Digital game distribution platforms have captured the majority of the market in the game industry since the introduction of intelligent devices and the Internet. Customers adhering to the forum is a significant issue for game platforms. The sticking point is a personalized game recommendation that is tailored to the user's preferences. By analyzing customer preferences and recommending appropriate game lists, the game platform could gain a competitive advantage over competitors. However, because of the numerous factors that must be considered, creating a personalized game list is difficult. This study considers many complementary elements required for a game recommendation, such as games and players, external and internal, crowd and individual. We propose a game recommendation mechanism that incorporates personality traits, social relationships, and crowds' opinions. The recommendation method takes into account the semantics of the community, social tagging, and user behavior. This study aims to assist game platforms in developing game recommendations based on a broader range of factors, allowing users to access more great games tailored to their preferences.

The prevalence of mobile devices has significantly increased in recent years, becoming an integral part of our daily lives. This shift has created promising opportunities for mobile advertising, with industry leaders like Apple and Google already integrating it into their services. However, effective mobile advertising still grapples with challenges such as precise customer targeting and adaptability in an ever-changing landscape. To address these issues, we propose an innovative mobile advertising recommender system that employs "context -fitness" and "social referral" techniques. Experiments provide compelling evidence that context -aware information significantly enhances accuracy in predicting users' evolving needs. With our system, we can identify the most suitable ads for targeted users in a changing environment and enhance ad effectiveness by considering friends' influence.

Recently, with the popularity of social investing platforms, participating in an investment club has become a good choice for investors. Following financial experts in the investment club likely generates more profit as they have higher expertise in planning an investment portfolio. In this study, we propose a portfolio selection mechanism that combines collective intelligence extracted from investors’ opinions and LSTM stock price predictions to infer a club's investment preference and predict the profitability of the extracted investment targets. Based on a club's risk tolerance and investment preference, the proposed mechanism can create an appropriate stock portfolio for the investors in the club. Utilizing StockTwits and stock historical data, the experimental results verify that the proposed portfolio selection mechanism performs better than market indices and other benchmark approaches in the market.

The Budget-based Neighboring Object Group Query (BR-NOGQ) is a novel type of location-based query that considers both the spatial relationships between objects and the user's budget constraints on experiencing these objects. However, processing a large number of BR-NOGQs concurrently can overload a centralized system, leading to poor performance. To address this issue, this paper focuses on developing a distributed processing technique for answering multiple BR-NOGQs using the MapReduce platform. The proposed approach involves designing a grid structure to manage information about different types of objects and developing a MapReduce-based algorithm for efficient distributed processing of multiple BR-NOGQs. Experimental results using a synthetic dataset demonstrate the scalability and efficiency of the proposed algorithm.

In recent years, many of the location-based queries have been proposed that consider the proximity of spatial sites to provide users with information. However, most studies focus on a single type of sites and do not consider the cost of visiting the sites. As a result, in this paper we present a novel type of location-based queries, namely the Budget-Range-based neighboring site group query (or BR-based NSGQ for short), to find the groups of sites that are within a distance d of each other and have a total cost not exceeding a budget range [bgtm, bgtM]. The site groups are termed the neighboring site groups within budget range (abbreviated as NSGs-BR). In order to efficiently answer the BR-based NSGQs, we modify the R-tree structure to present the RcC-tree, and then design four checking rules to prune the non-qualifying site groups. We propose a query processing algorithm, namely the BR-based NSGQ algorithm, to find all the NSGs-BR by combing the traversal of the RcC-tree and the four checking rules. Finally, numerous experiments are evaluated to demonstrate the efficiency of the BR-based NSGQ algorithm in terms of the CPU time and the number of node accesses of the RcC-tree.

In recent years, social networks have grown rapidly, and their applications in the healthcare domain are increasingly proposed. Using the crowd wisdom generated from social networks, we can find similar and reliable people sharing helpful experiences. The existing dedicated social networking services for health mainly focus on sharing, but not categorising and extracting. In this research, we construct an environment for social knowledge sharing and expert referring. Analysing queries from online public health databases and the factors of health similarity, social reliability and social intimacy, we extract health knowledge to recommend relevant social knowledge (also called threads) and helpful experts providing consulting. Specifically, the proposed social diagnosis mechanism helps the health seeker to identify relevant threads and recommends enthusiastic experts for healthcare support. Experimental results reveal that the proposed mechanism can effectively improve healthcare knowledge sharing and realise diagnosis support from the crowd.

People suffering from mental health difficulty need someone’s listening and advice, but there are not enough human resources to provide support. In this research, we aim to propose a social mechanism for recommending healthcare knowledge over social networks to resolve the issue of lacking consulters and encourage people to take the initiative to seek for online help. By analysing users’ posts, background, preferences, similarities and relationships, the proposed mechanism can provide proper posts and consulters to facilitate experience-sharing and consulting help from the crowd. With reliable referrals support, people are more comfortable speaking their minds and expressing their emotions, and thus they receive better guidance.

The O2O business model combines the efficiency of online retailing with the value created from physical customer experience. While many O2O apps and services have been proposed, accurately targeting customers and effectively advertising in a dynamic environment remain big challenges for O2O e-commerce. To address these challenges, we propose a novel social recommendation mechanism that incorporates social and contextual intelligence techniques. The proposed mechanism can identify the most suitable events for targeted users in a changing environment and significantly improve advertising effectiveness by considering the influence of friends.

Many mobile applications employ "check-in" intelligence to develop location-based commerce services through the recommendation of activities, nearby venues or coupons. In this paper, we aim to study the issues of innovative location-based e-commerce services built on social, mobility and contextual intelligence. Specifically, we explore the key elements of social, mobility, and contextual intelligence mechanism and prose a suite of important mobile commerce services. Founded on the established social, mobility, and context intelligence, we further propose a suite of innovative endorser advertising mechanism, which aims to find out those endorsers who have advertisement proneness and high sharing willingness in advertisement information diffusion, with a recommended list of potential advertisement receivers. Our mechanism propagates advertisement information in an efficiency way by helping consumers effortlessly filtering the advertisements fitting their preference, location, and context. On the other hand, it helps business propagate advertisements to the target consumers in an efficiency way.

Social networks have become indispensable in our daily lives, and have significant implications for the development of electronic commerce. In centralized e-marketplaces, buyers face two main problems in purchasing decisions. Firstly, for some products, sellers do not provide product information. Secondly, buyers can be deceived by fake reviews or ratings manipulated by malicious providers. In this research, after analyzing users' social activities, we propose an appraisal mechanism for the social marketplace, which customers can use to find products and to obtain credible referrals. The proposed mechanism can effectively discover suitable and trustworthy sellers to expedite the online purchasing process and enable social commerce to flourish.

Presently, people use social media at a greater rate to share their personal investment experiences. This plentiful user-generated data source has been promisingly used by investors for portfolio creation. A new type of investing platform that allows investors to copy the portfolios of experienced investors has grown dramatically. In this research, we propose a collective intelligence mechanism that can extract and consolidate the opinions expressed over the social investing platform and generate appropriate portfolios by analyzing other investors' knowledge, authority, and opinions toward the investment target. The experimental results obtained based on the social investing platform eToro.com reveal that the portfolio recommended by the proposed mechanism outperforms the market index and other benchmark approaches in various financial performance aspects.

“Check-in” function of mobile social network platform acts as a key role in connecting the online word to the offline word (O2O). In this paper, we propose a suite of innovative social event endorsing mechanism, which aims to find out those endorsers who have event proneness and high sharing willingness and high propagation strength in event information diffusion, with a recommended list of potential event attenders. Our mechanism propagates social event information in an efficient way by helping consumers effortlessly filter the events fitting their preference and location. On the other hand, it helps business propagate social event to the target consumers in an efficiency way.

In recent years, motivated by many practical applications such as viral marketing, researchers have paid significant attention to the circulation of information on social networks. The influential nodes that can influence the largest part of social networks are an essential topic in social network analysis. Most present solutions address the issue of discovering the influential nodes that could maximize influence effectiveness rather than minimize the cost of the information diffusion. In this paper, we investigate the circulation of emergency information, such as timely production promotion or disaster information, through a social network. These are real-life problems that have a significant effect in a very short time. We focus on how to minimize the total cost for all users in a specific social network to receive such information. We propose an efficient k-best social disseminator discovering algorithm in which the total diffusion cost on spreading timely information for each user in this social network is minimized.

The phenomenon of "impulse purchasing" or "impulse shopping" is an unplanned decision to buy or to shop based on the context (e.g. emotion, feelings, event etc.) at that time. For example, when people have just finished watching a ball game, they are more likely to purchase game-related products in that time than they would in a normal situation. In this paper, we proposed a novel social activity recommendation mechanism for enhancing location- based e-commerce, by incorporating the techniques of social event analysis, context characteristic analysis and activity fitness analysis. The proposed mechanism could identify the most social event for targeted users in a changing environment, and provide the users "the most willing to attend" event activity in a more intellective way.

Crowdsourcing is a new trend that uses the wisdom of crowds on the Internet to solve certain problems that need vast amounts of human resources. There have been a number of crowdsourcing platforms developed for various domains. However, the landscape of crowdsourcing platforms is widely dispersed and most tasks remain hidden. Finding out the tasks closely matching contributors' personal preference and capabilities is difficult. In this research, we aim to design a social mechanism for task-oriented crowdsourcing recommendations, which the requesters can easily use to find suitable contributors who are also very willing to finish their tasks. Our experimental results show that the proposed mechanism is effective in identifying appropriate contributors with respect to different types of task. The proposed mechanism can help to establish a long-term partnership that brings value to the participants of task-oriented crowdsourcing.

In recent years, there are growing numbers of people going abroad for studying and traveling which indicates that the demand of currency exchanges is increasing. However, some problems are existed when we exchange currency through the banks. Consequently, the new financial service called P2P currency exchange emerged which aims to disrupt the foreign exchange (FX) markets. In this paper, we propose a recommendation mechanism for P2P currency exchange which is based on social networks and analyze users' preference, similarity and location-based service. Then evaluating social trust by social influence computing. We look forward to providing proper candidates and encouraging sharing economy in finance sector which greatly decrease the cost of currency exchange.

In this paper, we proposed a novel social event shopping recommendation mechanism for enhancing location-based e-commerce, by analyzing the fitness considering the criteria factors of preference similarity, event relativity, social influence, and mobility influence, the proposed system could effectively recommend the most suitable shopping stores to users.

The purpose of this study is to build a web-based customized Corporate Identity System, with a search engine to facilitate logo searching, suggest logos and assist in the design processes. This web-based system should be icon-oriented, based on a database of corporate logos, logotypes and applicable product modules. With the assistance of such a system, designers and clients can generate a customized design process. They can find the logo, logotype and the supplementary design elements from the databases and apply them to business items, banners, packaging, uniforms, transportation and so on, using the online search engine. From this integrated platform, the basic elements of Corporate Identity Design can be modularized, edited and presented immediately on the internet, providing designers and their clients with the most time efficient means of communicating and testing ideas, Collective Intelligence becomes prevalent, enterprises are now facing even more rapid changes on the internet. Aside from getting hold of the core technology, effectively utilizing the synergy brought by Collective Intelligence, selecting the most appropriate corporate image solutions, and creating an information sharing center are crucial actions; it is also necessary to accumulate and share knowledge, and elevate the value of corporate image and culture so that the competitive advantages can be sustained.

To survive in a fiercely competitive business environment, it has become increasingly important for physical retailers to provide customers with services offering a better shopping experience. Many renovate and enlarge their shopping spaces to make their stores more enjoyable places to visit. The growth in social media and the use of mobile devices provide retailers with an opportunity to offer a context-aware guidance service to enhance customers' in-store shopping experience. In this research, by extracting and analysing shopping information (shopping context, visiting trajectory) and social information (user's interest, friends' influence), a contextual store shopping recommendation system is proposed to provide an appropriate route for first-time customers or those who are unfamiliar with a retailer's shopping space. Our experimental results show that the proposed model is effective in providing an appropriate shopping route and enhancing users' shopping experience, which could significantly improve the profitability and competitive advantage of the retailers.

O2O business model synergize the efficiency improved from online retailing and value created from physical customer experience. Nowadays, while many O2O apps and services have been proposed, the study of the accuracy of customer targeting and the effectiveness of advertising in a dynamic environment are big challenges currently faced by O2O e-commerce. In this paper, we proposed a novel social recommendation mechanism for enhancing O2O e-commerce, by incorporating the techniques of context-awareness and social referral. The proposed mechanism could identify the most suitable ads for targeted users in a changing environment, and could significantly improve the effectiveness of advertising by taking the influence of friends into consideration.