Recent successes in word embedding and document embedding have motivated researchers to explore similar representations for networks and to use such representations for tasks such as edge prediction, node label prediction, and community detection. Existing methods are largely focused on finding distributed representations for unsigned networks and are unable to discover embeddings that respect ...

Social interactions can exhibit either positive or negative linkages, resulting in the abstraction of “signed graphs” or “signed social networks.” The social balance theory implies that a signed social network tends to converge to a balanced state where all individuals are divided into two cohesive groups that are antagonistic to each other. In this paper, we take this implication as a premise,...

With the ever-increasing number of web services registered in service communities, many users are apt to find their interested web services through various recommendation techniques, e.g., Collaborative Filtering (i.e., CF)-based recommendation. Generally, CF-based recommendation approaches can work well, when a target user has similar friends or the target services (i.e., services preferred by...

Motivated by social balance theory, we develop a theory of link classification in signed networks using the correlation clustering index as measure of label regularity. We derive learning bounds in terms of correlation clustering within three fundamental transductive learning settings: online, batch and active. Our main algorithmic contribution is in the active setting, where we introduce a new...

How do social interactions in fictional words? Here we show that network theory can be used to systematically and quantitatively analyse relationships among noble houses and how the web of alliances and conflicts changes over time in the fantasy drama TV series Game of Thrones. Network analysis proved to be a powerful tool in capturing structures and dynamics of the story. Degree distribution a...

Most of the research on social networks has almost exclusively focused on positive links between entities. There are much more insights that we may gain by generalizing social networks to the signed case where both positive and negative edges are considered. One of the reasons why signed social networks have received less attention that networks based on positive links only is the lack of an ex...

In the current article, we extend the literature on fan identification and social identity theory by examining the effects of unscrupulous off-field behaviors of athletes. In doing so, we drew from both social identity theory and Heider’s balance theory to hypothesize a significant interaction between fan identification level and leadership response on fans’ subsequent levels of identification....

The Shifting Balance Genetic Algorithm (SBGA) is a pluggable module for a GA (or any other Evolutionary Algorithm) based on a modification of Sewall Wright’s shifting balance theory. The SBGA is intended to enhance a GA’s ability to adapt to a changing environment. Here we describe the detailed mechanisms required to implement the SBGA as well as an experiment that shows that the SBGA not only ...

Citations are important to track and understand the evolution of human knowledge. At the same time, it is widely accepted that all the citations made in a paper are not equal. However, there is no thorough understanding of how citations are created that explicitly criticize or endorse others. In this paper, we do a detailed study of such citations made within the NLP community by differentiatin...