Detecting profilable and overlapping communities with user-generated multimedia contents in LBSNs

Abstract

In location-based social networks (LBSNs), users implicitly interact with each other by visiting places, issuing comments and/or uploading photos. These heterogeneous interactions convey the latent information for identifying meaningful user groups, namely social communities, which exhibit unique location-oriented characteristics. In this work, we aim to detect and profile social communities in LBSNs by representing the heterogeneous interactions with a multimodality nonuniform hypergraph. Here, the vertices of the hypergraph are users, venues, textual comments or photos and the hyperedges characterize the k-partite heterogeneous interactions such as posting certain comments or uploading certain photos while visiting certain places. We then view each detected social community as a dense subgraph within the heterogeneous hypergraph, where the user community is constructed by the vertices and edges in the dense subgraph and the profile of the community is characterized by the vertices related with venues, comments and photos and their inter-relations. We present an efficient algorithm to detect the overlapped dense subgraphs, where the profile of each social community is guaranteed to be available by constraining the minimal number of vertices in each modality. Extensive experiments on Foursquare data well validated the effectiveness of the proposed framework in terms of detecting meaningful social communities and uncovering their underlying profiles in LBSNs.

Harvesting Multiple Sources for User Profile Learning

“…The data was obtained from three geographical regions with high Foursquare user activity, namely: Singapore London and New York. It can be used for research on user profile learning and other contemporary problems such as venue recommendation [27], user identification across multiple social networks [23], and cross-region user community detection [28]. Considering the sensitivity of users' private information, we release the extracted features instead of the original data.…”

“…Some prior works were devoted to urban user mobility analysis [8][13] [14]; while others focused mostly on location-based user community detection and profiling [27] or market trade area analysis [17]. The user demographic profiling task gained popularity following the works in [18] [21], where participants were asked to build a model to predict user's age and gender based on users' textual posts.…”

Personalized Recommendations of Locally Interesting Venues to Tourists via Cross-Region Community Matching

“…With the extracted users' underlying social dimensions, we seek to first group them according to their latent interests at the regional level [Zhao et al 2013]. There are a number of approaches to detect communities or dense subgroups, such as clustering or community detection.…”

“…In this work, to avoid parameter tuning, we use adaptive affinity propagating (AAP), which improves AP by automatically adjusting the damping factor and preference during the learning process [Wang et al 2008]. Given the set of interest communities detected in each geographical region, we aim to understand and represent each community by means of its group profiles [Zhao et al 2013] so that the correspondences between communities at different regions can be readily created. According to the concept of homophily [McPherson et al 2001], connections occur at a higher rate between similar people than dissimilar …”

New Yorker Melange

“…Rudinac et al proposed a visual summarization approach, using community-contributed images and associated metadata to discover various aspects of a geographic area [9]. Finally, Zhao et al devised a multimodal approach to detecting overlapping communities in Foursquare [12].…”