Mobile Recommendation Research Articles

Towards a social and context-aware mobile recommendation system for tourism

Loyalty in tourism is one of the main concerns for tourist organizations and researchers alike. Recently, technology in general and CRM and social networks in particular have been identified as important enablers for loyalty in tourism. This paper presents POST-VIA 360, a platform devoted to support the whole life-cycle of tourism loyalty after the first visit. The system is designed to collect data from the initial visit by means of pervasive approaches. Once data is analysed, POST-VIA 360 produces accurate after visit data and, once returned, is able to offer relevant recommendations based on positioning and bio-inspired recommender systems. To validate the system, a case study comparing recommendations from the POST-VIA 360 and a group of experts was conducted. Results show that the accuracy of system’s recommendations is remarkable compared to previous efforts in the field.

Strategies and Measures for Sustainable Urban Transport Systems

Increasing sustainability of urban transport systems is a crucial objective of all strategic plans both at national and European level. Different strategies and measures can be adopted to improve the efficiency of transport systems, according to a large set of factors that can affect the results of the implemented actions. A comprehensive study has been carried out in order to define a methodology able to define effective and efficient strategies and measures, allowing to increase the sustainability level of different kinds of cities, from small-medium sized to large metropolitan areas. The methodology has been tested on a group of 50 Italian cities, whose characteristics have been analysed through an initial set of more than 200 indicators. Three main groups of indicators have been taken into account: State indicators, Sustainability indicators, Policy indicators. The main aim has been to identify existing relationships between Sustainability and Policy indicators for cities showing commonalities in terms of State indicators. A correlation analysis allowed to identify 53 relevant indicators from the initial set of 200, while a cluster analysis, based on a hierarchical model, allowed to group the cities into five different groups, according to their population size and density. Correlations between relevant indicators have also been analysed within each group, while linear regression models have allowed to describe some functional relations between Policy and Sustainability indicators. A benchmarking exercise has allowed to identify strategies and measures adopted by the best performers within each group, hence defining possible paths to a better sustainability level for the remaining cities. Finally, recommendations for a correct urban mobility planning procedures have been produced.

Mobile Targeting Using Customer Trajectory Patterns

Rapid improvements in the precision of mobile technologies make it possible for advertisers to go beyond using the real-time static location and contextual information about consumers. In this study, we propose a novel “trajectory-based” targeting strategy for mobile recommendation that leverages full information on consumers’ physical movement trajectories using granular behavioral information from different mobility dimensions. To analyze the effectiveness of this new strategy, we design a large-scale randomized field experiment in a large shopping mall that involved 83,370 unique user responses for a 14-day period in June 2014. We find that trajectory-based mobile targeting can lead to higher redemption probability, faster redemption behavior, and higher transaction amount from customers compared to other baselines. It also facilitates higher revenues for the focal store as well as the overall shopping mall. Moreover, the effect of trajectory-based targeting comes not only from improvements in the efficiency of customers’ current shopping process, but also from its ability to nudge customers towards changing their future shopping patterns and generate additional revenues. Finally, we find significant heterogeneity in the impact of trajectory-based targeting. It is especially effective in influencing high-income consumers. Interestingly, it becomes less effective in boosting the revenues of the shopping mall during the weekends and for those shoppers who like to explore across products categories. Our finding suggests that highly targeted mobile promotions can have the inadvertent impact of reducing impulse purchase behavior by customers who are in an exploratory shopping stage. On a broader note, our work can be viewed as a first step towards studying the large-scale, fine-grained digital trace of individual physical behavior, and how it can be used to predict and market to individual anticipated future behavior.

Combining User Contexts and User Opinions for Restaurant Recommendation in Mobile Environment

In a mobile setting, user preferences vary in different contexts. Advances in mobile technologies have made the collection of user context information feasible, and as a result, the context-aware mobile recommender system field has been formed. Although there exist several different approaches to incorporating context into the recommendation process, context-aware recommendations are still difficult to compute. It is unclear which contextual factors are important and to which degree they influence user-item selection decisions. In this paper, the authors design a novel mobile restaurant recommender system combining user contexts and user opinions to provide restaurants to mobile users. This system extracts restaurant features from online user reviews and calculates the polarity of them based on sentiment analysis. It takes a new approach for assessing and modeling the relationship between contextual factors and restaurant features. On this basis, a hybrid recommender method is constructed, which integrates the contextual matching algorithm based on analytic hierarchy process and the collaborative filtering algorithm based on context similarity. From the user study, this system suggests restaurants that make the user more satisfied than another comparative system.

A Mobile Recommendation System Supporting Group Collaborative Decision Making

Nowadays, recommendation services that allow users to obtain the information needed in their vicinity have become very popular among users of mobile devices. In fact, these systems guide the user to choose amongst the available information, identifying and making suggestions of relevant information based on user's preferences and context information. Furthermore, this is particular important in mobile devices with small screens, where it is essential that what is shown is truly relevant for the user in order to help him/her in the decision process. Several mobile recommender systems have been proposed but there still exist open challenges. This paper proposes BomApetite a mobile system to recommend restaurants to a group, based on the preferences of all the group participants, which integrates restaurant information from well-known platforms. The recommendation strategy considers the importance the user gives to each platform. To support group decision making the system uses a method that determines the best alternatives for the group from individual preferences and provides a voting process so that the group can reach a consensus. The results of a user study assessing the usability and usefulness of the system showed that overall participants had a favorable opinion.

A Mobile Recommendation Algorithm Based on Statistical Analysis of User Data

A Mobile Recommendation Algorithm Based on Statistical Analysis of User Data

Pull-based recommendations in mobile environments

In the field of Context-Aware Recommendation Systems (CARS), only static contextual information is usually considered. However, the dynamic contextual information would very helpful in mobile computing scenarios. Despite this interest, the design and implementation of flexible and generic frameworks to support an easy development of context-aware mobile recommendation systems have been relatively unexplored. In this paper, we describe a framework that facilitates the development of CARS for mobile environments. We mainly focus on the development of the elements needed to support pull-based recommendations and the experimental evaluation of the proposed system.

Compliance with Australian stroke guideline recommendations for outdoor mobility and transport training by post-inpatient rehabilitation services: An observational cohort study.

BackgroundCommunity participation is often restricted after stroke, due to reduced confidence and outdoor mobility. Australian clinical guidelines recommend that specific evidence-based interventions be delivered to target these restrictions, such as multiple escorted outdoor journeys. The aim of this study was to describe post-inpatient outdoor mobility and transport training delivered to stroke survivors in New South Wales, Australia and whether therapy differed according to type, sector or location of service provider.MethodsUsing an observational retrospective cohort study design, 24 rehabilitation service providers were audited. Provider types included outpatient (n = 8), day therapy (n = 9), home-based rehabilitation (n = 5) and transitional aged care services (TAC, n = 2). Records of 15 stroke survivors who had received post-hospital rehabilitation were audited per service, for wait time, duration, amount of therapy and outdoor-related therapy.ResultsA total of 311 records were audited. Median wait time for post-hospital therapy was 13 days (IQR, 5–35). Median duration of therapy was 68 days (IQR, 35–109), consisting of 11 sessions (IQR 4–19). Overall, a median of one session (IQR 0–3) was conducted outdoors per person. Outdoor-related therapy was similar across service providers, except that TAC delivered an average of 5.4 more outdoor-related sessions (95 % CI 4.4 to 6.4), and 3.5 more outings into public streets (95 % CI 2.8 to 4.3) per person, compared to outpatient services.ConclusionThe majority of service providers in the sample delivered little evidence-based outdoor mobility and travel training per stroke participant, as recommended in national stroke guidelines.Trial registrationAustralian and New Zealand Clinical Trials Registry ACTRN12611000554965.

Context-Aware Mobile Proactive Recommendation

Mobile recommender systems aim to recommending the right product or information to the right users at anytime and anywhere. It is well known that the contextual information is often the key for the performances of mobile recommendations. Therefore, in this paper, we firstly identify which types of contextual information could affect users' personal preferences, which is called users' adaptive options preferences, and qualitatively construct an adaptive options analytical hierarchy process model for users' personal preferences , and quantitatively analyze impact weights of contextual information on users' personal preferences. Then we propose a novel contextaware learning algorithm for mobile users' adaptive options preferences. Secondly we divide all users into two groups according to their frequency in using of all services in history logs, and propose two different proactive recommendation methods for the two classes of users. Finally experiments are conducted to demonstrate the performance of the preference learning algorithm, the impact of contexts and the proportion of the training dataset on the algorithm, and recommendation precision of the two methods.

An Analysis of Features and Tendencies in Mobile Banking Apps

Abstract Mobile devices such as smartphones and tablets are being employed alongside personal computers, and even replacing them in some applications. Banks are increasingly investing on mobility, by enabling the mobile web and mobile app channels for online banking, and by providing new mobile payment services. In this paper, the services for off-branch banking offered by several Italian banks are analyzed, showing that mobile apps have surpassed the mobile web channel in completeness of the offer, due to the fact that additional capabilities of mobile devices make possible advanced features and applications. An outlook on the near future is provided, remarking that mobile marketing and mobile recommender systems can greatly take advantage of being run natively on devices, making it desirable for businesses to invest on designing mobile apps.

Improving Smart Conference Participation Through Socially Aware Recommendation

This research addresses recommending presentation sessions at smart conferences to participants. We propose a venue recommendation algorithm, Socially-Aware Recommendation of Venues and Environments (SARVE). SARVE computes correlation and social characteristic information of conference participants. In order to model a recommendation process using distributed community detection, SARVE further integrates the current context of both the smart conference community and participants. SARVE recommends presentation sessions that may be of high interest to each participant. We evaluate SARVE using a real world dataset. In our experiments, we compare SARVE to two related state-of-the-art methods, namely: Context-Aware Mobile Recommendation Services (CAMRS) and Conference Navigator (Recommender) Model. Our experimental results show that in terms of the utilized evaluation metrics: precision, recall, and f-measure, SARVE achieves more reliable and favorable social (relations and context) recommendation results.

RecomMetz: A context-aware knowledge-based mobile recommender system for movie showtimes

Recommender systems are used to provide filtered information from a large amount of elements. They provide personalized recommendations on products or services to users. The recommendations are intended to provide interesting elements to users. Recommender systems can be developed using different techniques and algorithms where the selection of these techniques depends on the area in which they will be applied. This paper proposes a recommender system in the leisure domain, specifically in the movie showtimes domain. The system proposed is called RecomMetz, and it is a context-aware mobile recommender system based on Semantic Web technologies. In detail, a domain ontology primarily serving a semantic similarity metric adjusted to the concept of “packages of single items” was developed in this research. In addition, location, crowd and time were considered as three different kinds of contextual information in RecomMetz. In a nutshell, RecomMetz has unique features: (1) the items to be recommended have a composite structure (movie theater+movie+showtime), (2) the integration of the time and crowd factors into a context-aware model, (3) the implementation of an ontology-based context modeling approach and (4) the development of a multi-platform native mobile user interface intended to leverage the hardware capabilities (sensors) of mobile devices. The evaluation results show the efficiency and effectiveness of the recommendation mechanism implemented by RecomMetz in both a cold-start scenario and a no cold-start scenario.

Mining Users' Similarity from Moving Trajectories for Mobile E-commerce Recommendation

Users’ similarity mining in mobile e-commerce systems is an important field with wide applications, such as personalized recommendation and accurate advertising. Moving trajectories of e-commerce users contain much useful information, providing a very good opportunity for understanding the users’ interesting and discovering the similarity between mobile-device-holders. In this paper, we explores the problems in the existing mobile ecommerce recommendation methods, and propose a mobile users’ moving trajectories mining based user similarity discovering approach for mobile e-commerce system. We formally defines the moving trajectory and view the areas, where users stay within for a certain time, as interested regions, which reflect the preferences of mobile-device-holders. Based on the number of overlapped interested areas, a user similarity measure method is proposed. Experimental evaluation, conducted based on the publicly available datasets commendably demonstrate the effectiveness of our approach.

Context-aware Social Popularity based Recommender System

Contexts and social web information have been recognized to be valuable information for making perfect recommender system. Context-aware recommender systems (CARS) have been implemented in different applications and domains which improve the performance of recommendations. Context-aware approaches have been successfully applied in various domains such as music, movies, mobile recommendations, personalized shopping assistants, conversational and interactional services, social rating services and multimedia. The recommender systems are widely being used for products, content and services recommendations. Successful deployment of recommender system in social web and many commercial website like Amazon.com, flipkart, HomeShop18 and numerous different sectors have already done. The growth of the social web has revolutionized the architecture of sharing and association in the web, making it essential to reiterate recommendation. If recommender systems have established their key role in providing the user access to resources on the web, when sharing resources has turn into social, it is likely for recommendation techniques in the social web should consider social popularity factor and the relationships among users to compute their predictions. In this paper contextual information are being included in social popularity based SVD++ model to improve accuracy and scalability of recommendations.

Context-aware Mobile Recommendation System Based on Context History

Recommendation systems for the mobile Web have focused on endorsing specificr content based on user preferences. But, user preferences vary in different contexts, such as at different times of day and in different locations. Therefore, in a mobile networking setting, providing proactive personalized service is more likely to depend on actual user context. This paper proposed a context-aware mobile recommendation system framework based on user models utilizing the context history. The approach was validated in the tourism domain. From our experiment and evaluation, the proposed framework is a promising approach to provider proactive personalized services to mobile users. Moreover, this research offers the personalized services to new users analyzing between the new user’s information and the stored association rules. DOI : http://dx.doi.org/10.11591/telkomnika.v12i4.4786

Mining Check-In History for Personalized Location Naming

Many innovative location-based services have been established to offer users greater convenience in their everyday lives. These services usually cannot map user's physical locations into semantic names automatically. The semantic names of locations provide important context for mobile recommendations and advertisements. In this article, we proposed a novel location naming approach which can automatically provide semantic names for users given their locations and time. In particular, when a user opens a GPS device and submits a query with her physical location and time, she will be returned the most appropriate semantic name. In our approach, we drew an analogy between location naming and local search, and designed a local search framework to propose a spatiotemporal and user preference (STUP) model for location naming. STUP combined three components, user preference (UP), spatial preference (SP), and temporal preference (TP), by leveraging learning-to-rank techniques. We evaluated STUP on 466,190 check-ins of 5,805 users from Shanghai and 135,052 check-ins of 1,361 users from Beijing. The results showed that SP was most effective among three components and that UP can provide personalized semantic names, and thus it was a necessity for location naming. Although TP was not as discriminative as the others, it can still be beneficial when integrated with SP and UP. Finally, according to the experimental results, STUP outperformed the proposed baselines and returned accurate semantic names for 23.6% and 26.6% of the testing queries from Beijing and Shanghai, respectively.

Special Issue on Social Computing and its Applications

Social computing is at the intersection of social behavior and computing systems, creating or recreating social conventions and social contexts using software and technology. Various social computing applications such as blogs, email, instant messaging, social networking (e.g. Facebook, MySpace, Twitter, LinkedIn, etc.), wikis and social bookmarking have been widely popularized where people interact socially via the computing space. Such applications have profoundly impacted social behavior and lifestyle while also pushing the boundary of computing technology. While people can enjoy or even indulge in the benefits such as freedom and convenience offered by social computing, various critical issues such as privacy protection, touchscreen-based HCI design and modeling of social behavior in computing space still remain challenging. The timely responses and actions to these issues form the most active and promising research practices conducted in this interdisciplinary arena. The prominent effort and achievement made by experts and practitioners from various backgrounds lies in modeling and mining this vast volume of data to extract, represent and exploit meaningful knowledge, and to investigate the heterogeneity, dynamics and complexity of social phenomenon and behavior, to reveal the hidden patterns and knowledge for advancing research in relevant domains such as cognitive, behavioral, social, economic, cultural and operational research. Moreover, this trend also stimulates the propagation and popularity of a broad spectrum of new applications and technologies in these domains. Therefore, social computing and its applications open a promising direction of such research and practice, and offer unique opportunities for theoretical research, algorithmic innovation and practical breakthrough from Computer Science and Information Technology, to Social and Behavioral science. This special issue is a timely reflection of scientific and practical findings in social computing, evidenced by the overwhelming attention and response of 13 submissions received from seven countries and recommended by 2012 International Conference of Social Computing and its Applications (SCA’2012). The topics of these submissions cover a wide range of interests in social computing and application, addressing various hottest research questions, e.g. social community detection, search in social context, influence analysis, social mobile computing, recommendation systems and learning in social behavioral platform.All submissions have gone through a rigorous review process and each submission has been reviewed by at least three reviewers. After two to three rounds of reviews and revisions, we then recommend six best quality papers in terms of the technical depth and innovation, algorithmic and experimental soundness, and satisfactory presentation to be included into this special issue, which are summarized in the following. As the microblogging systems such as Twitter and SinaWeibo become more and more popular in recent years, the requirement for real-time and personalized search over microblogging systems also becomes more important. The paper entitled ‘Realtime and Personalized Search over a Microblogging System’ presents a new search engine containing four modules to infer the topics of microblogs and update the interests of users, build indexes efficiently, return microblogs for a keyword search and personalize the order of microblogs, respectively. The experiments were conducted on a real dataset to illustrate the effectiveness and efficiency of the proposed methods. This paper reflects the latest research progress in social media search. In modern societies, the process of communication is greatly influenced by information technology and computer

Mobile recommender systems in tourism

Recommender Systems (RSs) have been extensively utilized as a means of reducing the information overload and offering travel recommendations to tourists. The emerging mobile RSs are tailored to mob...

Mobile Recommender Systems and Their Applications

Mobile recommender systems have recently become one of the hottest topics in the domain of recommender systems.The main task of mobile recommender systems is to improve the performance and accuracy along with user satisfaction utilizing mobile context,mobile social network and other information.This paper presents an overview of the field of mobile recommender systems including key techniques,evaluation and typical applications.The prospects for future development and suggestions for possible extensions are also discussed.

Mobile recommendation based on link community detection.

Since traditional mobile recommendation systems have difficulty in acquiring complete and accurate user information in mobile networks, the accuracy of recommendation is not high. In order to solve this problem, this paper proposes a novel mobile recommendation algorithm based on link community detection (MRLD). MRLD executes link label diffusion algorithm and maximal extended modularity (EQ) of greedy search to obtain the link community structure, and overlapping nodes belonging analysis (ONBA) is adopted to adjust the overlapping nodes in order to get the more accurate community structure. MRLD is tested on both synthetic and real-world networks, and the experimental results show that our approach is valid and feasible.