Traffic Classification (TC), consisting in how to infer applications generating network traffic, is currently the enabler for valuable profiling information, other than being the workhorse for ...service differentiation/blocking. Further, TC is fostered by the blooming of mobile (mostly encrypted) traffic volumes, fueled by the huge adoption of hand-held devices. While researchers and network operators still rely on machine learning to pursue accurate inference, we envision Deep Learning (DL) paradigm as the stepping stone toward the design of practical (and effective) mobile traffic classifiers based on automatically-extracted features, able to operate with encrypted traffic, and reflecting complex traffic patterns. In this context, the paper contribution is fourfold. First, it provides a taxonomy of the key network traffic analysis subjects where DL is foreseen as attractive. Secondly, it delves into the non-trivial adoption of DL to mobile TC, surfacing potential gains. Thirdly, to capitalize such gains, it proposes and validates a general framework for DL-based encrypted TC. Two concrete instances originating from our framework are then experimentally evaluated on three mobile datasets of human users’ activity. Lastly, our framework is leveraged to point to future research perspectives.
This paper analyzes some salient factors affecting the internationalization speed of digital innovations by tracking international penetrations of 127 apps at Apple's app store. Although apps are ...globally available via online platforms, their international penetration is still subject to cultural, administrative, geographic, and economic (CAGE) distances that act as user adoption barriers to impede app internationalization. App developers may overcome these barriers by employing the demand-side strategies of engaging users in value co-creation. We contribute to an improved understanding of internationalization process in a digital context and also extend demand-side perspective to inform international entrepreneurship research.
•Cross-national distance impedes app internationalization even in cyberspace.•App developers may partly overcome distance by engaging users in value co-creation.
•We analyse how SMEs in developing economies use mobile apps to improve their business efficiency during the pandemic.•The study recognizes effective measures and actions taken by SMEs that have ...turned to mobile-app-based business to improve their sustainability.•We investigate the efficiency of a conceptual model of mobile-app-based business for SMEs.•The analysis suggests that SMEsneed a powerful mobile-app-based business network to succeed in the entrepreneurial business process.
Small and Medium-Sized Enterprises (SMEs) are struggling to cope with the business uncertainty caused by the COVID-19 pandemic. This study examines how SMEs in developing economies have used mobile apps to improve their business efficiency during the pandemic. We aim to recognize effective measures and actions taken by SMEs that have turned to mobile-app-based business to improve their sustainability during the crisis. The study bridges a literature gap by extending the Theory of Consumption Values and the Theory of Planned Behavior to SMEs that incorporate mobile-app-based business. Data was collected from 343 SMEs from three Industrial Development Corporations (IDCs) in India. Using the covariance-based structural equation modeling method, we investigated the efficiency of a conceptual model of mobile-app-based business for SMEs. The results revealed that consumer choice behavior, perceived behavior control, subjective behavior control and attitude towards the mobile app all influence SMEs’ decision-making and business strategy. As such, SMEsneed a powerful mobile-app-based business network to succeed in the entrepreneurial business process. Using instrumental variable analysis, we discovered that increased mobile app usage significantly improves SMEs’ long-term efficiency. The analysis provides several theoretical and managerial ramifications.
More than 78 countries have developed COVID contact-tracing apps to limit the spread of coronavirus. However, many experts and scientists cast doubt on the effectiveness of those apps. For each app, ...a large number of reviews have been entered by end-users in app stores.
Our goal is to gain insights into the user reviews of those apps, and to find out the main problems that users have reported. Our focus is to assess the “software in society” aspects of the apps, based on user reviews.
We selected nine European national apps for our analysis and used a commercial app-review analytics tool to extract and mine the user reviews. For all the apps combined, our dataset includes 39,425 user reviews.
Results show that users are generally dissatisfied with the nine apps under study, except the Scottish (“Protect Scotland”) app. Some of the major issues that users have complained about are high battery drainage and doubts on whether apps are really working.
Our results show that more work is needed by the stakeholders behind the apps (e.g., app developers, decision-makers, public health experts) to improve the public adoption, software quality and public perception of these apps.
•Users are generally dissatisfied with the nine apps under study.•Two major issues are high battery drainage and doubts on apps’ correct functionality.•A large number of cross-(mobile) device issues have been reported for the apps.
Smartphones offer multimedia convergence in a single device, ubiquitous access to media, and constant connections with others. The rapid rise of smartphone use calls for more scholarly attention paid ...to users’ media usage and time expenditure. This study aims to (a) understand smartphone usage patterns by examining time spent using smartphones and task switching between mobile applications (apps), and (b) test the validity of self-reported measures of these behaviors by comparing self-reports with log data from the smartphone. Data were collected from 50 participants over 1 week. Results show that on average participants spent 2 hours 39 minutes on their smartphone and made 101 app switches per day. Among other findings, social networking was the most used app category, age was a significant demographic factor, and participants, especially heavy smartphone users, overestimated their mobile app usage. Theoretical and practical implications of these findings are discussed.
A vast amount of mobile apps have been developed during the past few months in an attempt to "flatten the curve" of the increasing number of COVID-19 cases.
This systematic review aims to shed light ...into studies found in the scientific literature that have used and evaluated mobile apps for the prevention, management, treatment, or follow-up of COVID-19.
We searched the bibliographic databases Global Literature on Coronavirus Disease, PubMed, and Scopus to identify papers focusing on mobile apps for COVID-19 that show evidence of their real-life use and have been developed involving clinical professionals in their design or validation.
Mobile apps have been implemented for training, information sharing, risk assessment, self-management of symptoms, contact tracing, home monitoring, and decision making, rapidly offering effective and usable tools for managing the COVID-19 pandemic.
Mobile apps are considered to be a valuable tool for citizens, health professionals, and decision makers in facing critical challenges imposed by the pandemic, such as reducing the burden on hospitals, providing access to credible information, tracking the symptoms and mental health of individuals, and discovering new predictors.
There are many e-Health mobile apps on the apps store, from apps to improve a user’s lifestyle to mental coaching. Whilst these apps might consider user context when they give their interventions, ...prompts, and encouragements, they still tend to be rigid e.g., not using user context and experience to tailor themselves to the user.
To better engage and tailor to the user, we have previously proposed a Reference Architecture for enabling self-adaptation and AI personalization in e-Health mobile apps. In this work we evaluate the end users’ perception, usability, performance impact, and energy consumption contributed by this Reference Architecture.
We do so by implementing a Reference Architecture compliant app and conducting two experiments: a user study and a measurement-based experiment.
Although limited in the number of participants, the results of our user study show that usability of the Reference Architecture compliant app is similar to the control app. Users’ perception was found to be positively influenced by the compliant app when compared to the control group. Results of our measurement-based experiment showed some differences in performance and energy consumption measurements between the two apps. The differences are, however, deemed minimal.
Our experiments show promising results for an app implemented following our proposed Reference Architecture. This is preliminary evidence that the use of personalization and self-adaptation techniques can be beneficial within the domain of e-Health apps.
This article examines the transformative effects of platforms on cultural production through an analysis of the LINE “super app.” Super apps are apps that do-everything; mega-platforms unto ...themselves. They are particularly prevalent in East Asia. Like China’s WeChat or South Korea’s KakaoTalk, Japan’s LINE has evolved from a single purpose chat app to the do-everything platform for everyday cultural and economic activities. It is also the very reason for the global proliferation of stickers or large-size emoji in other chat apps, from Apple’s iMessage to Facebook’s Messenger to Tencent’s WeChat. This article offers a close examination of LINE to highlight and theorize the process of the “platformization of cultural production.” To do so, it traces Japan’s longer history of platforms going back to the i-mode mobile platform launched in 1999, and examines LINE’s regionally specific sticker-oriented strategies in East Asia. With a focus on the entrepreneurial work of sticker designers as cultural producers, this article also mobilizes LINE to both highlight the specificities of this platform and contest the excessive attention paid to platforms from Silicon Valley, or, at best, their Chinese counterparts. LINE and the regional convergences of super apps in East Asia are a potent reminder of the need to analyze platforms outside of the bi-polar hegemony of the United States versus Chinese tech world—which increasingly frames journalistic discourse and academic research—and of the need to attend to the historical and regional particularities of platforms and their cultural impacts.
The coronavirus disease-19 pandemic introduced a crisis of safety and relevance for dating apps, as their affordances for facilitating in-person encounters posed the risk of viral transmission. This ...article examines how eight apps primarily catering to heterosexual markets responded to the pandemic through changes to socio-technical arrangements, new user prescriptions, and the curation of corporate data and success stories. By analyzing corporate social media and promotional materials alongside in-app developments, we find that these companies reimagined app affordances to promote “virtual dating,” a set of practices and symbolic meanings that prioritize visual, synchronous digital interaction as the most responsible, reliable, and successful dating approach to the pandemic. Virtual dating centers apps as databases of potential partners while prescribing modes of use aimed toward affective relief, displays of authenticity, and romantic courtship. This reimagining counters moral panics about digitally mediated relationships by resorting to heteronormative dating scripts while overlooking alternative app uses.
The high global prevalence of depression, together with the recent acceleration of remote care owing to the COVID-19 pandemic, has prompted increased interest in the efficacy of digital interventions ...for the treatment of depression. We provide a summary of the latest evidence base for digital interventions in the treatment of depression based on the largest study sample to date. A systematic literature search identified 83 studies (N = 15,530) that randomly allocated participants to a digital intervention for depression versus an active or inactive control condition. Overall heterogeneity was very high (I2 = 84%). Using a random-effects multilevel metaregression model, we found a significant medium overall effect size of digital interventions compared with all control conditions (g = .52). Subgroup analyses revealed significant differences between interventions and different control conditions (WLC: g = .70; attention: g = .36; TAU: g = .31), significantly higher effect sizes in interventions that involved human therapeutic guidance (g = .63) compared with self-help interventions (g = .34), and significantly lower effect sizes for effectiveness trials (g = .30) compared with efficacy trials (g = .59). We found no significant difference in outcomes between smartphone-based apps and computer- and Internet-based interventions and no significant difference between human-guided digital interventions and face-to-face psychotherapy for depression, although the number of studies in both comparisons was low. Findings from the current meta-analysis provide evidence for the efficacy and effectiveness of digital interventions for the treatment of depression for a variety of populations. However, reported effect sizes may be exaggerated because of publication bias, and compliance with digital interventions outside of highly controlled settings remains a significant challenge.
Public Significance StatementThis meta-analysis demonstrates the efficacy of digital interventions in the treatment of depression for a variety of populations. Additionally, it highlights that digital interventions may have a valuable role to play in routine care, most notably when accompanied by human guidance. However, compliance with digital interventions remains a major challenge, with little more than 50% of participants completing the full intervention on average.