New Type Of Social Network Research Articles

DFGR: Diversity and Fairness Awareness of Group Recommendation in an Event-based Social Network

An event-based social network is a new type of social network that combines online and offline networks, and one of its important problems is recommending suitable activities to users. However, the current research seldom considers balancing the accuracy, diversity and fairness of group activity recommendations. To solve this problem, we propose a group activity recommendation approach that considers fairness and diversity perception. Firstly, we calculate activity similarity based on the context and construct an activity similarity graph. We define the weighted coverage on the similarity graph as a submodular function and transform the problem of fair and diverse group activity recommendation into maximizing the weighted coverage on the similarity graph while considering accuracy, fairness, and diversity. Secondly, we employ a greedy algorithm to find an approximate solution that maximizes the weighted coverage with an approximation ratio. Finally, we conducted experiments on two real datasets and demonstrate the superiority of our method compared to existing approaches. Specifically, in the domain of diversity-based recommendation algorithms, our method achieves a remarkable 0.02% increase in recall rate. Furthermore, in the domain of fairness-based recommendation algorithms, our proposed method outperforms the latest approach by 0.05% in terms of overall metrics. These results highlight the effectiveness of our method in achieving a better balance among accuracy, fairness, and diversity.

EMPLOYEE MOBILITY AND INNOVATION: THE ROLE OF TURNOVER RATE AND NETWORK CENTRALITY

Innovation is crucial to a company’s competitive advantage and employees play an important role in generating innovation within a company. Based on social capital theory, we proposed a new type of social network: the employee mobility network, and explored the impact of employee mobility on innovation. Specifically, we examined the role of both employee turnover rate, and an organisation’s centrality in the employee mobility network in predicting innovation. We collected data from World Intellectual Property Organisation (WIPO), Talentale, and Forbes Global 2000 to test our hypotheses. The results showed that turnover rate had a significantly inverted-U curve relationship with innovation, and both degree and closeness centralities of an organisation in the employee mobility network had a significant positive relationship with innovation. Based on the results, we suggest that companies should find a balanced value for their turnover rate to get the highest return in innovation. Also, we suggest that companies should improve social influence in employee mobility networks in order to attract talent and increase company innovation.

The Impact of Corporate Social Network on Innovation: A Mediation Analysis of Agency Costs and Financial Constraints

This paper examines the impacts of corporate social network on innovation activities (both R&D inputs and patent outputs) and explores the potential influence path of social networks driving corporate innovation. Using Chinese share markets’ listed companies in the period from 2009 to 2016 as the sample, we establish a new type of social network based on the connections of the core management team (including directors, supervisors and executives) and find that a corporate social network based on the core management team has a positive causal effect on enhancing R&D investments and patent performance. Empirical results are robust after controlling for endogeneity and the causal relationship between social networks and corporate innovation is robustly monotonic. We perform a mediation analysis following the bootstrapping procedures, and find that alleviating financial constraints plays a mediating role in the process of a social network of this new type improving corporate innovation, while mitigating agency conflicts does not. Our conclusions demonstrate that, in the promotion of corporate innovation by the corporate social network, financial constraints have a more profound impact than agency costs.

Online dynamic group-buying community analysis based on high frequency time series simulation

Group-buying often fails even when there are satisfactory quantities as not enough consumers join in the required time, which can waste seller, purchaser, and platform operator time resources; therefore, the group buying features require further research. Over a 3 weeks period, around 700 million click-stream records from 1,061,770 users from a stable and continuous time series were allocated to groups of 5 min frequency, and a hybrid neural network model developed to simulate group-buying behavior in four experiments, from which it was found that adding to the cart and adding as a favorite were significant group-buying behavior features, and shopping depth was the main demographic feature, but age was not. Compared with previous ambiguous online consumer feature conclusions on gender, the results revealed that the commodity feature was the main determinant for gender feature significance. The college student feature was found to be a pseudo feature, and should connect with other fixed effects such as low income or education level. This paper is the first to construct an online dynamic group-buying community, which is a new type of social network and could provide a new perspective for social commerce research. A big data neural network-based method for examining group-buying community behavior over time is proposed that can offer novel insights to online vendors for the development of targeted marketing campaigns.

Co-Location Social Networks: Linking the Physical World and Cyberspace

Various dedicated web services in the cyberspace, e.g., social networks, e-commerce, and instant communications, play a significant role in people’s daily-life. Billions of people around the world access these services through multiple online identifiers (IDs), and interact with each other in both the cyberspace and the physical world. Thanks to the rapid development of wireless and mobile technologies, nowadays these two kinds of interactions are highly relevant with each other. In order to link between the cyberspace and the physical world, we propose a new type of social network, i.e., co-location social network (CLSN). A CLSN contains online IDs describing people’s online presence and offline “encountering” events when people come across each other. By analyzing real data collected from a mainstream ISP in China, which contains 32.7 million IDs across the most popular web services, we build a large-scale CLSN, and explore its unique properties from various aspects. The results indicate that the CLSN is quite different from existing online and offline social networks in terms of classic graph metrics. Moreover, we propose a community-based user identification algorithm to find all online IDs belonging to the same physical user. Using some ground-truth data, we demonstrate that our proposed algorithm achieves a high accuracy in user identification. Finally, we perform a user-centric analysis, and we demonstrate the behavioral difference among different types of users.

Complex Dynamic Event Participant in an Event-Based Social Network: A Three-Dimensional Matching

In recent years, event-based social networks (EBSNs), such as Meetup, Eventbrite and Douban, have emerged as a popular new type of social network on which online users can organize and register for offline social events. Existing approaches focus mainly on arrangement strategies that include users and events on an EBSN platform under an offline scenario, where all information is known in advance. However, these strategies ignore the importance of the organizer, and the offline scenarios can be impractical since all elements appear dynamically in reality. Therefore, we consider not only the user and event in the EBSN platform under the online scenario but also the importance of the organizer. In this paper, we study the complex dynamic event participant in an EBSN that considers three elements: users, events and organizers. We first formalize the event arrangement problem in the online scenario through event arrangement through three-dimensional matching (EATDM). Then, we propose a straightforward solution of the EATDM problem, a greedy algorithm with a competitive ratio, and further develop a basis solution, a random algorithm. We also propose a threshold-based algorithm and a weighted-threshold algorithm with a tighter competitive ratio. Finally, we verify the validity and practicability of the proposed algorithms on synthetic and real datasets, and we find that the weighted-threshold algorithm performs better than the random algorithm, the greedy algorithm and the threshold-based algorithm in terms of the total utility value.

Using Slack to communicate with medical students.

Academic libraries often make use of social networks like Facebook and Twitter to connect with their student users. While the Spokane Academic Library at Washington State University also employs this outreach strategy, the health sciences librarian was able to use a new type of social network called Slack to communicate more directly with the inaugural class of the Elson S. Floyd College of Medicine. As a digital workspace for communication and collaboration, Slack provided the medical librarian with an effective medium through which to post library announcements and updates, as well as have individual conversations with students about library-related questions and concerns.