Michele A. Brandão

Using link semantics to recommend collaborations in academic social networks

Social network analysis (SNA) has been explored in many contexts with different goals. Here, we use concepts from SNA for recommending collaborations in academic networks. Recent work shows that research groups with well connected academic networks tend to be more prolific. Hence, recommending collaborations is useful for increasing a groups connections, then boosting the group research as a collateral advantage. In this work, we propose two new metrics for recommending new collaborations or intensification of existing ones. Each metric considers a social principle (homophily and proximity) that is relevant within the academic context. The focus is to verify how these metrics influence in the resulting recommendations. We also propose new metrics for evaluating the recommendations based on social concepts (novelty, diversity and coverage) that have never been used for such a goal. Our experimental evaluation shows that considering our new metrics improves the quality of the recommendations when compared to the state-of-the-art.

The strength of co-authorship ties through different topological properties

Social networks are complex structures that describe individuals (graph nodes) connected in any social context (graph edges). Different metrics can be applied to those networks and their properties in order to understand behavior and even predict the future. One of such properties is tie strength, which allows to identify prominent individuals, analyze how relationships play different roles, predict links, and so on. Here, we specifically address the problem of measuring tie strength in co-authorship social networks (nodes are researchers and edges represent their co-authored publications). We start by presenting four cases that emphasize the problems of current metrics. Then, we propose a new metric for tie strength, called tieness, that is simple to calculate and better differentiates the degrees of strength. Accompanied with a nominal scale, tieness also provides better results when compared to the existing metrics. Our analyses consider three real social networks built from publications collected from digital libraries on Computer Science, Medicine, and Physics. Finally, we also make all datasets publicly available.

CNARe: Co-authorship Networks Analysis and Recommendations

We present CNARe, an easy-to-use online system that shows personalized collaboration recommendations to researchers. It also provides visualizations and metrics that allow to investigate how the recommendations affect a co-authorship social network and other analyses.

Collaboration strength metrics and analyses on GitHub

We perform social analyses over an important community: the open code collaboration network. Specifically, we study the correlation among features that measure the strength of social coding collaboration on GitHub - a Web-based source code repository that can be modeled as a social coding network. We also make publicly available a curated dataset called GitSED, GitHub Socially Enhanced Dataset. Our results have many practical applications such as to improve the recommendation of developers, the evaluation of team formation and existing analysis algorithms.

Bibliographic Analysis to Calculate the Relevance of Publications

A large amount of information available on the Web challenges people to find the relevant ones. Here, we propose a new approach to help researchers to find the best references for given keywords. Such approach is based on the foundations of Lotka and Zipf laws. Also, we apply different information organization techniques to treat, store and index publications available in Scopus database. Our results reveal that our new approach is promising to identify relevant publications.

Who is really in my social circle?: Mining social relationships to improve detection of real communities

Tie strength allows to classify social relationships and identify different types of them. For instance, social relationships can be classified as persistent and similar based respectively on the regularity with which they occur and the similarity among them. On the other hand, rare and somewhat similar relationships are random and cause noise in a social network, thus hiding the actual structure of the network and preventing an accurate analysis of it. In this article, we propose a method to handle social network data that exploits temporal features to improve the detection of communities by existing algorithms. By removing random relationships, we observe that social networks converge to a topology with more pure social relationships and better quality community structures.

Tie strength dynamics over temporal co-authorship social networks

In co-authorship social networks, nodes are authors linked by co-authorship interactions. As time is a relevant aspect of such interactions, concepts and metrics designed to static networks have to be adapted to temporal networks. Tie strength is one of those concepts. Here, we verify if current tie strength definitions are valid for temporal networks by analyzing the strength of ties dynamism over temporal co-authorship networks. Surprisingly, our results show that most ties, even the strong ones, tend to perish over time. Thus, most co-authorships are symbiotic without positive concerns. Also, real co-authorship social networks from different research areas have more weak and random ties than strong and bridge ties.