App Usage Behavior Research Articles

Using Monte Carlo Simulation to Forecast the Scientific Utility of Psychological App Studies: A Tutorial

Mobile applications offer a wide range of opportunities for psychological data collection, such as increased ecological validity and greater acceptance by participants compared to traditional laboratory studies. However, app-based psychological data also pose data-analytic challenges because of the complexities introduced by missingness and interdependence of observations. Consequently, researchers must weigh the advantages and disadvantages of app-based data collection to decide on the scientific utility of their proposed app study. For instance, some studies might only be worthwhile if they provide adequate statistical power. However, the complexity of app data forestalls the use of simple analytic formulas to estimate properties such as power. In this paper, we demonstrate how Monte Carlo simulations can be used to investigate the impact of app usage behavior on the utility of app-based psychological data. We introduce a set of questions to guide simulation implementation and showcase how we answered them for the simulation in the context of the guessing game app Who Knows (Rau et al., 2023). Finally, we give a brief overview of the simulation results and the conclusions we have drawn from them for real-world data generation. Our results can serve as an example of how to use a simulation approach for planning real-world app-based data collection.

Does current pre-experience matter? A study of customer perceived characteristics and MarTech usage behavior of mobile banking application users in Sri Lanka

Purpose: The integration of Marketing Technology (MarTech) in Mobile Banking (MB) apps gains recognition in marketing automation, previous research lacks a comprehensive framework for understanding customer behavior. This study addresses this gap by proposing a new model within Financial Technology (FinTech), incorporating customer characteristics.
 Design/methodology/approach: The Integrated MarTech Usage Behavior Model (IMTUBM) triangulates three theories to explore the MarTech landscape in a longitudinal survey of 400 MB app users in Sri Lanka, utilizing Partial Least Squares Structural Equation Modeling (PLS-SEM) with Smart-PLS software.
 Findings: The resultant Integrated MB App Usage Behavior Model (IMBUBM) provides a foundational understanding of customer characteristics in the MarTech domain. Notably, this study conceptualizes awareness, elucidating that experiential aspects are shaped by both previous and pre-experience.
 Originality: This study introduces the concept of current pre-experience as a moderator in the MarTech landscape within FinTech, arguing for its deeper exploration compared to previous experience. 
 Implications: These findings not only suggest avenues for future research in MarTech but also provide managerial insights, encouraging refinement of strategies based on heightened customer awareness. Additionally, the study emphasizes the importance of current pre-experience in bridging the gap between customer intention and behavior in MarTech usage.
 Keywords: Awareness, Customer characteristics, FinTech organization, MarTech domain, MB app, Pre-experience, Sri Lanka

Analyzing mobile app data demand and usage behavior in Sri Lanka

Owing to the rapid advancement of mobile computing, daily human practices have become more efficient and convenient. Consequently, the number of mobile app users has increased drastically over the last ten years, and a significant amount of energy is consumed by those mobile apps where the energy consumption depends on the data usage of the apps. Therefore, it is important to optimize data consumption to ensure sustainable digitalization. Mobile app personalization is one of the vital areas to optimize the data consumption of mobile apps. In this research, mobile app data usage and user experience data were collected and analyzed quantitatively and qualitatively. The data were collected from 40 Android smartphone users in Sri Lanka. Primarily, semi-structured interviews were conducted to collect qualitative data to identify mobile app usage patterns. In addition, data usage of each mobile app was collected using the in-built data usage tracker in Android smartphones for four months. Descriptive and correlation analyses were used to analyze quantitative data, whereas thematic and content analyses drew insights from the collected qualitative data. Our findings show the most data-demanding mobile app categories in terms of data consumption as social media, video players & editors, and communication. Moreover, users aged between 21 to 30 contribute to the high data consumption in mobile app usage. In addition, qualitative analysis shows that app usage behavior varied during and after the pandemic, and elderly (51-65 years) mobile app users use only a limited number of features from an app.

Digitalization of Loyalty: Impacts of Mobile Technology on Reward Redemption and Engagement Level

ABSTRACT Although digitalization is a prevalent strategy in reward programs, a minimal amount is known regarding the relationship between reward app usage and reward redemption behaviors. The enhanced availability and accessibility of information via mobile app can alter customers’ reward-redemption patterns and engagement level, highlighting the need for firms to adjust their reward-based service strategies. Using unique datasets that reflect individual consumers’ transactional and reward redemption behaviors, we conducted a series of analyses to capture the dynamics in the latent engagement state transitions of customers according to the type of reward program used. Results show that although reward app usage, on average, induces a more active engagement state, it polarizes the volatility of engagement state transitions. Furthermore, we find that greater volatility of engagement state transitions is significantly associated with a higher likelihood of churn. Finally, a follow-up survey and panel vector autoregression analyses are conducted to uncover the mechanisms that underlie the relationship. The results provide insights into how retailers can strategically design their reward programs in the emerging mobile-based omnichannel environment.

Can mobile-health applications contribute to long-term increase in physical activity after medical rehabilitation?-A pilot-study.

Due to the positive effects of rehabilitation declining over time, the aim of this study was to investigate the long-term physical activity level (PAL) following inpatient rehabilitation in relation to the use of a smartphone-based after-care program. 202 patients (mean Body Mass Index (BMI): 30,8 kg/m2; 61% female) with chronic diseases (e.g., diabetes mellitus, obesity, chronic low back pain, depression) were recruited between 08/2020 and 08/2021 in this single-arm observational study. All patients underwent a 3-week inpatient rehabilitation program. PAL (in total activity minutes/week) was measured with a validated (online) questionnaire (Freiburger Questionnaire on PA) after 3, 6, 9, and 12 months. App usage (online time, completion of a course) was recorded automatically and used to evaluate the app user behavior (adherence). A variety of socio-economic factors (age, sex, education level, income etc.) were collected to identify possible barriers of app use. Except for sex, no significant difference was observed for socio-economic factors regarding app usage behavior. Median PAL significantly increased after rehabilitation in the total cohort from 360 min/week (before rehabilitation) to 460 min/week 6 months after rehabilitation, then declined to 420 min/week 9 months after rehabilitation before falling below baseline level after 12 months. There was no significant difference in PAL between app users (45%, 91/202) and non-users (55%, 111/202), although app users tended to retain higher activity levels after 3 and 6 months, respectively. Overall, our study emphasizes the effectiveness of a 3-week rehabilitation program on PAL and the acceptance and usability of a smartphone-based after-care program in this patient group. The adherence to this 3-months after-care app program was acceptable (30%), with modest evidence supporting the effectiveness of app use to sustain PAL in the short term.

Analysis of Application Used on Smartphones

As smartphones have become indispensable personal devices, the number of smartphone users has increased dramatically over the last decade. These personal devices, which are supported by a variety of smartphone apps, allow people to access Internet services in a convenient and ubiquitous manner. App developers and service providers can collect fine-grained app usage traces, revealing connections between users, apps, and smartphones. We present a comprehensive review of the most recent research on smartphone app usage analysis in this survey. Our survey summarizes advanced technologies and key patterns in smartphone app usage behaviors, all of which have significant implications for all relevant stakeholders, including academia and industry. We begin by describing four data collection methods: surveys, monitoring apps, network operators, and app stores, as well as nine publicly available app usage datasets. We then systematically summarize the related studies of app usage analysis in three domains: app domain, user domain, and smartphone domain. We make a detailed taxonomy of the problem studied, the datasets used, the methods used, and the significant results obtained in each domain. Finally, we discuss future directions in this exciting field by highlighting research challenges.

DDHCN: Dual decoder Hyperformer convolutional network for Downstream-Adaptable user representation learning on app usage

In mobile scenarios, there is a need for general user representations to solve multiple target tasks. However, there are some challenges in the related research (e.g., difficulty in learning a representation that satisfies both great generalization and performance). To address these problems, we proposed a network for downstream-adaptable mobile user modeling, which employed a novel fine-tuning strategy for optimizing the performance of several downstream tasks. Additionally, we designed a time-difference module to eliminate the impact of low-frequency and non-uniform app usage behavior over time. A parallel decoder structure was developed to incorporate multi-type features by minimizing information loss. We evaluated our method on a real-world dataset of 100,000 mobile users and three downstream tasks (i.e., age prediction, gender prediction, and app recommendation). The experimental results showed that our method could outperform existing methods significantly. It achieved 96.5% ACC on gender prediction, 68.1% ACC on age prediction, and 64.2% Recall@5 on app recommendation. These results imply that our method performs well on both generalization and performance. It could be anticipated promising to the unseen tasks inference.

A Minimalistic Approach to Predict and Understand the Relation of App Usage with Students' Academic Performance

Due to usage of self-reported data which may contain biasness, the existing studies may not unveil the exact relation between academic grades and app categories such as Video. Additionally, the existing systems' requirement for data of prolonged period to predict grades may not facilitate early intervention to improve it. Thus, we presented an app that retrieves past 7 days' actual app usage data within a second (Mean=0.31s, SD=1.1s). Our analysis on 124 Bangladeshi students' real-time data demonstrates app usage sessions have a significant (p<0.05) negative association with CGPA. However, the Productivity and Books categories have a significant positive association whereas Video has a significant negative association. Moreover, the high and low CGPA holders have significantly different app usage behavior. Leveraging only the instantly accessed data, our machine learning model predicts CGPA within ±0.36 of the actual CGPA. We discuss the design implications that can be potential for students to improve grades.

Learning Dynamic App Usage Graph for Next Mobile App Recommendation

Next mobile app recommendation aims to recommend the next app that a user is most likely to use based on the user's app usage behaviors, which is beneficial for improving user experience, app pre-loading, and system optimization. However, existing works ignore the complex dependencies between apps in the app usage sessions. In addition, they do not consider the dynamics of user interests over time. To address these concerns, we propose a novel model named dynamic usage graph network (DUGN) to recommend the next app that a user is most likely to use. To model the complex dependencies among apps explicitly, we adopt the dynamic graph structure to learn the dynamics of user interests. Firstly, we extract user interests in each app usage graph by using the hierarchical graph attention mechanism. Secondly, we capture user interests evolving over time, and generate the dynamic user embeddings by modeling the temporal dependencies among multiple app usage graphs. Finally, we obtain the current user interests in the current app usage graph, fuse multiple user interests and generate comprehensive user embeddings for next mobile app recommendation. We conduct experiments on real-world datasets. The results show that our model outperforms the state-of-art recommendation methods.

You Are How You Use Apps: User Profiling Based on Spatiotemporal App Usage Behavior

Mobile apps have become an indispensable part of people’s daily lives. Users determine what apps to use and when and where to use them based on their tastes, interests, and personal demands, depending on their personality traits. This article aims to infer user profiles from their spatiotemporal mobile app usage behavior. Specifically, we first transform mobile app usage records into a heterogeneous graph. On the graph, nodes represent users, apps, locations, and time slots. Edges describe the co-occurrence of entities in usage records. We then develop a multi-relational heterogeneous graph attention network (MRel-HGAN), an end-to-end system for user profiling. MRel-HGAN first adopts a neighbor sampling strategy based on bootstrapping to sample heavily connected neighbors of a fixed size for each node. Next, we design a relational graph convolutional operation and a multi-relational attention operation. Through such modules, MRel-HGAN can generate node embedding by sufficiently leveraging the rich semantic information of the multi-relational structure in the mobile app usage graph. Experimental results on real-world mobile app usage datasets show the effectiveness and superiority of our MRel-HGAN in the user profiling task for attributes of gender and age.

The Mediating Role of e-Lifestyles to Use the Fitness Center App

This paper studies the effect of e-Lifestyles on the fitness industry. The aim is to investigate the (mediating) role of e-Lifestyles in the relationship between behavioral intentions to use the fitness center app, app usage behavior, and member overall satisfaction with the fitness center, i.e., explain whether e-Lifestyles allow us to better understand fitness center satisfaction or app usage intention. Results of 1403 members revealed that the relationship between behavioral intentions to use the app and the members’ overall satisfaction with the fitness center is positively mediated by e-Lifestyles. Results further demonstrate that there is a direct positive effect of behavioral usage intentions of the app-on-app usage behavior and overall member satisfaction toward the fitness center. The study adds to the literature on e-Lifestyles by demonstrating its significance in the context of fitness center management. This study helps managers conduct more thorough marketing plans and develop differentiated strategies and provides information for app designers.

ATPP : A Mobile App Prediction System Based on Deep Marked Temporal Point Processes

Predicting the next application (app) a user will open is essential for improving the user experience, e.g., app pre-loading and app recommendation. Unlike previous solutions that only predict which app the user will open, this article predicts both the next app and the time to open it. Time prediction is essential to avoid loading the next app too early and consuming unnecessary resources on smartphones. To predict the next app and open time jointly, we model the app usage sequence as a marked temporal point process (MTPP), whose conditional intensity function can capture the probability of a new app usage event. We develop a novel data-driven MTPP-based app prediction system, named ATPP (App Temporal Point Process), which adopts a recurrent neural network architecture to learn the MTPP conditional intensity function for app prediction. ATPP adopts a set of techniques to incorporate the unique features of app prediction in our RNN architecture, including learning the correlated usage behavior of different apps by representation learning, the temporal dependency of app usage by an attention mechanism, and the location-related app usage behavior by feature extraction and fusion layer. We conduct extensive experiments on a large-scale anonymized app usage dataset to verify ATPP’s effectiveness.

TikTok app usage behavior: the role of hedonic consumption experiences

PurposeTikTok social media app has become one of the most popular forms of leisure and entertainment activities, but how hedonic consumption experiences (comprising fantasy, escapism, enjoyment, role projection, sensory, arousal and emotional involvement) of the TikTok app determine users' intention to use the app and its resulting impact on the actual usage behavior remains limited in the information systems literature, especially featuring the hedonic consumption perspective in entertainment industry.Design/methodology/approachThis study employs uses & gratification theory to answer the “why” via predicting the role of hedonic consumption experiences that serve as gratifications to trigger technology acceptance behavior (especially, in form of users' behavioral intention to use the TikTok app and its further impact on usage behavior). This study utilizes the partial least squares-structural equation modeling approach to perform data analyses on 258 TikTok app users.FindingsOur results provide a strong support such that users' playful consumption experiences (i.e. escapism, role projection, arousal, sensory experience and enjoyment) positively influence their intention to use the TikTok app and its resultant effect on users' actual usage of the app. In contrast, fantasy and emotional involvement fail to influence users' intention to use the TikTok app.Originality/valueTo the best of our knowledge, our investigation is one of the first studies to apply the hedonic consumption experiences as potential gratifications that derive users' intention and its subsequent influence on the actual usage of the TikTok app. Our study results would assist marketing and brand managers to redefine approaches and tactics to create effective strategies that implement essential determinants to increase behavioral intention among entertainment service providers.

DeepAPP: A Deep Reinforcement Learning Framework for Mobile Application Usage Prediction

This paper aims to predict a set of apps a user will open on her mobile device in the next time slot. Such an information is essential for many smartphone operations, e.g., app pre-loading and content pre-caching, to improve user experience. However, it is hard to build an explicit model that accurately captures the complex environment context and predicts a set of apps at one time. This paper presents a deep reinforcement learning framework, named as DeepAPP, which learns a model-free predictive neural network from historical app usage data. Meanwhile, an online updating strategy is designed to adapt the predictive network to the time-varying app usage behavior. To transform DeepAPP into a practical deep reinforcement learning system, several challenges are addressed by developing a context representation method for complex contextual environment, a general agent for overcoming data sparsity and a lightweight personalized agent for minimizing the prediction time. Extensive experiments on a large-scale anonymized app usage dataset reveal that DeepAPP provides high accuracy (precision 70.6 percent and recall of 62.4 percent) and reduces the prediction time of the state-of-the-art by 6.58×. A field experiment of 29 participants demonstrates DeepAPP can effectively reduce launch time of apps.

Reidentification Risk in Panel Data: Protecting fork-Anonymity

Market research companies collect extensive data on purchasing, travel, and app and media usage behaviors of consumers, prescriptions written by physicians, and so forth. Although the companies provide assurances of anonymity to the study participants, there is a significant concern about the vulnerability of these data. Could a motivated intruder match the pattern of purchases with the name and other personal and potentially sensitive details of an individual? We find that 17% to 94% of market research panelists in 15 frequently bought consumer goods categories are subject to high risk of reidentification through a potential record linkage attack based on their unique purchasing histories even when their identities are anonymized. We also demonstrate that the risk of reidentification in such data are vastly understated by the conventional measure, unicity, and propose a new measure, termed “sno-unicity.” To protect the privacy of panelists, we consider the well-known privacy notion of k-anonymity and develop a new approach called “graph-based minimum movement k-anonymization” that is designed especially for retaining the usefulness of panel data. We show that our approach works well in protecting participants’ privacy without substantially altering the information that marketers need for sound marketing decisions.

Analysis of Salesperson Behavior on Using Retailer App (Case Study: Indosat Ooredoo Hutchison)

The evolution of information technology affects many organizations in Indonesia, especially telco companies. Indosat Ooredoo Hutchison or more commonly known as PT Indosat, Tbk. or Indosat, a telco company in Indonesia has implemented a mobile application called Simpel for use by the salespeople to sell products. Currently, the app has been used by 60% of the users for less than 10 transactions in a month which resulted in only 9% of total revenue generated by the retailer app. This occurrence gave a challenge for Indosat to manage and increase the transaction count in the aforesaid app. This study aimed to analyze the factors influencing a salesperson’s decision to more frequently use Simpel to sell products. Every telco company can learn from this research to enhance app features better. The analysis is based on human behavior in information systems environment. The combination of UTAUT and other variables was used in this study. The total sample was obtained from 467 respondents who registered and used the app. Analysis were conducted using the structural equation models to learn the impact that performance expectancies, effort expectancies, social influence, facilitation conditions, and quality of sales applications have towards behavioral intention to use mobile app; and to learn the impact of behavioral intention, social influence, and facilitating conditions towards improving the sales app usage behavior.

COVID-19 Paradox: The Role of Privacy Concerns and Ad Intrusiveness on Consumer's Attitude Toward App Usage Behavior.

The COVID-19 pandemic has changed lives in an unprecedented way. The most notable and urgent requirement to combat the epidemic was to transform the way human interacts with each other. The adherence to maintaining social distance has given an upsurge to the increased usage of mobile app users. This change in human interaction for fulling their basic to social to work needs through the intervention of app usage has led to privacy concerns by users. By keeping in view the changing dynamics of the way society works, this study is an endeavor to investigate gender differences of ad intrusive and privacy concerns on app usage behavior. Employing a quantitative research design, 371 respondents were surveyed using through an online structured questionnaire. Data were analyzed by using partial least square structural equation modeling (PLS-SEM). Results suggest that advertising intrusiveness and privacy concerns are significant in determining the consumer’s attitude toward App usage, and a positive attitude toward App usage results in App usage behavior. However, gender’s moderating role in attitude toward app usage and app usage behavior is insignificant for this study. The study provides a more comprehensive understanding and complements prior insights on ads intrusiveness and privacy concerns toward app usage.

Smartphone App Usage Analysis: Datasets, Methods, and Applications

As smartphones have become indispensable personal devices, the number of smartphone users has increased dramatically over the last decade. These personal devices, which are supported by a variety of smartphone apps, allow people to access Internet services in a convenient and ubiquitous manner. App developers and service providers can collect fine-grained app usage traces, revealing connections between users, apps, and smartphones. We present a comprehensive review of the most recent research on smartphone app usage analysis in this survey. Our survey summarizes advanced technologies and key patterns in smartphone app usage behaviors, all of which have significant implications for all relevant stakeholders, including academia and industry. We begin by describing four data collection methods: surveys, monitoring apps, network operators, and app stores, as well as nine publicly available app usage datasets. We then systematically summarize the related studies of app usage analysis in three domains: app domain, user domain, and smartphone domain. We make a detailed taxonomy of the problem studied, the datasets used, the methods used, and the significant results obtained in each domain. Finally, we discuss future directions in this exciting field by highlighting research challenges.

Examining the role of consumer impulsiveness in multiple app usage behavior among mobile shoppers

Building on the stimulus-organism-response (S-O-R) theory, this study identifies and empirically tests the prominence of various technology-related, consumer characteristics, and situational variables (Stimuli) on fostering impulsive habits among mobile shoppers. We further examine the direct and indirect effects of consumer impulsiveness on the use of multiple shopping applications for online purchases. Data collected from 275 mobile shopping application (app) users through an online survey were analyzed using partial least square structural equation modeling (PLS-SEM). Results confirm the significant impact of mobility, personalization, product assortment, and hedonic motivation on impulsiveness, except the app's visual appeal. Impulsiveness was found to be strongly correlated with users' intention to install another shopping app, whereas consumers behavioral intention was a significant precursor of their multiple app usage behavior. The findings apprise managers of the role of impulsiveness in encouraging split loyalty among mobile shoppers and prescribe new strategies for sustained use of shopping platforms.

Factors Affecting User\u2019s Behavioral Intention and Use of a Mobile-Phone-Delivered Cognitive Behavioral Therapy for Insomnia: A Small-Scale UTAUT Analysis

A mobile app could be a powerful medium for providing individual support for cognitive behavioral therapy (CBT), as well as facilitating therapy adherence. Little is known about factors that may explain the acceptance and uptake of such applications. This study, therefore, examines factors from an extended version of the Unified Theory of Acceptance and Use of Technology (UTAUT2) model to explain variation between people’s behavioral intention to use a CBT for insomnia (CBT-I) app and their use-behavior. The model includes eight aspects of behavioral intention: performance expectancy, effort expectancy, social influence, self-efficacy, trust, hedonic motivation, anxiety, and facilitating conditions, and investigates further the influence of the behavioral intention and facilitating conditions on app-usage behavior. Data were gathered from a field trial involving people (n = 89) with relatively mild insomnia using a CBT-I app. The analysis applied the Partial Least Squares-Structural Equation Modeling method. The results found that performance expectancy, effort expectancy, social influence, self-efficacy, trust, and facilitating conditions all explained part of the variation in behavioral intention, but not beyond the explanation provided by hedonic motivation, which accounted for R2 = 0.61. Both behavioral intention and facilitating conditions could explain the use-behavior (R2 = 0.32). We anticipate that the findings will help researchers and developers to focus on: (1) users’ positive feelings about the app as this was an indicator of their acceptance of the mobile app and usage; and (2) the availability of resources and support as this also correlated with the technology use.