App Recommendation Research Articles

2B-Alert app 2.0: personalized caffeine recommendations for optimal alertness.

If properly consumed, caffeine can safely and effectively mitigate the effects of sleep loss on alertness. However, there are no tools to determine the amount and time to consume caffeine to maximize its effectiveness. Here, we extended the capabilities of the 2B-Alert app, a unique smartphone application that learns an individual's trait-like response to sleep loss, to provide personalized caffeine recommendations to optimize alertness. We prospectively validated 2B-Alert's capabilities in a 62-h total sleep deprivation study in which 21 participants used the app to measure their alertness throughout the study via the psychomotor vigilance test (PVT). Using PVT data collected during the first 36h of the sleep challenge, the app learned the participant's sleep-loss response and provided personalized caffeine recommendations so that each participant would sustain alertness at a pre-specified target level (mean response time of 270ms) during a 6-h period starting at 44h of wakefulness, using the least amount of caffeine possible. Starting at 42h, participants consumed 0 to 800mg of caffeine, per the app recommendation. 2B-Alert recommended no caffeine to five participants, 100-400mg to 11 participants, and 500-800mg to five participants. Regardless of the consumed amount, participants sustained the target alertness level ~80% of the time. 2B-Alert automatically learns an individual's phenotype and provides personalized caffeine recommendations in real time so that individuals achieve a desired alertness level regardless of their sleep-loss susceptibility.

Comprehensive Analysis for Intelligent Recommendation on Mobile Applications

With the development of mobile devices and mobile apps, corresponding app recommendation analysis has received increasing focus in recent years. Such recommendation analysis covers aims including app evaluation, API-based app development, customer investigation, app security, etc. Meanwhile, various types of recommendation techniques are exploited in the app recommendation analysis, which continually improves the development of this direction. However, there is still a lack of a systematical study providing an overall development picture for these app recommendation efforts. Thus, it faces an obstacle for related researchers following this direction of work, and correspondingly is not conducive to the future development. To overcome the problem, in this paper, we take the first step to systematically investigate this direction of efforts. To this end, we summary the main works and techniques used in more than 35 important works in this direction. To better understand the development routines, we have analyzed the characteristics of these works from two perspectives, i.e., technology and research scenario. We have obtained some interesting conclusions within this research direction, and put forward some work suggestions according to the overall research.

Content Recommendation Systems in Web-Based Mental Health Care: Real-world Application and Formative Evaluation.

Recommender systems have great potential in mental health care to personalize self-guided content for patients, allowing them to supplement their mental health treatment in a scalable way. In this paper, we describe and evaluate 2 knowledge-based content recommendation systems as parts of Ginger, an on-demand mental health platform, to bolster engagement in self-guided mental health content. We developed two algorithms to provide content recommendations in the Ginger mental health smartphone app: (1) one that uses users' responses to app onboarding questions to recommend content cards and (2) one that uses the semantic similarity between the transcript of a coaching conversation and the description of content cards to make recommendations after every session. As a measure of success for these recommendation algorithms, we examined the relevance of content cards to users' conversations with their coach and completion rates of selected content within the app measured over 14,018 users. In a real-world setting, content consumed in the recommendations section (or "Explore" in the app) had the highest completion rates (3353/7871, 42.6%) compared to other sections of the app, which had an average completion rate of 37.35% (21,982/58,614; P<.001). Within the app's recommendations section, conversation-based content recommendations had 11.4% (1108/2364) higher completion rates per card than onboarding response-based recommendations (1712/4067; P=.003) and 26.1% higher than random recommendations (534/1440; P=.005). Studied via subject matter experts' annotations, conversation-based recommendations had a 16.1% higher relevance rate for the top 5 recommended cards, averaged across sessions of varying lengths, compared to a random control (110 conversational sessions).Finally, it was observed that both age and gender variables were sensitive to different recommendation methods, with responsiveness to personalized recommendations being higher if the users were older than 35 years or identified as male. Recommender systems can help scale and supplement digital mental health care with personalized content and self-care recommendations. Onboarding-based recommendations are ideal for "cold starting" the process of recommending content for new users and users that tend to use the app just for content but not for therapy or coaching. The conversation-based recommendation algorithm allows for dynamic recommendations based on information gathered during coaching sessions, which is a critical capability, given the changing nature of mental health needs during treatment. The proposed algorithms are just one step toward the direction of outcome-driven personalization in mental health. Our future work will involve a robust causal evaluation of these algorithms using randomized controlled trials, along with consumer feedback-driven improvement of these algorithms, to drive better clinical outcomes.

Sleep mHealth Applications and Behavior Change Techniques Evaluation

ABSTRACT Objectives Mobile health apps may be an effective way to increase sleep management skills. Although little has been documented about the content and quality of available sleep management apps, providers often make app recommendations to help with sleep self-management. The objective of this study was to systematically evaluate the content and quality of commercially available sleep apps. Methods Following a systematic search of the Apple App and Google Play stores, 56 sleep management apps were evaluated. App content was evaluated using the taxonomy of behavior change techniques (BCTs), and app quality was assessed using the Mobile App Rating Scale. Results Sleep management apps included 0–15 BCTs (M = 6.89) and 0–9 sleep BCTs (M = 4.87). App quality ranged from 2.51 to 4.80 (M = 3.78) out of 5.00. Sleepiest Sleep Sounds Stories, ShutEye: Sleep Tracker, and Mintal Tracker: Sleep Recorder included the highest number of sleep BCTs and highest quality scores. Conclusions While the content and quality of sleep management apps is variable, the findings are promising as many apps included a high number of BCTs and high quality. Although evidence of efficacy through randomized controlled trials is necessary to establish efficacy, this review can aid in app selection in the interim.

Post-separation parenting apps in the hands of family law practitioners: expectations versus experience

Abstract Post-separation parenting apps are an alternative to mainstream digital communication (e.g. text and email) for separated parents. They vary in cost and features, generally incorporating a messaging tool, shared calendar, expense tracker, and the ability to export records for legal purposes. While often recommended in the context of family law, evidence for efficacy and safety is lacking. This study sought insights from family law professionals about the value of post-separation parenting apps in high-conflict cases. Thirty family mediators, known in Australia as Family Dispute Resolution Practitioners, role-played pairs of high-conflict separated parents using one of 10 popular post-separation parenting apps. After completing a set of common co-parenting tasks, dyadic interviews and focus groups were used to discuss their observations. Overall, practitioners expressed disappointment with the apps. Key themes included potential individual differences in separated parents’ technical skills, time availability, and intentions towards app use. Usability challenges specific to the tested apps were also identified. Rather than simplifying interactions for separated parents, these combined contextual variables were thought likely to contribute to frustration and inter-parental conflict. As a result, practitioners in the study resolved to be far more cautious with app recommendations for high-conflict clients.

Implementation of the Management of Anticoagulation in the Periprocedural Period App into an Electronic Health Record: A Cost-Effectiveness Analysis.

The Management of Anticoagulation in the Periprocedural Period (MAPPP) app is a free tool providing up-to-date guidelines on the periprocedural management of patients on long-term anticoagulants. After validating its effectiveness in the post-procedural period, we aimed to study its overall cost-effectiveness. SF-12 surveys were sent to eligible patients, converted into SF-6D forms, and subsequently into quality-adjusted life years (QALYs) to calculate the incremental cost-effectiveness ratio (ICER). The number of 30-day readmissions was used to calculate hospitalization costs, utilizing publicly available data. From 1/1/2018 to 1/31/2019, 642 patients were screened for enrollment, with an overall response rate of 94% (164/175) among the consented and 49% (164/336) among all eligible patients. The average QALY score was 0.7134 (95% CI [0.6836, 0.7431]) for the patients whose treatment plan followed the MAPPP app recommendations (acceptance group) and 0.7104 (95% CI [0.6760, 0.7448]) for those who did not (rejection group), without statistically significant differences. The difference in ICER scores was -$429 866.67, with the negative sign demonstrating that acceptance was the dominant strategy. By utilizing QALYs and ICER scores we have shown that the acceptance of MAPPP app recommendations is the dominant strategy for the periprocedural management of patients on long-term anticoagulation.

937. Appropriateness of using a Mobile Application for Choosing Antibiotic Therapy in Hospitalized Patients at Siriraj Hospital

Abstract Background Development of facility-specific clinical practice guidelines and incorporation of computerized clinical decision support have been recommended as the effective antimicrobial stewardship strategies. The DigitalAMSTM is a mobile-based application used to guide choosing empirical antibiotics. Before the hospital-wide implementation of DigitalAMSTM, the appropriateness and limitation of such an application needs to be evaluated. Methods A retrospective cross-sectional study of hospitalized adult patients who received at least one dose of antibiotic and had at least one documented site of infection were enrolled between 1 Jan and 31 Jun 2018. All necessary data was obtained via chart review. The antibiotic regimen that was prescribed by the ward physician (WARD), the regimen recommended by the DigitalAMSTM (APP), the regimen recommended by the independent infectious disease (ID) physicians before and after knowing the culture results (Emp-ID and Def-ID) were compared. Results A total of 401 patients of the targeted infections i.e. 98 subjects with pneumonia, 103 subjects with urinary tract infection (UTI), 98 subjects with bacteremia and 102 subjects with skin and soft tissue infection (SSTI) were enrolled. The percent agreement between the APP and the WARD was less than half in all sites of infection. The APP regimen provided approximately 80% agreement with the Emp-ID regimen among subjects with UTI (78.6%), bacteremia (85.7%) and SSSI (85.2%), while the percent agreement of the WARD regimen and the Emp-ID was approximately half in all sites of infection. The lowest percent agreement between the APP regimen and the Emp-ID regimen was found among subjects with pneumonia (59.1%). Univariate analysis did not reveal any association between subjects who received the antibiotic regimen matching to the APP recommendation and the 28-day mortality. Conclusion Our study confirmed that the DigitalAMSTM application could improve appropriateness of antibiotic regimens for empirical therapy for four common infections among adult hospitalized patients at Siriraj Hospital. However, some revisions need to be done to improve the appropriateness of antibiotic regimens in the APP, especially for subjects with pneumonia. Disclosures All Authors: No reported disclosures.

Correct dosing of Prothrombinex-VF in normalising elevated international normalised ratio in critically ill patients: a prospective cohort pilot study.

Prothrombinex-VF is being increasingly used as an off-label therapy to correct non-warfarin-related elevations in international normalised ratio (INR) in the critically ill. Currently there are no dosing guidelines for such use. To validate a prediction equation, embedded in a smartphone application (app), to guide dosing of Prothrombinex-VF in critically ill patients. A prospective pilot cohort study of critically ill adult patients with elevated INRs who were treated with Prothrombinex-VF. The main outcome measured was INR following Prothrombinex-VF administration. Of the 31 patients included, five (16%) were taking warfarin prior to admission and 14 (45%) had chronic liver disease. There was a significant decrease in INR after Prothrombinex-VF treatment (P < 0.001) and a significant correlation between the app's predicted INRs and the measured INRs (r=0.63 and P < 0.001). The app's predicted INRs were less accurate for patients with chronic liver disease than for those without. Overall, the app's recommendations achieved an INR either similar to (29.6%) or better than (55.6%) what would have been achieved had the warfarin reversal guidelines been applied to dose the Prothrombinex-VF. The app appeared to be reasonably accurate at predicting normalisation of elevated INRs after administration of Prothrombinex-VF, especially among patients without liver disease. Its dosing recommendations were similar to or possibly better than preexisting warfarin reversal guidelines in over 85% of the situations analysed, if we assume a higher dose of Prothrombinex-VF would achieve a greater reduction in INR than a lower dose.

Motivating consumers for health and fitness: The role of app features

AbstractSmartphone apps can create value for consumers by supporting their health goals. The purpose of the study was to reveal people's preferences for Self‐Determination theory derived app features of health‐related apps that can potentially promote motivation and sustained use of such apps. Three discrete choice experiments, followed by a ranking task, were used to assess consumer preferences for specific app features that can support the basic needs for autonomy, competence and relatedness among respondents from Germany and Spain (N = 719). Participants preferred the autonomy supporting app features, namely making changes to the menu recommendations or self‐selecting their rewards. The competence supporting features of levels of progress and feedback that provided encouragement together with facts were preferred across countries; however, presenting the feedback in a dynamic display was disliked in Germany. The relatedness supporting feature, presence of an anthropomorphic cue with the menu recommendations, was preferred in Germany but disliked in Spain. Health and fitness apps can benefit from including features that bring value to consumers by responding to their psychological needs and help them achieve their health goals. Allowing choice flexibility in app recommendations, providing feedback that is encouraging in addition to informative, and including gamification elements in health apps, can respond to consumer preferences and thereby increase engagement with apps. The study contributes to understanding how the theoretically derived features of health apps can be included in the design of apps to match consumer preferences.

Security and privacy recommendation of mobile app for Arabic speaking

&lt;p&gt;There is an enormous number of mobile apps, leading users to be concerned about the security and privacy of their data. But few users are aware of what is meant by app permissions, which sometimes do not illustrate what kind of data is gathered. Therefore, users are still concerned about security risks and privacy, with little knowledge and experience of what security and privacy awareness. Users depend on ratings, which may be fake, or keep track of their sense to install an app, and an enormous number of users do not like to read reviews. To solve this issue, we propose a recommender system that reads users' reviews, and which exposes flaws, violations and third-party policies or the quality of a user's experience. In order to design and implement our recommender, we conduct a survey which supports two significant points: to detect the level of security and privacy awareness between users, and to gather new words into a dictionary of a recommender system, which assists to classify each review on the correct level, which can indeed reveal the scale of security and privacy in an app.&lt;/p&gt;

Investigating the impact of demographic and device information in the recommendation of mobile applications

The number of people with access to mobile devices, as well as applications to these devices (i.e., apps), has been increasing significantly. Thus, users have to choose among a large number of apps proposing to do the same functions, those that better serve them. A possible solution to this problem is the adoption of recommendation systems. Meanwhile, usually these systems consider only users' preferences to create a profile or request sensitive data (e.g., call and message logs). This work investigates the impact of using demographic and device information on app recommendation by using only easy-to-obtain data to enrich a user profile. We evaluate two approaches: a similarity-based Collaborative Filtering with a limited number of apps and a topic-based approach (i.e., LDA) with wider large-scale data. We also inspected the results under both apps and categories context. The general results reveal that the enriched data provides a better app recommendation with the addition of information about the user's region mean wage achieving up to 210% (or 12 percentage points) of improvement in terms of recall.

STRATEGI SOFT BALANCING INDIA DALAM PEMBLOKIRAN APLIKASI CINA

This article aims to explain why India has banned 267 Chinese application amidst the escalation of the Ladakh border dispute. Rely on seconder data with explanative type research and adopt soft-balancing concept from T.V Paul about economic sanction and Robert A. Pape regarding economic strengthen. The results show that the Chinese apps banned are India's soft-balancing strategy toward China. Soft-Balancing strategy driven by capability disparity among India and China economically, military, and technologically. Soft-balancing strategy open the room for strengthening the Indian apps ecosystem. Strengthen the Indian apps Ecosystem through a recommendation of Indian apps to substitute the function of Chinese apps, held Digital India AatmaNirbhar Bharat Innovate Challenge to Indian apps developer, and launched AatmaNirbhar Bharat apps to support the self-reliance of Indian apps ecosystem.

Perception of Innovative Usage of AI in Optimizing Customer Purchasing Experience within the Sustainable Fashion Industry

The research was designed to contribute to scientific efforts in exploring the attitude of fashion stakeholders towards AI and its use in attaining sustainability in fashion industry. Although the role of AI in Fashion has been studied before, the aim of this research is to challenge and analyze the attitudes towards sustainable fashion of both stakeholders and consumers. The research considers the views of consumers, industry professionals and company shareholders on the role AI plays in pursuing ideas of Sustainable Fashion. Contrary to expectations, the companies with significant turnover did not show any greater awareness of the new trends in the fashion business. Furthermore, previous familiarity with the usage of AI did not prove to promote openness towards the recommendation of apps which use AI to promote Sustainable Fashion. The value of this research lies in the findings, which help provide a framework which can be used to change the viewpoint of the key market players. The crucial finding is that the AI approach on sustainability will influence both users (changing their purchasing decisions toward more sustainable choices if provided with a set of information on ecological impact, production choices), and corporate businesses (changing the overall business strategy, planning, marketing communication and production designs). The paper offers milestones for further research on synergies between AI, fashion industry lined with UNS SDGs and purchasing behavior.

Personalized Mobile App Recommendation by Learning User’s Interest from Social Media

Abstract: In social media, user interests and knowledge are vital but often overlooked resources. There are a few ways to get a sense of what people are known for, such as Twitter lists and LinkedIn Skill Tags, but most people are untagged, so their interests and expertise are effectively hidden from applications like personalised recommendation and community detection and expert mining. We obtain personalised app recommendations by learning the interest's association between applications and tweets by introducing an unique generative model called IMCF+ to convert user interest from rich tweet information to sparse app usage. We analyse the performance of this technique predicts the top ten apps with an 82.5 percent success rate using only 10% training data. Furthermore, in the high sparsity situation and user cold-start scenario, this purpose technique outperforms the other six state-of-the-art algorithms by 4.7 percent and 10%, demonstrating the effectiveness of our technology. All of these findings show that our method can reliably extract user interests from tweets in order to aid in the solution of the personalised app recommendation problem. Keywords: Social Media, User Profile, deep learning, Privacy, matrix factorization,App recommendation.

Adolescents' Algorithmic Resistance to Short Video APP's Recommendation: The Dual Mediating Role of Resistance Willingness and Resistance Intention.

Adolescents have gradually become a vital group of interacting with social media recommendation algorithms. Although numerous studies have been conducted to investigate negative reactions (both psychological and behavioral reactance) that the dark side of recommendation algorithms brings to social media users, little is known about the resistance intention and behavior based on their agency in the daily process of encountering algorithms. Focusing on the concept of algorithm resistance, this study used a two-path model (distinguishing resistance willingness and resistance intention) to investigate the algorithmic resistance of rural Chinese adolescents (N = 905) in their daily use of short video apps. The findings revealed that the perceived threat to freedom, algorithmic literacy, and peer influence were positively associated with the resistance willingness and intention; while the independent psychology on algorithmic recommendations significantly weakened resistance willingness and intention. Furthermore, this study verified the mediating role of resistance willingness and intention between the above independent variables and resistance behavior. Additionally, the positive impact of resistance willingness on resistance intention was confirmed. In conclusion, this study offers a comprehensive approach to further understanding adolescents’ algorithmic resistance awareness and behavior by combining psychological factors, personal competency, and interpersonal influences, as well as two types of resistance reactions (rational and irrational).

CFDIL: a context-aware feature deep interaction learning for app recommendation.

The rapid development of mobile Internet has spawned various mobile applications (apps). A large number of apps make it difficult for users to choose apps conveniently, causing the app overload problem. As the most effective tool to solve the problem of app overload, app recommendation has attracted extensive attention of researchers. Traditional recommendation methods usually use historical usage data to explore users’ preferences and then make recommendations. Although traditional methods have achieved certain success, the performance of app recommendation still needs to be improved due to the following two reasons. On the one hand, it is difficult to construct recommendation models when facing with the sparse user–app interaction data. On the other hand, contextual information has a large impact on users’ preferences, which is often overlooked by traditional methods. To overcome the aforementioned problems, we proposed a context-aware feature deep interaction learning (CFDIL) method to explore users’ preferences and then perform app recommendation by learning potential user–app relationships in different contexts. The novelty of CFDIL is as follows: (1) CFDIL incorporates contextual features into users’ preferences modeling by constructing novel user and app feature portraits. (2) The problem of data sparsity is effectively solved by the use of dense user and app feature portraits, as well as the tensor operations for label sets. (3) CFDIL trains a new deep network structure, which can make accurate app recommendation using the contextual information and attribute information of users and apps. We applied CFDIL on three real datasets and conducted extensive experiments, which shows that CFDIL outperforms the benchmark methods.

Participatory Design of a Mobile App to Safeguard Mental Resilience in the Context of Drug Use in Young Adults: Multi-Method Study.

BackgroundExisting mental health apps are largely not aimed at generally healthy young people who may be experimenting with addictive substances and mind-altering experiences.ObjectiveThe aim of this study is to examine the interest and expectations of young people regarding a proposed smartphone app designed to help protect and promote mental health and resilience in the face of risks associated with substance use.MethodsThe study was based on agile system development and had 3 empirical substudies. Our feasibility study (study 1) included an anonymous questionnaire that examined the potential interest of young people in this type of app. It was answered by 339 Israelis aged 18-30 years. The second part of the feasibility study was a pilot study with 1.2% (4/339) of the people who answered the questionnaire and expressed interest in participating in a focus group. They tested and refined the elements planned for the focus groups. Study 2 was a participatory design study involving 7 focus groups of 5 to 7 participants each (young people aged 18-35 years, n=38). Persona development, open discussion, and a Technology Acceptance Model questionnaire were used to elicit user expectations and requirements for the app and to understand the perceived usefulness and usability of the proposed features. Study 3 comprised in-depth interviews with experts in the field of youth mental health and drug use to enlist their professional opinion regarding the value of such an app and recommendations about the features it should include.ResultsThe mock-up for the proposed app had five key features: personalized assessment of risk for a drug-associated mental crisis, support for self-monitoring, useful information (eg, warning signs and first-aid guidelines), resilience-building exercises, and a support center. Participants rated highly the usefulness of all 5 main features and 96% (24/25) of the specific features we proposed within those main categories. The participants also suggested additional features as well as a new user persona we had not considered: the parents or family members of the young person. The focus groups rated highly the perceived usability of the app. Most of the experts saw value in all the main features and suggested specific knowledge sources for the app’s content. Finally, participants of both the feasibility study and the participatory design study expressed moderate to high interest in using the app for self-help and high interest in using the app to help friends.ConclusionsThe findings provide preliminary encouraging support for the 5 main features suggested by the research team and reinforce recommendations for mobile health apps found in the literature. The findings emphasize the insight that this kind of app should be designed primarily for use by individuals seeking to help others.

Functional feature-aware APP recommendation with personalised PageRank

Functional feature-aware APP recommendation with personalised PageRank

A Preliminary Evaluation of Mobile Phone Apps to Curb Alcohol Consumption.

Mobile apps have become increasingly prevalent in modern society, and persuasive technology has a broader market than ever. Mobile-based alcohol cessation apps can promote positive behaviour change in users and improve the overall health of our society. This research aimed to understand the various features users respond to and make design recommendations for alcohol cessation apps. This paper reports on three sources of feedback (user ratings, user reviews, MARS App Quality score) provided on 20 alcohol cessation apps in the Google Play Store. Our findings suggest that self-control type apps received much greater positive user reviews than motivational apps. In addition, this trend was not observed through numeric user ratings. We also speculate on design recommendations for apps that are meant to inhibit alcohol intake.

Connecting Older Adults With Mental Health Apps: A Survey of Provider App and Education Material Use

Many older veterans have access to mobile devices and are interested in using apps for mental health self-management, but few have ever downloaded health apps. To address the need for awareness of and access to VA mental health apps, we developed patient educational materials aimed towards older (or novice) users of mobile devices. The present study explored health care providers’ and staff’s perceptions about use of mental health mobile applications (apps) with older veterans and examined potential utility of these patient educational materials. Requestors of mobile device education materials (N = 90) were surveyed when ordering materials and again 4 months later. Baseline and follow-up surveys assessed frequency of app recommendation, and comfort recommending apps. Baseline surveys examined perceived advantages of apps; follow-up surveys examined perceived utility of the educational materials. Descriptive statistics and qualitative analysis were conducted. Most requesters (68.5%) initially were not comfortable using apps, yet perceived many advantages to using apps and hoped materials could facilitate app use. At follow-up, requestors felt more comfortable recommending apps alongside our materials. Qualitative analysis revealed perceived advantages to using the education materials. The benefits of developing and disseminating educational materials for providers to share with older veterans helped support older veterans’ app use, and potentially increased providers’ comfort with and frequency of recommending apps to their older patients. Access to educational materials can mitigate discomfort among providers in recommending apps to older users and may bring about valuable discussions about apps which support mental health.