2013/01/24 by Derek Greene, Greene, Derek, Pádraig Cunningham +1 · 2 citations
Computer Science · Physics and Astronomy · #Advanced Graph Neural Networks #Complex Network Analysis Techniques #FOS: Computer and information sciences #FOS: Physical sciences #Physics and Society (physics.soc-ph) #Recommender Systems and Techniques #Social and Information Networks (cs.SI)
paper · pdf · doi:10.48550/arxiv.1301.5809
openalex publication_date 2013/01/24 · openalex created_date 2022/10/03 · openalex updated_date 2026/07/28
In many social networks, several different link relations will exist between\nthe same set of users. Additionally, attribute or textual information will be\nassociated with those users, such as demographic details or user-generated\ncontent. For many data analysis tasks, such as community finding and data\nvisualisation, the provision of multiple heterogeneous types of user data makes\nthe analysis process more complex. We propose an unsupervised method for\nintegrating multiple data views to produce a single unified graph\nrepresentation, based on the combination of the k-nearest neighbour sets for\nusers derived from each view. These views can be either relation-based or\nfeature-based. The proposed method is evaluated on a number of annotated\nmulti-view Twitter datasets, where it is shown to support the discovery of the\nunderlying community structure in the data.\n