Mobile App Recommendation Research Articles

User-selectable interaction and privacy features in mobile app recommendation (MAR)

User-selectable interaction and privacy features in mobile app recommendation (MAR)

Heterogeneous Convolutional Neural Networks for Emotion Recognition Combined with Multimodal Factorised Bilinear Pooling and Mobile Application Recommendation

The field of emotion recognition has garnered considerable interest due to its diverse applications in mental health, personalised advertising and enhancing user experiences. This research paper introduces a unique and innovative method for emotion recognition by integrating heterogeneous convolutional neural networks (CNNs) with multimodal factorised bilinear pooling. Furthermore, the paper also incorporates the integration of mobile application recommendations as part of the overall approach. The proposed method leverages the power of CNNs to extract high-level features from different modalities, including facial expressions, speech signals and physiological signals. By using heterogeneous CNNs, each modality is processed independently to capture modality-specific emotional cues effectively. To fuse the extracted features, multimodal factorised bilinear pooling is employed, which captures the complex interactions between different modalities while reducing the computational complexity. This pooling technique efficiently combines the modality-specific features, resulting in a compact and discriminative representation of the emotional state. In addition to emotion recognition, this paper also introduces the integration of mobile app recommendations. By leveraging the recognised emotion, the system recommends relevant mobile applications that are tailored to the user’s emotional state. This integration enhances user experience and facilitates emotion regulation through the utilisation of appropriate mobile apps. Experimental evaluations are conducted on benchmark emotion recognition datasets, including the DEAP and MAHNOB_HCI datasets. The findings of the study highlight the effectiveness of the proposed methodology in terms of accuracy and robustness, surpassing existing approaches in the field. Additionally, the integration of the mobile app recommendation system showcases encouraging outcomes by offering personalised recommendations tailored to the user’s emotional state.

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.

A deep multi-embedding model for mobile application recommendation

With the explosion in the number of mobile applications, it becomes difficult and time-consuming for users to find the most suitable and interesting application from the millions of applications that exist today. Therefore, mobile app recommendation becomes a top priority to help people solve this problem. In previous studies, there are two common methods to solve this problem, one is to apply matrix factorization to the rating data to predict the target user's ratings for other applications, and the other is to predict ratings based on the user's review text. In addition to combining the above two traditional methods, this study also combines deep learning methods to generate better models. For rating data, we use a deep matrix factorization method to obtain latent factor vectors of users and items from the rating matrix to improve the embedding of ratings. For review text, we improve the text representation by using a multi-embedding approach. Most importantly, our model also incorporates deep neural networks with nonlinear transformation capabilities to extract more representative abstract features. We conduct experiments on datasets collected from the real world. Extensive experimental results show that our proposed method has better performance than other existing methods.

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.

Data usage-based privacy and security issues in mobile app recommendation (MAR): a systematic literature review

PurposeSimilarly, Zhu et al. (2014) and Zhang et al. (2014) stated that addressing privacy concerns with the recommendation process is necessary for the healthy development of app recommendation. Recently, Xiao et al. (2020) mentioned that a lack of effective privacy policy hinders the development of personalized recommendation services. According to the reported work, privacy protection technology methods are too limited for mobile focusing on data encryption, anonymity, disturbance, elimination of redundant data to protect the recommendation process from privacy breaches. So, this situation motivated us to conduct a systematic literature review (SLR) to provide the viewpoint of privacy and security concerns as mentioned in current state-of-the-art in the mobile app recommendation domain.Design/methodology/approachIn this work, the authors have followed Kitchenham guidelines (Kitchenham and Charters, 2007) to devise the SLR process. According to the guidelines, the SLR process has three main phases: (1) define, (2) conduct the search and (3) report the results. Furthermore, the authors used systematic mapping approach as well to ensure the whole process.FindingsBased on the selected studies, the authors proposed three main thematic taxonomies, including architectural style, security and privacy strategies, and user-usage in the mobile app recommendation domain. From the studies' synthesis viewpoint, it is observed that the majority of the research efforts have focused on the movie recommendation field, while the mainly used privacy scheme is homomorphic encryption. Finally, the authors suggested a set of future research dimensions useful for the potential researchers interested to perform the research in the mobile app recommendation domain.Originality/valueThis is an SLR article, based on existing published research, where the authors identified key issues and future directions.

Incorporating contextual information into personalized mobile applications recommendation

With the rise of the mobile Internet, the number of mobile applications (apps) has shown explosive growth, which directly leads to the apps data overload. Currently, the recommender system has become the most effective method to solve the app data overload. However, most of the existing recommended methods for apps ignore the app functional exclusiveness features, which makes it difficult to further improve the app recommendation performance. To solve this problem, we propose a personalized context-aware mobile app recommendation approach, called PCMARA. Specifically, (1) PCMARA explores the relationship between contextual information and function of apps and constructs the app contextual factors for app which represent the function of app. (2) PCMARA leverages the app contextual factor to design a novel app similarity model, which enable to effectively eliminate the adverse effects that ignore the app functional exclusiveness. (3) PCMARA comprehensively considers the contextual information of users and apps to generate a recommendation list for users based on the target users’ current time and location. We applied the PCMARA to a real-world dataset and conducted a large-scale recommendation effect experiment. The experimental results demonstrate the superiority of PMARA over the benchmark methods.

The value of visual quality and service quality to augmented reality enabled mobile shopping experience

This study demonstrates that visual quality is an emergent factor in explaining behavioral intention in online shopping, as online retail technology continues to evolve. The researchers develop, and test a model, in augmented reality (AR) and non-AR contexts, explaining the effect of aesthetic appeal of the interface of a mobile retail app and position relevance of a product in the user environment on visual quality of the app. The model explains the influence of visual and service quality on user satisfaction toward the app and the influence of user satisfaction on recommendation intention. The data were collected from 102 mobile app users who were asked to use the view-in-room features on a mobile augmented reality (MAR) app. Another group of 155 mobile app users were requested to search for a product using a typical mobile app search interface. Both groups provided their responses via an online survey. The researchers used partial least squares structural equation modeling (PLS-SEM) to analyze the collected data. Results indicate that the model has superior explanatory power when applied to an AR context. This research also provides key insights for practitioners related to improving the rate of mobile app recommendations by their customers.

Bidirectional sensing of user preferences and application changes for dynamic mobile app recommendations

Recent years have witnessed the rapid adoption of mobile devices and significant growth in the use of mobile apps. However, the large number of mobile apps makes it difficult for users to determine which ones are of interest. Current app recommendation methods focus on the similarities between user interest and mobile app functionality at a single moment, but they do not consider how these change over time and do not address the underlying mutual effect of such changes. This paper describes a bidirectional sensing method for user interest and app changes that enables precise mobile app recommendations. The proposed method applies continuous bidirectional sensing to both user interest and the functional changes to apps and obtains the evolution trajectory of both. Then, a personal interest evolution network is used to learn the relationship between the two trajectories. Finally, user interest in an app is predicted, and the top-N strategy is used to recommend suitable apps. Experiments on real data sets show that our method can accurately sense user interests and functional changes to apps, and that recommendations based on the personal interest evolution network correspond to actual recommendation scenarios.

Mobile app recommendation via heterogeneous graph neural network in edge computing

As a new computing technology proposed with the development of 5G, IoT technologies and increasing requirement of mobile applications and services, edge computing enables mobile application developers and content providers to serve context-aware mobile services (e.g., mobile app recommendation). Mobile app recommendation is known as an effective solution to overcome the information overload in mobile app markets. Most existing models only consider user-app interaction and feature modeling, and neglect the structural information which actually is a crucial part in the scenario of app recommendation. To fully exploit both structural and feature information for app recommendation, this paper proposes a novel heterogeneous graph neural network framework (HGNRec) including one inner module and one outer module. Specifically, the inner module is able to use a node-level attention to learn the importance between a node and its meta-path based neighbors. The outer module with a path-level attention can learn the importance of different meta-paths. With the learned importance from two modules, the comprehensive embeddings for user and app nodes can be generated by integrating features from meta-path based neighbors. Extensive experiments on the real-world Google Play mobile app dataset demonstrate the effectiveness of HGNRec.

Dynamic Parameters-Based Reversible Data Transform (RDT) Algorithm in Recommendation System

The protection and processing of the sensitive data in recommendation system are the major concern. Existing literature, used homomorphic encryption (HE), Reversible Data Transform (RDT), differential privacy (DP) and many more schemes to protect user information. Existing RDT scheme require prior sharing of the parameters and an alternative mechanism e.g., Shamir Threshold Protocol or Diffie-hellman algorithm are used to protect the sharing parameters. In this paper, we proposed a chaotic based RDT approach for privacy-preserving data mining (PPDM) in recommendation system. Using this approach, RDT parameter values will be generated locally and because of this, prior sharing of the parameter values for the recovery process will not be necessary. This approach can be used as an alternative to the standard-RDT algorithm where bandwidth and memory are considered important factors. Our results on the Iris data set clearly show that the proposed chaotic RDT shows similar results as standard-RDT. Secondly, in this paper, we explore the usage of the RDT algorithm on real app usage records in the mobile app recommendation (MAR) domain. Thirdly, we tested the application of the RDT algorithm for the standard MovieLens dataset to ensure the validity of results because app usage dataset is publicly not available. Our results show that the proposed RDT algorithm can replace HE if an adaptive recommendation approach is used. Similarly, we can safely use the RDT approach to any data including user rating, health data or app usage frequency to ensure user privacy before delivering it to the recommender-server.

A privacy-preserving protocol for continuous and dynamic data collection in IoT enabled mobile app recommendation system (MARS)

User trust is an important factor in the success of recommendation systems, including Internet of Things (IoT)-based recommendation systems. However, such trust can be eroded in many different ways (e.g., unauthorized data modifications). Several privacy-preservation schemes have been designed for specific data and/or require strict assumptions (e.g., a private/secure communication channel between client-server and third-party authentication). However, these may limit their application in practice. Hence, in this paper we propose the Reversible Data Transform (RDT) algorithm based privacy-preserving data collection protocol. Our protocol allows us to achieve privacy preservation against beyond the scope processing and does not require a private channel or rely on a third-party authentication. Due to group formation, the disclosure probability of the internal disclosure attack will not be greater than 1/k. Similarly, the reversible privacy-preserving data mining approach protects beyond the scope processing. Findings from the experimentation demonstrates the utility of the proposed protocol and its potential to be deployed in a mobile app recommendation system.

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

The diversity of personal interest and preference of mobile users results in a wide spectrum of mobile app usage, and it is important to predict such app preference in order to provide personalized services. However, currently available individual app usage data is very limited, which does not cover a large user base. In this paper, we demonstrate that it is possible to make personalized app usage estimation by learning user's app preference from the social media, i.e., public accessible tweets, which can also reflect user's interest and make up for the sparsity of app usage data. By proposing a novel generative model named IMCF+ to transfer user interest from rich tweet information to sparse app usage, we achieve personalized app recommendations via learning the interest's correlation between apps and tweets. Based on a real-world app usage and tweet dataset over a large population, we evaluate the performance of IMCF+ with a variety of scenarios and parameters. With only 10 percent training data, our IMCF+ approach achieves 82.5 percent hitrate in predicting the top ten apps. Moreover, IMCF+ outperforms the other six state-of-the-art algorithms by 4.7 percent and 10 percent in high sparsity case and user cold-start scenario, indicating the effectiveness of our method. All these results demonstrate that our technique can reliably learn user's interest from tweets to help solve the personalized app recommendation problem. Our study is the first step forward for transferring user's interest learned from social media to app preference, which paves the way for providing higher-quality personalized app recommendation and services for mobile users.

Serendipity adjustable application recommendation via joint disentangled recurrent variational auto-encoder

• Mobile app recommender able to adjust the level of serendipity is proposed. • It generates next app usage prediction based on the disentangled representation. • We vary the attributes of the disentanglement for serendipitous recommender. • It shows better results than other benchmark methods in the experiments. In this study, we propose an advanced mobile application recommendation method that can systematically adjust the level of serendipity. Previous studies focused on generating recommendations that are relevant to users’ interests. However, this leads to a lack of serendipity and novelty for the user and is therefore not sufficient to achieve high levels of user satisfaction. Our model is trained to predict the next application to be recommended based on a disentangled representation of the sequence in which applications were previously used. We introduce variety into our model by varying the attributes of the disentangled representation. The results of our experiments indicate that the proposed method can systematically and effectively adjust the level of serendipity by varying the values and dimensions of the attribute variables in the disentangled representation. Additionally, our method produces recommendations that are superior to those of other benchmark methods in terms of serendipity and relevance.

Mobile Health Usage, Preferences, Barriers, and eHealth Literacy in Rheumatology: Patient Survey Study.

BackgroundMobile health (mHealth) defines the support and practice of health care using mobile devices and promises to improve the current treatment situation of patients with chronic diseases. Little is known about mHealth usage and digital preferences of patients with chronic rheumatic diseases.ObjectiveThe aim of the study was to explore mHealth usage, preferences, barriers, and eHealth literacy reported by German patients with rheumatic diseases.MethodsBetween December 2018 and January 2019, patients (recruited consecutively) with rheumatoid arthritis, psoriatic arthritis, and axial spondyloarthritis were asked to complete a paper-based survey. The survey included questions on sociodemographics, health characteristics, mHealth usage, eHealth literacy using eHealth Literacy Scale (eHEALS), and communication and information preferences.ResultsOf the patients (N=193) who completed the survey, 176 patients (91.2%) regularly used a smartphone, and 89 patients (46.1%) regularly used social media. Patients (132/193, 68.4%) believed that using medical apps could be beneficial for their own health. Out of 193 patients, only 8 (4.1%) were currently using medical apps, and only 22 patients (11.4%) stated that they knew useful rheumatology websites/mobile apps. Nearly all patients (188/193, 97.4%) would agree to share their mobile app data for research purposes. Out of 193 patients, 129 (66.8%) would regularly enter data using an app, and 146 patients (75.6%) would welcome official mobile app recommendations from the national rheumatology society. The preferred duration for data entry was not more than 15 minutes (110/193, 57.0%), and the preferred frequency was weekly (59/193, 30.6%). Medication information was the most desired app feature (150/193, 77.7%). Internet was the most frequently utilized source of information (144/193, 74.6%). The mean eHealth literacy was low (26.3/40) and was positively correlated with younger age, app use, belief in benefit of using medical apps, and current internet use to obtain health information.ConclusionsPatients with rheumatic diseases are very eager to use mHealth technologies to better understand their chronic diseases. This open-mindedness is counterbalanced by low mHealth usage and competency. Personalized mHealth solutions and clear implementation recommendations are needed to realize the full potential of mHealth in rheumatology.

CAMAR: a broad learning based context-aware recommender for mobile applications

The emergence of a large number of mobile apps brings challenges to locate appropriate apps for users, which makes mobile app recommendation an imperative task. In this paper, we first conduct detailed data analysis to show the characteristics of mobile apps which are different with conventional items (e.g., movies, books). Considering the specific property of mobile apps, we propose a broad learning approach for context-aware mobile app recommendation with tensor analysis (CAMAR). Specifically, we utilize a tensor-based framework to effectively integrate app category information and multi-view features on users and apps to facilitate the performance of app recommendation. The multi-dimensional structure is employed to capture the hidden relationships among the app categories and multi-view features. We develop an efficient factorization method which applies Tucker decomposition to jointly learn the full-order interactions among the app categories and features without physically building the tensor. Furthermore, we employ a group $$\ell _{1}$$ -norm regularization to learn the group-wise feature importance of each view with respect to each app category. Experiments on two real-world datasets demonstrate the effectiveness of the proposed method.

Stance detection and mobile app recommendation discourse on tweets

AbstractWeb‐based social networking such as microblogging administrations and long‐range informal communication locales are changing the way in which individuals collaborate on the web and search for data and opinions. An essential parameter of online networking discourse is searchability. A key semiotic asset supporting this capacity is the hashtag, a type of social label that enables microbloggers to insert metadata in online networking posts. In this paper, an attempt is made to analyze stance detection and app recommendation discourse on tweets in view of hashtag techniques, which is in the territory of etymology, and to spotlight the structure of dialect at the provision level. With a revival of enthusiasm for topics identified by modeling language at the discourse level, a graphical model of conversational structure (ie, the structural topic model) has been constructed by means of utilizing three methods: displaying words connected with topics or documents highly connected with topics, calculating topic correlations, and assessing associations between metadata and topical content, its capture of latent topics, and topical structures inside documents on a benchmark dataset (ie, SemEval 2016) has been scrutinized for stance detection, and data have been crawled from Twitter, using the hashtag #App for app recommendations.

Multi-view factorization machines for mobile app recommendation based on hierarchical attention

Mobile app recommendation has been an effective solution to overcoming the information overload in mobile app markets. Recent studies have demonstrated the power of neural network in recommendation tasks which is however rarely exploited for mobile apps. As one of the development of neural network, attention-based models have shown promising results for recommendation because of its capability of filtering out uninformative features from raw inputs. In this paper, to effectively predict users’ preferences for apps, we propose a hierarchical neural network model called MV-AFM for app recommendation which models the interactions of features from different views (view interactions for short) through the attention mechanism. Specifically, the novelty of MV-AFM is the introduction of view segmentation for feature interactions and the construction of two level attention networks: the feature-level attention, starting from the feature embeddings within each view, which intends to select the representative features for the view, and the view-level attention, which learns the importance of interactions between any two views. Extensive experiments on two real-world mobile app datasets demonstrate the effectiveness of MV-AFM.

Exploiting Usage to Predict Instantaneous App Popularity

Popularity of mobile apps is traditionally measured by metrics such as the number of downloads, installations, or user ratings. A problem with these measures is that they reflect usage only indirectly. Indeed, retention rates, i.e., the number of days users continue to interact with an installed app, have been suggested to predict successful app lifecycles. We conduct the first independent and large-scale study of retention rates and usage trends on a dataset of app-usage data from a community of 339,842 users and more than 213,667 apps. Our analysis shows that, on average, applications lose 65% of their users in the first week, while very popular applications (top 100) lose only 35%. It also reveals, however, that many applications have more complex usage behaviour patterns due to seasonality, marketing, or other factors. To capture such effects, we develop a novel app-usage trend measure which provides instantaneous information about the popularity of an application. Analysis of our data using this trend filter shows that roughly 40% of all apps never gain more than a handful of users ( Marginal apps). Less than 0.1% of the remaining 60% are constantly popular ( Dominant apps), 1% have a quick drain of usage after an initial steep rise ( Expired apps), and 6% continuously rise in popularity ( Hot apps). From these, we can distinguish, for instance, trendsetters from copycat apps. We conclude by demonstrating that usage behaviour trend information can be used to develop better mobile app recommendations.

Mobile App Recommendation: An Involvement-Enhanced Approach

Given the ubiquitous and critical role of mobile apps in people’s lives as well as the sheer size of the market, developing effective mobile app recommendation methods that can help users locate the apps they desire is critical for both users and platforms. Premised in involvement theory, we propose a novel mobile app recommendation method that integrates both users’ download and browsing behaviors for mobile app recommendations, in contrast to existing methods that rely on download behaviors but neglect browsing behaviors. Specifically, we introduce a novel model that appropriately combines download and browsing behaviors to learn users’ overall interests in and involvement with apps, develop a new algorithm to infer the model’s parameters, and propose an innovative mobile app recommendation strategy that combines users’ overall interests and their current interests to recommend apps. Finally, using data collected from one of the largest mobile app platforms in China, we demonstrate and analyze the superior performance of our method over several state-of-the-art mobile app recommendation methods.