Predicting numeric ratings for Google apps using text features and ensemble learning

Application (app) ratings are feedback provided voluntarily by users and serve as important evaluation criteria for apps. However, these ratings can often be biased owing to insufficient or missing votes. Additionally, significant differences have been observed between numeric ratings and user reviews. This study aims to predict the numeric ratings of Google apps using machine learning classifiers. It exploits numeric app ratings provided by users as training data and returns authentic mobile app ratings by analyzing user reviews. An ensemble learning model is proposed for this purpose that considers term frequency/inverse document frequency (TF/IDF) features. Three TF/IDF features, including unigrams, bigrams, and trigrams, were used. The dataset was scraped from the Google Play store, extracting data from 14 different app categories. Biased and unbiased user ratings were discriminated using TextBlob analysis to formulate the ground truth, from which the classifier prediction accuracy was then evaluated. The results demonstrate the high potential for machine learning-based classifiers to predict authentic numeric ratings based on actual user reviews.     

Smartphone user segmentation based on app usage sequence with neural networks

The term user segmentation refers to classifying users into groups depending on their specific needs, characteristics, or behaviors. It is a key element of product development and marketing in many industries, such as the smartphone industry, which employs user segmentation to gather information about usage logs, to produce new products for such specific groups of users. However, previous studies on smartphone user segmentation have been primarily based on demographics and reported usage, which are inherently subjective and prone to skew by the observers and participants. Hamka et al. (2014) was the first to conduct a study, in which smartphone user segmentation was performed using log data collected through smartphone measurements. However, they focused only on network usage and the number of apps used, and not on characteristics or preferences. In this study, we proposed novel ways of segmenting smartphone users based on app usage sequences collected from smartphone logs. We proposed a variant of seq2seq architecture combining the advantages of previous deep neural networks: neural embedding architecture and seq2seq architecture. Furthermore, we compared the user segmentation results of the proposed method with an answer set of segmentation results conducted by domain experts. These experiments demonstrated that the proposed method effectively determines similarities between usage sequences and outperforms existing user segmentation methods.     

Systematic evaluation of mobile fitness apps: Apps as the Tutor,Recorder, Game Companion,and Cheerleader

Mobile fitness applications are innovating the ways in which smartphone users self-manage their health. Prior research found that app functions may impact app efficacy. However, research to date has not sought to systematically investigate how different combinations of app functions impact user response to apps, especially adoption intent. This article describes two studies on mobile fitness app characteristics and user attitudes. Study One used content analysis and hierarchical cluster analysis on 98 iPhone fitness apps and identified four app clusters: “Tutor”, “Recorder”, “Game Companion”, and “Cheerleader.” Tracking was the predominant function in current market, but tracking-focused Recorder apps received lowest user ratings among all app clusters. Users favored Tutor apps that combine exercise education and tracking, and Game Companion apps that combine gamification, tracking, and social functions. Function combinations, rather than standalone functions, impact app success. Following a Reasoned Action Approach, Study Two found various effects of individual differences (age, gender, BMI, eHealth literacy, smartphone experience, function preference) on user attitude toward different fitness app types. A comparison between two studies demonstrated a mismatch between market offerings and user needs regarding app functions. Implications of results for mobile fitness app design to improve consumer health and for theories are discussed.     

A data reduction scheme for active authentication of legitimate smartphone owner using informative apps ranking

Smartphones are vulnerable to fraudulent use despite having strong authentication mechanisms. Active authentication based on behavioral biometrics is a solution to protect the privacy of data in smart devices. Machine-learning-based frameworks are effective for active authentication. However, the success of any machine-learning-based techniques depends highly on the relevancy of the data in hand for training. In addition, the training time should be very efficient. Keeping in view both issues, we’ve explored a novel fraudulent user detection method based solely on the app usage patterns of legitimate users. We hypothesized that every user has a unique pattern hidden in his/her usage of apps. Motivated by this observation, we’ve designed a way to obtain training data, which can be used by any machine learning model for effective authentication. To achieve better accuracy with reduced training time, we removed data instances related to any specific user from the training samples which did not contain any apps from the user-specific priority list. An information theoretic app ranking scheme was used to prepare a user-targeted apps priority list. Predictability of each instance related to a candidate app was calculated by using a knockout approach. Finally, a weighted rank was calculated for each app specific to every user. Instances with low ranked apps were removed to derive the reduced training set. Two datasets as well as seven classifiers for experimentation revealed that our reduced training data significantly lowered the prediction error rates in the context of classifying the legitimate user of a smartphone.     

AdaptiveMutate: a technique for privacy preservation

Mobile apps are known to be rich sources for gathering privacy-sensitive information about smartphone users. Despite the presence of encryption, passive network adversaries who have access to the network infrastructure can eavesdrop on the traffic and therefore fingerprint a user’s app by means of packet-level traffic analysis. Since it is difficult to prevent the adversaries from accessing the network, providing secrecy in hostile environments becomes a serious concern.In this study, we propose AdaptiveMutate, a privacy-leak thwarting technique to defend against the statistical traffic analysis of apps. First, we present a method for the identification of mobile apps using traffic analysis. Further, we propose a confusion system in which we obfuscate packet lengths, and/or inter-arrival time information leaked by the mobile traffic to make it hard for intruders to differentiate between the altered app traffic and the actual one using statistical analysis. Our aim is to shape one class of app traffic to obscure its features with the minimum overhead. Our system strives to dynamically maximize its efficiency by matching each app with the corresponding most dissimilar app. Also, AdaptiveMutate has an adaptive capability that allows it to choose the most suitable feature to mutate, depending on the type of apps analyzed and the classifier used, if known.We evaluate the efficiency of our model by conducting a comprehensive simulation analysis that mutates different apps to each other using AdaptiveMutate. We conclude that our algorithm is most efficient when we mutate a feature of one app to its most dissimilar one in another app. When applying the identification technique, we achieve a classification accuracy of 91.1%. Then, using our obfuscation technique, we are able to reduce this accuracy to 7%. Also, we test our algorithm against a recently published approach for mobile apps classification and we are able to reduce its accuracy from 94.8% to 17.9%. Additionally, we analyze the tradeoff between the shaping cost and traffic privacy protection, specifically, the associated overhead and the feasibility for real-time implementation.     

Mobile apps usage and dynamic capabilities: A structural equation model of SMEs in Lagos,Nigeria

Significant knowledge exists regarding the application of dynamic capability (DC) frameworks in large firms, but their impact on smaller organisations is yet to be fully researched. This study surveyed 1162 small and medium sized enterprises (SMEs) in Lagos in an effort to understand how SMEs in developing country contexts use mobile apps to enhance their businesses through DCs. Through the use of the covariance-based structural equation modelling (SEM) technique, the study explored the fitness of a conceptual formative model for SMEs. The model assembled 7 latent variables namely: mobile app usage, adaptive capability, absorptive capability, innovative capability, opportunity sensing ability, opportunity shaping ability and opportunity seizing ability. Subsequently, 15 hypotheses aimed at testing the relationships between the latent variables were developed and tested. The findings revealed that mobile app usage increases the adaptive, absorptive and innovative capabilities of SMEs. Absorptive capabilities help SMEs to maximise opportunities, while innovative capabilities negatively influence SMEs’ tendency to maximise opportunities. The results failed to establish a direct relationship between mobile app usage and SMEs’ ability to maximise opportunities. The research outcomes indicate that SMEs in Lagos respond to opportunities innovatively but they seldom exhibit innovation in order to create opportunities. The heterogeneous nature of SMEs complicates any clear-cut narrative as to how SMEs in Lagos should employ mobile apps to create and maximise opportunities. However, mobile apps could induce innovation and, as such, impact significantly when developed and applied to the contextual requirements of SMEs. The research revealed the untapped potential of SMEs’ mobile app usage in Lagos.     

Untangling the effect of cognitive trust and perceived value on health-related information seeking,sharing and psychological well-being: Motivations sought perspective

Previous literature has documented that mobile application utilization increased exponentially throughout the ongoing COVID-19 epidemic. To comprehend the possible antecedents of individuals’ psychological well-being, this research invokes motivation theory and associated literature on perceived assessment (cognitive trust, perceived value, and perceived threat) to comprehensively investigate the determinants of factors influencing mobile app users’ health-related information behaviors and psychological outcomes. Data were gathered collected from 898 users of mobile apps, and this article adopted structural equation modeling (SEM) to evaluate the hypothesis generation model. Obtained findings demonstrated that cognitive trust and perceived value positively impacted seeking and sharing health-related information, which subsequently benefited individuals’ psychological well-being during the public health crisis. Furthermore, perceived threat exerted a negative impact on seeking and sharing health-related information. These results contribute to existing studies on psychological well-being by broadening the antecedence domain of information practices and revealing the underlying psychological mechanism behind this dynamic process. This study could also benefit practitioners by providing insights into embedded system and mobile app development, which would play a pivotal role in enhancing user experiences that optimize psychological well-being.     

Religion-focused dating apps: A Q methodology study on the uses of mutual

Dating apps have become an increasingly viable option for individuals seeking interpersonal romantic relationships. While there is significant research regarding user motivation on dating apps such as Bumble, Tinder, and Match.com, there is no published research that discusses the motivations of Mutual app users. Developed as a dating app to target members of The Church of Jesus Christ of Latter-Day Saints, Mutual allows users to find potential mates who share their religious background and specify their relationship readiness (from “Into Dating I Guess” to “Ready for a Ring”). This research aims to illuminate the various motivations, attitudes, and opinions of Mutual app users through Q methodology, which identifies perceptual groups among homogeneous populations through a factor analysis of participants’ agreement with similar statements regarding Mutual use. Findings indicated four factor groups: the Relationship Readies (i.e., those serious about dating), the Swipeaholics (i.e., those looking for entertainment), the Faithless (i.e., those who felt pressured to use Mutual), and the Eligible Optimists (i.e., those who saw the app as a convenient, entertaining way to date). Different from other research on dating apps, this study indicates that people may use a niche religion-focused dating app to find individuals with similar moral values or due to external pressure from others. Results warrant further investigation into niche dating apps.     

Repackaging Attack on Android Banking Applications and Its Countermeasures

Although anyone can easily publish Android applications (or apps) in an app marketplace according to an open policy, decompiling the apps is also easy due to the structural characteristics of the app building process, making them very vulnerable to forgery or modification attacks. In particular, users may suffer direct financial loss if this vulnerability is exploited in security-critical private and business applications, such as online banking. In this paper, some of the major Android-based smartphone banking apps in Korea being distributed on either the Android Market or the third party market were tested to verify whether a money transfer could be made to an unintended recipient. The experimental results with real Android banking apps showed that an attack of this kind is possible without having to illegally obtain any of the sender’s personal information, such as the senders public key certificate, the password to their bank account, or their security card. In addition, the cause of this vulnerability is analyzed and some technical countermeasures are discussed.     

A Mobile App Search Engine

With the popularity of mobile apps on mobile devices based on iOS, Android, Blackberry and Windows Phone operating systems, the numbers of mobile apps in each of the respective native app stores are increasing in leaps and bounds. Currently there are close to one million mobile apps across these four major native app stores. Due to the enormous number of apps, both the constituents in the app ecosytem, consumers and app developers, face problems in ‘app discovery’. For consumers, it is a daunting task to discover the apps they like and need among the huge number of available apps. Likewise, for developers, enabling their apps to be discovered is a challenge. To address these issues, Mobilewalla (MW) an app search engine provides an independent unbiased search for mobile apps with semantic search capabilities. It has also developed an objective scoring mechanism based on user and developer involvement with an app. The scoring mechanism enables MW to provide a number of other ways to discover apps—such as dynamically maintained ‘hot’ lists and ‘fast rising’ lists. In this paper, we describe the challenges of developing the MW platform and how these challenges have been mitigated. Lastly, we demonstrate some of the key functionalities of MW.     

Mobile city applications for Brussels citizens: Smart City trends,challenges and a reality check

This article combines quantitative and qualitative methods to take a first look at the app economy and mobile services landscape in the City and Region of Brussels, capital of Belgium and Europe. By scraping the iTunes App Store and Google Play market places we get a view on platform distribution, pricing, public vs. commercial, adoption, appreciation and popular categories of Brussels apps aimed at citizens, as well as a view on the app economy in the city. This data is then complemented by qualitative expert interviews with actors in the field, such as cities, interest groups and developers. In the context of the current debate surrounding what constitutes a Smart City and the importance of smartphones and mobile in this area, we perform a reality check, using Brussels as a case. We find that the laggard position Brussels is currently in could be an opportunity to leapfrog in the field of mobile services, but that a focused vision and clear mobile strategy, while thinking of the city as a local innovation platform built on open data, is quintessential to achieving this.     

Identifying relevant segments of AI applications adopters – Expanding the UTAUT2’s variables

Artificial intelligence (AI) is a future-defining technology, and AI applications are becoming mainstream in the developed world. Many consumers are adopting and using AI-based apps, devices, and services in their everyday lives. However, research examining consumer behavior in using AI apps is scant. We examine critical factors in AI app adoption by extending and validating a well-established unified theory of adoption and use of technology, UTAUT2. We also explore the possibility of unobserved heterogeneity in consumers’ behavior, including potentially relevant segments of AI app adopters. To augment the knowledge of end users’ engagement and relevant segments, we have added two new antecedent variables into UTAUT2: technology fear and consumer trust. Prediction-orientated segmentation was used on 740 valid responses collected using a pre-tested survey instrument. The results show five segments with different behaviors that were influenced by the variables of the proposed model. Once known, the profiles were used to propose apps to AI developers to improve consumer engagement. The moderating effects of the added variables—technology fear and consumer trust—are also shown. Finally, we discuss the theoretical and managerial implications of our findings and propose priorities for future research.     

Facilitation of consumer loyalty toward branded applications: The dual-route perspective

Although many brands develop mobile applications (apps) to build relationships with consumers, most branded apps fail to retain consumers’ loyalty. This study examines the facilitation of consumer loyalty toward branded apps (continuance intention, in-app purchase intention, and word-of-mouth intention) from the dual-route perspective. One route is the affective (relationship) route, where brand benefits (functional benefits, experiential benefits, symbolic benefits, and monetary benefits) drive parasocial interactions between consumers and the brand, which, in turn, influences branded app loyalty. The other route is the utility route, where system characteristics (system quality and information quality) affect perceived usefulness, which, in turn, facilitates branded app loyalty. An online survey was conducted, and the research model was empirically tested using partial least squares structural equation modeling. The findings support the dual-route perspective according to which both affective and utilitarian paths facilitate branded app loyalty. The key theoretical contribution of this study is that it moves beyond the utilitarian path and finds the affective (relationship) path to give a more complete picture of the facilitation of consumer loyalty in the branded app context. A strategy is provided to suggest to practitioners how to design branded apps to facilitate consumer loyalty.     

Privacy Perception when Using Smartphone Applications

Our smartphone is full of applications and data that analytically organize, facilitate and describe our lives. We install applications for the most varied reasons, to inform us, to have fun and for work, but, unfortunately, we often install them without reading the terms and conditions of use. The result is that our privacy is increasingly at risk. Considering this scenario, in this paper, we analyze the user’s perception towards privacy while using smartphone applications. In particular, we formulate two different hypotheses: 1) the perception of privacy is influenced by the knowledge of the data used by the installed applications; 2) applications access to much more data than they need. The study is based on two questionnaires (within-subject experiments with 200 volunteers) and on the lists of installed apps (30 volunteers). Results show a widespread abuse of data related to location, personal contacts, camera, Wi-Fi network list, running apps list, and vibration. An in-depth analysis shows that some features are more relevant to certain groups of users (e.g., adults are mainly worried about contacts and Wi-Fi connection lists; iOS users are sensitive to smartphone vibration; female participants are worried about possible misuse of the smartphone camera).

     

Irreplaceable: the role of place information in a location based service

Location is no longer only a backdrop of mobile device usage, as current location-based services (LBS) can customise content based on a user's geographic position. The application Foursquare has emerged as a leading commercial LBS. One of the first LBS to reach a large, global audience, Foursquare features geosocial networking, place listings, user reviews and recommendations. With physical place as the organising concept of the application, Foursquare combines locative technology with social media features to give users the ability to interact with place by writing place reviews, uploading photos or creating place listings into its database. The application enables users to access, create and share geographically relevant information in ways that would have been difficult before the advent of locative media. To explore how people were using LBS in relation to their places, a small-scale ethnographic study of Foursquare users was conducted using interviews, remote observation and contextual inquiry. The findings of the study indicate that Foursquare users sought, appreciated and made creative use of the application's geographically relevant place information.     

Download or swipe left: The role of complexity,future-oriented emotions and feature overload

With the intense competition in the mobile applications (apps) market, it is imperative for app providers to understand how visual stimuli from their apps can create a positive first impression and enhance the app download rates. In the present study, the mechanism through which visual complexity influences mobile app download intention is examined. Using a combination of convenience and snowball sampling, 218 participants were recruited to take part in a single-group post-test only quasi-experimental design. The findings of the study showed that visual complexity influences mobile app download intentions through the mediating role of two future-oriented emotions (i.e. hope and anticipated regret). Additionally, the study showed that the indirect effect of visual complexity on download intentions was moderated by feature overload with the importance of visual complexity significantly reducing as perceptions of feature overload increases. The proposed model explained 46% variance in the intentions to download a mobile app. The findings not only provide practical insights for mobile app developers and publishers but also theoretical insights on consumer decision making in the pre-use context of mobile apps.     

Facebook ads not working in the same way: The effect of cultural orientation and message construals on consumer response to social media ads

The research examined the impacts of psychological distance and message type on social media by cultural orientation. This research assessed social media usage and construal levels on Facebook pages in two cultures (Individualism – the U.S. vs. Collectivism – South Korea). While the U.S. participants had different levels of construals in two Facebook pages (News Feed vs. Timeline), the Korean participants did not. Further, the results demonstrated that for U.S. Facebook users, the different distances from the two Facebook pages impact their evaluation of ad messages framed with different construal terms: In News Feed that U.S. users feel distant from, an ad message framed with high construal terms (vs. low construal terms) was more effective. In Timeline that U.S. users feel proximal to, an ad message focusing on low construal terms (vs. high construal terms) led to more favorable response. However, Korean Facebook users did not exhibit varying psychological distances from those two Facebook pages. Rather, they consistently preferred high-level construal messages regardless of where the ad messages were posted. The importance of this study is the suggestion that cultural orientation and social media usage need to be considered for the development of particular ad messages that engage social media users across the globe.     

基于情境感知的人体经络个性化信息服务研究

由于人体经络系统较为复杂,包含经络、穴位、疾病、脏腑及针灸等方面的大量知识信息,同时用户往往由于兴趣、目的及环境的不同而有不同的信息需求,用户不能有针对性地获取所需的信息。为了增强人体经络系统信息服务的个性化,提高用户的学习效率和使用兴趣,将普适计算中的情境感知计算引入到人体经络系统的个性化信息服务中,应用普适计算、图形图像等先进技术,建立起能够感知用户行为的人体经络系统,为经络的学习和研究提供一种直观便捷的有力工具,同时也为电子商务、信息检索、文献分类和多媒体推荐等领域中的个性化信息服务的研究及应用提供了新的思路。     

运用XD与HBuilderX在Android平台的智能手机App设计及应用

随着智能手机时代的到来,大多数人的生活方式已经改变,如今,智能手机已成为人们工作的一部分,并在他们的工作中起着重要作用。作为移动互联网行业的关键领域,智能手机在互联网行业中变得越来越重要。人们一直在密切关注智能手机App设计的用户体验。以智能手机App为核心的用户体验构建设计是智能手机应用程序设计的核心和关键点,也是使得用户需求得以满足的重要方式。智能手机App的存在时间相对较短。其开发过程缺少完整的设计过程和理论支持。如何给用户提供良好体验的App设计就显得非常重要。针对此问题,一方面,需要从逻辑设计入手考虑用户体验。另一方面,通过调查来分析用户体验,进行有效的图形设计。在手机App层出不穷的新时期,要合理设计智能手机的应用程序,以增强用户体验。     

Enhancing customer loyalty to mobile instant messaging: Perspectives of network effect and self-determination theories

Mobile instant messaging (MIM) apps are popular information and communication technologies (ICTs). As known for ICTs, network effect variables such as perceived network size and perceived complementarity are important for determining user loyalty. However, there is insufficient research on why they are determinants, i.e., knowing the underlying mechanism. Grounded in network effect and self-determination theories, we study such underlying mechanism. Based on an analysis of responses from an online survey of 292 participants using structural equation modelling, we find that the network effect variables of perceived network size and perceived complementarity are positively related to three user-perceived values, namely user-perceived functional, self-expressive, and social values. They are, in turn, positively related to satisfaction of the needs for competence, autonomy, and relatedness, respectively, that further leads to user loyalty. This study contributes to the MIM literature by being the first to use the three user-perceived values and satisfaction of the three needs as novel process variables to construct a model for explaining the impacts of network effect variables on user loyalty to MIM apps. This study provides the insight that MIM providers can more effectively enhance user loyalty by providing the three values that users appreciate and satisfying the three needs, when increasing and advertising their network sizes and availability of complementary offerings.