Zhiyong Yu

Discovering and Profiling Overlapping Communities in Location-Based Social Networks

With the recent surge of location-based social networks (LBSNs), such as Foursquare and Facebook Places, huge digital footprints of peoples locations, profiles, and online social connections become accessible to service providers. Unlike social networks (e.g., Flickr, Facebook) that have explicit groups for users to subscribe to or join, LBSNs usually have no explicit community structure. In order to capitalize on the large number of potential users, quality community detection and profiling approaches are needed. In the meantime, the diversity of peoples interests and behaviors when using LBSNs suggests that their community structures overlap. In this paper, based on the user check-in traces at venues and user/venue attributes, we come out with a novel multimode multi-attribute edge-centric coclustering framework to discover the overlapping and hierarchical communities of LBSNs users. By employing both intermode and intramode features, the proposed framework is not only able to group like-minded users from different social perspectives but also discover communities with explicit profiles indicating the interests of community members. The efficacy of our approach is validated by intensive empirical evaluations using the collected Foursquare dataset.

An OSGi-based infrastructure for context-aware multimedia services

This article proposes an OSGi-based infrastructure for context-aware multimedia services in a smart home environment. A context-aware multimedia middleware (CMM), which supports multimedia content filtering, recommendation, and adaptation according to changing context is presented. It also performs context aggregation, reasoning, and learning. To foster device and service interoperability, CMM is integrated with an OSGi service platform. We envisage the OSGi-based infrastructure to fill the niche of three gateways in a smart home: network connecting, context provisioning, and multimedia personalizing

Tree-Based Mining for Discovering Patterns of Human Interaction in Meetings

Discovering semantic knowledge is significant for understanding and interpreting how people interact in a meeting discussion. In this paper, we propose a mining method to extract frequent patterns of human interaction based on the captured content of face-to-face meetings. Human interactions, such as proposing an idea, giving comments, and expressing a positive opinion, indicate user intention toward a topic or role in a discussion. Human interaction flow in a discussion session is represented as a tree. Tree-based interaction mining algorithms are designed to analyze the structures of the trees and to extract interaction flow patterns. The experimental results show that we can successfully extract several interesting patterns that are useful for the interpretation of human behavior in meeting discussions, such as determining frequent interactions, typical interaction flows, and relationships between different types of interactions.

Capture, recognition, and visualization of human semantic interactions in meetings

Human interaction is one of the most important characteristics of group social dynamics in meetings. In this paper, we propose an approach for capture, recognition, and visualization of human interactions. Unlike physical interactions (e.g., turn-taking and addressing), the human interactions considered here are incorporated with semantics, i.e., user intention or attitude toward a topic. We adopt a collaborative approach for capturing interactions by employing multiple sensors, such as video cameras, microphones, and motion sensors. A multimodal method is proposed for interaction recognition based on a variety of contexts, including head gestures, attention from others, speech tone, speaking time, interaction occasion (spontaneous or reactive), and information about the previous interaction. A support vector machines (SVM) classifier is used to classify human interaction based on these features. A graphical user interface called MMBrowser is presented for interaction visualization. Experimental results have shown the effectiveness of our approach.

Participant Selection for Offline Event Marketing Leveraging Location-Based Social Networks

Offline event marketing invites people to participate in a sponsored gathering, thus allowing marketers to have face-to-face, direct, and close contact with their current and potential customers. This paper presents a framework that supports marketers in improving marketing effectiveness by carefully selecting invitees to such sponsored offline events by leveraging location-based social networks. In particular, we first transform the participant selection task into a combinatorial optimization problem. Second, we propose a marketing effect quantitative model that considers the distance and overlapping social influence. Third, we introduce algorithms to determine a participant team that can maximize the marketing effect while fulfilling the scale and item coverage constraints. We finally evaluate the effectiveness of the framework and validate the proposed marketing effect of the quantitative model with real-world data.

Inferring Human Interactions in Meetings: A Multimodal Approach

Social dynamics, such as human interaction is important for understanding how a conclusion was reached in a meeting and determining whether the meeting was well organized. In this paper, a multimodal approach is proposed to infer human semantic interactions in meeting discussions. The human interaction, such as proposing an idea, giving comments, expressing a positive opinion, etc., implies user role, attitude, or intention toward a topic. Our approach infers human interactions based on a variety of audiovisual and high-level features, e.g., gestures, attention, speech tone, speaking time, interaction occasion, and information about the previous interaction. Four different inference models including Support Vector Machine (SVM), Bayesian Net, Naive Bayes, and Decision Tree are selected and compared in human interaction recognition. Our experimental results show that SVM outperforms other inference models, we can successfully infer human interactions with a recognition rate around 80%, and our multimodal approach achieves robust and reliable results by leveraging on the characteristics of each single modality.

Handling conditional preferences in recommender systems

In this paper, we propose an approach to handle conditional preferences in recommender systems. A quantitative conditional preference model based on domain knowledge is introduced. The inheritance property in concept trees and bipolar property in preference statements are adopted when interpreting conditional preference rules. Group preferences are merged from personal preferences with consideration of manipulability. A graphical user interface is developed for visualization of domain knowledge, conditional preference rules, personal and group preferences.

Cross-domain community detection in heterogeneous social networks

With the recent surge of location-based social networks (LBSNs), e.g., Foursquare and Facebook Places, huge amount of human digital footprints that people leave in the cyber-physical space become accessible, including users’ profiles, online social connections, and especially the places that they have checked in. Different from social networks (e.g., Flickr, Facebook) which have explicit groups for users to subscribe or join, LBSNs usually have no explicit community structure. Meanwhile, unlike social networks which only contain a single type of social interaction, the coexistence of online/offline social interactions and user/venue attributes in LBSNs makes the community detection problem much more challenging. In order to capitalize on the large number of potential users/venues as well as the huge amount of heterogeneous social interactions, quality community detection approach is needed. In this paper, by exploring the heterogenous digital footprints of LBSNs users in the cyber-physical space, we come out with a novel edge-centric co-clustering framework to discover overlapping communities. By employing inter-mode as well as intra-mode features, the proposed framework is able to group like-minded users from different social perspectives. The efficacy of our approach is validated by intensive empirical evaluations based on the collected Foursquare dataset.

Exploiting Personal and Community Context in Mobile Social Networks

Mobile social networks (MSNs) are believed to be more user-friendly and intelligent than online social networks. In this chapter, we first extend the definition of mobile social networks by classifying MSNs into four categories, and define two important terms, e.g., personal context and community context in the emerging field of mobile social networks. We then present the context model and the related taxonomy of personal context and community context. We further divide the life cycle of MSNs into four phases — discovery, connection, interaction, and management — and elaborate how personal context and community context facilitates the process in each phase. Three major data sources for deriving personal and community context in MSNs are identified, e.g., sensor-rich mobile and wearable devices, Internet applications and Web services, and static infrastructure. Leveraging the three data sources, techniques ranging from data representation, data cleansing, and data anonymization to clustering techniques and inference techniques are presented for inferring personal and community context. Finally, future research directions and challenges are identified, in order to shed light on next-generation MSN development from the context-aware perspectives.

Selecting the Best Solvers: Toward Community Based Crowdsourcing for Disaster Management

Crowd sourcing is a new paradigm of service provision. Current commercial crowd sourcing platforms rarely consider the interaction between task takers, which is extremely required in the disaster management scenario. In this paper, we designed a framework for community based crowd sourcing, i.e., task takers are from an existing community or will easily form a new community. A size-specified community creation method using multiple social contexts is also proposed.