before model building. There are two models, namely a model without feature selection (NBC model) and a model with feature selection (NBC-IG model). The evaluation results showed that the NBC model with 1106 features performed well, with 82.91% accuracy, 83.96% precision, and 90.23% recall. Meanwhile, the NBC-IG model with 536 features showed higher performance, with 85.09% accuracy, 85.79% precision, and 92.09% recall. The application of IG feature selection with the IG value limit parameter > 0.01 in the NBC model successfully reduced the number of features by 570, and improved model performance with an increase in accuracy by 2.18%, precision by 1.83%, and recall by 1.86%.

Mobile health applications for epilepsy in Indian app stores: A systematic review and content analysis using the mobile app rating scale

ObjectiveThe growing prevalence of smartphones may prompt individuals with epilepsy to pursue unfulfilled healthcare requirements through mobile health (mHealth) apps, but the content and quality of these mHealth apps are rarely analysed. Hence, this study aimed to identify and assess the quality of epilepsy apps for patients with epilepsy (PWE), their caregivers, and healthcare practitioners (HCPs) available in the Play Store and App Store of India. MethodsWe performed a systematic search on the Google Play Store and Apple App Store of India to identify the mHealth apps for epilepsy which were released and updated till May 2023. The identified applications were downloaded and the quality was assessed using a Mobile app rating scale (MARS) for the overall quality, Aesthetics, Engagement, Functionality, and Information by three independent reviewers. The intraclass correlation coefficient (ICC) was calculated to assess the interrater reliability between the reviewers. An unpaired t-test was calculated to analyse the difference in mean scores for Android and iOS applications. ResultsThe systematic search yielded a total of 2518 apps, out of which 26 were selected for inclusion in the study. Among these, 9 apps were compatible with Android, 11 with iOS, and 6 on both platforms. The mean (SD) MARS score of the apps was 3.5 (0.6) and the ICC for the overall app quality was 0.90 (95% CI: 0.82–0.96). Overall, apps scored highest in functionality (3.9), followed by aesthetics (3.6), information (3.3), and engagement (3.2). Among the included apps, the overall quality score was found to be higher for iOS apps than Android (MD = 0.54; 95% CI: 0.02 – 1.07; p-value: 0.042). ConclusionOur study identified twenty-six mHealth applications for epilepsy that integrated various aspects of epilepsy self-management. The results of this study emphasize the importance of ensuring that current and future applications offer evidence-based information, integrate features that align with patient preferences, and generate evidence regarding the effectiveness of application usage.

Mobile Technologies for Monitoring Sleep Time: A Systematic Search of App Stores in Brazil

Abstract Introduction Decreased sleep time is detrimental to physical and mental health, exerting negative impacts on daily functioning and quality of life. Mobile health (mHealth) applications can be useful for improving sleep quality. Objective To perform a systematic search of mHealth applications for monitoring sleep time at Brazilian online stores and evaluate the selected applications in terms of engagement, functionality, aesthetics, and quality of information. Methods A systematic search was performed at the Google Play Store and the App Store developed or updated between 2020 and 2022. The mobile app rating scale (MARS) was used to assess their quality. The characteristics and information of these applications were presented. Data were analyzed descriptively. Results Among the 2,264 relevant mHealth apps identified, 11 were eligible for inclusion. There was one app that offered only sleep time recordings, three offered sleep recordings and educational content, three monitored sleep time with audiovisual resources, two offered sleep time recordings with a focus on monitoring snoring, and two offered sleep time monitoring with individual content customizations. The apps scored fair on MARS, with a mean of 3.5 points (standard deviation: 0.8) on a scale of 1 to 5. Most apps scored low due to poor evidence-based information, aesthetics, and engagement. Conclusion Although the use of mHealth technologies for monitoring sleep time has considerable potential for investigation, it is a relatively new, underexplored topic. Collaboration between researchers, clinical professionals, patients, and application developers is necessary for the creation of new evidence-based mHealth applications focused on Brazilian users.

ANALISIS SENTIMEN TINGKAT KEPUASAN PELANGGAN TERHADAP LAYANAN KURIR J&T EXPRESS MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE (SVM) BERDASARKAN ULASAN PENGGUNA DI GOOGLE PLAYSTORE

Courier Service Is One Of The Services That Are Widely Used By The Public, Especially In The Current Digital Era. In This Context, Courier Services Allow Shippers To Deliver Goods Or Documents Without The Need To Be Present Directly To The Destination Location. J & T Express, As One Of The Shipping Expedition Service Providers In Indonesia, Is The First Choice For Many People. Although Technology Continues To Evolve And Competition Is Increasingly Fierce, The Quality Of Courier Services Is A Key Factor That Customers Need To Pay Attention To. However, It Should Be Noted That The J&T Express Application In The Google Play Store Received A Low Rating, And This Is The Background Of This Study. the main focus of this study was to identify the level of customer satisfaction with j&t express courier services through reviews available on the google play store. within the framework of this study, sentiment analysis was conducted using the support vector machine algorithm, by applying crisp-dm methodology. the results showed that from the business understanding stage to the modeling stage, the performance of the support vector machine can be considered good. in addition, this study also resulted in an implementation that can be accessed through a website with the address jnt-sentiment.streamlit.app. hopefully, this research can contribute to j & t express in understanding the views of customers and improving the quality of their services