Giseli Rabello Lopes

Collaboration recommendation on academic social networks

In the academic context, scientific research works are often performed through collaboration and cooperation between researchers and research groups. Researchers work in various subjects and in several research areas. Identifying new partners to execute joint research and analyzing the level of cooperation of the current partners can be very complex tasks. Recommendation of new collaborations may be a valuable tool for reinforcing and discovering such partners. This paper presents an innovative approach to recommend collaborations on the context of academic Social Networks. Specifically, we introduce the architecture for such approach and the metrics involved in recommending collaborations. We also present an initial case study to validate our approach.

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.

Identifying candidate datasets for data interlinking

One of the design principles that can stimulate the growth and increase the usefulness of the Web of data is URIs linkage. However, the related URIs are typically in different datasets managed by different publishers. Hence, the designer of a new dataset must be aware of the existing datasets and inspect their content to define sameAs links. This paper proposes a technique based on probabilistic classifiers that, given a datasets S to be published and a set T of known published datasets, ranks each Ti ∈ T according to the probability that links between S and Ti can be found by inspecting the most relevant datasets. Results from our technique show that the search space can be reduced up to 85%, thereby greatly decreasing the computational effort.

Recommending Tripleset Interlinking through a Social Network Approach

Tripleset interlinking is one of the main principles of Linked Data. However, the discovery of existing triplesets relevant to be linked with a new tripleset is a non-trivial task in the publishing process. Without prior knowledge about the entire Web of Data, a data publisher must perform an exploratory search, which demands substantial effort and may become impracticable, with the growth and dissemination of Linked Data. Aiming at alleviating this problem, this paper proposes a recommendation approach for this scenario, using a Social Network perspective. The experimental results show that the proposed approach obtains high levels of recall and reduces in up to 90% the number of triplesets to be further inspected for establishing appropriate links.

Two Approaches to the Dataset Interlinking Recommendation Problem

Whenever a dataset t is published on the Web of Data, an exploratory search over existing datasets must be performed to identify those datasets that are potential candidates to be interlinked with t. This paper introduces and compares two approaches to address the dataset interlinking recommendation problem, respectively based on Bayesian classifiers and on Social Network Analysis techniques. Both approaches define rank score functions that explore the vocabularies, classes and properties that the datasets use, in addition to the known dataset links. After extensive experiments using real-world datasets, the results show that the rank score functions achieve a mean average precision of around 60%. Intuitively, this means that the exploratory search for datasets to be interlinked with t might be limited to just the top-ranked datasets, reducing the cost of the dataset interlinking process.

StdTrip+K: Design Rationale in the RDB-to-RDF Process

The design rationale behind the triplification of a relational database is a valuable information source, especially for the process of interlinking published triplesets. Indeed, studies show that the arbitrary use of the owl:sameAs property, without carrying context information regarding the triplesets to be linked, has jeopardized the reuse of the triplesets. This article therefore proposes the StdTrip+K process that integrates a design rationale approach with a triplification strategy. The process supports the reuse of standard RDF vocabularies recommended by W3C for publishing datasets and automatically collects the entire rationale behind the ontology design, using a specific vocabulary called Kuaba+W.

TRTML - A Tripleset Recommendation Tool Based on Supervised Learning Algorithms

The Linked Data initiative promotes the publication of interlinked RDF triplesets, thereby creating a global scale data space. However, to enable the creation of such data space, the publisher of a tripleset \(t\) must be aware of other triplesets that he can interlink with \(t\). Towards this end, this paper describes a Web-based application, called TRTML, that explores metadata available in Linked Data catalogs to provide data publishers with recommendations of related triplesets. TRTML combines supervised learning algorithms and link prediction measures to provide recommendations. The evaluation of the tool adopted as ground truth a set of links obtained from metadata stored in the DataHub catalog. The high precision and recall results demonstrate the usefulness of TRTML.

Applying Gini coefficient to quantify scientific collaboration in researchers network

Some of the metrics more commonly used for Social Networks Analysis (SNA) do not consider the weights of relationships between the actors of the analyzed Social Network, if it exists. These weights aim to measure the importance of the relational ties between actors and also are important to be considered in a SNA. This paper purposes the Gini Coefficient to be applied on Social Networks Analysis. Our initial results demonstrate the validity and applicability of this approach for a collaboration of Brazilian network scientists.

On Materialized sameAs Linksets

The Linked Data initiative promotes the publication of previously isolated databases as interlinked RDF datasets, thereby creating a global scale data space. Datasets are frequently interlinked using some automated matching process that results in a materialized sameAs linkset, that is, a set of links of the form (s, owl:sameAs, o), which asserts that s denotes the same resource as o. This paper proposes strategies to reduce the cognitive overhead of creating materialized sameAs linksets and to correctly maintain them. The paper also outlines an architecture to improve the support for materialized sameAs linksets.

VRRC: web based tool for visualization and recommendation on co-authorship network (abstract only)

Scientific studies are usually developed by contributions from different researchers. Analyzing such collaborations is often necessary, for example, when evaluating the quality of a research group. Also, identifying new partnership possibilities within a set of researchers is frequently desired, for example, when looking for partners in foreign countries. Both analysis and identification are not easy tasks, and are usually done manually. This work presents VRRC, a new approach for visualizing recommendations of people within a co-authorship network (i.e., a graph in which nodes represent researchers and edges represent their co-authorships). VRRC input is a publication list from which it extracts the co-authorships. VRRC then recommends which relations could be created or intensified based on metrics designed for evaluating co-authorship networks. Finally, VRRC provides brand new ways to visualize not only the final recommendations but also the intermediate interactions within the network, including: a complete representation of the co-authorship network; an overview of the collaborations evolution over time; and the recommendations for each researcher to initiate or intensify cooperation. Some visualizations are interactive, allowing to filter data by time frame and highlighting specific collaborations. The contributions of our work, compared to the state-of-art, can be summarized as follows: (i) VRRC can be applied to any co-authorship network, it provides both net and recommendation visualizations, it is a Web-based tool and it allows easy sharing of the created visualizations (existing tools do not offer all these features together); (ii) VRRC establishes graphical representations to ease the visualization of its results (traditional approaches present the recommendation results through simple lists or charts); and (iii) with VRRC, the user can identify not only new possible collaborations but also existing cooperation that can be intensified (current recommendation approaches only indicate new collaborations). This work was partially supported by CNPq, Brazil.