arXiv subjects

Thiago C. Silva

Publications and source records attributed to Thiago C. Silva.

9 recordsLinked to original sources

arXiv2026

Auditing automated research assessment: an interpretable machine learning approach to validate funding criteria

This paper empirically examines the practical validity of the official evaluation criteria underpinning the Research Productivity (PQ) Grant framework, as governed by the Brazilian National Council for Scientific and Technological Development (CNPq). By operationalizing regulatory dimensions (including bibliographic output, human resource training, and scientific recognition) as measurable variables extracted from CVs and OpenAlex bibliometric data, we treat policy-defined indicators as testable hypotheses rather than a priori assumptions. Using a block-based adaptation of the Boruta feature selection algorithm across several machine learning classifiers, we evaluate the statistical contribution of each dimension in distinguishing grant levels, with a focus on identifying top-tier (Level 1A) researchers. Our models achieve high predictive performance, with mean AUC scores reaching 0.96, indicating that PQ levels carry a robust and structured statistical signal. However, explanatory power is heavily concentrated within a limited subset of features, specifically bibliographic production, graduate-level supervision and institutional management roles. Conversely, several criteria explicitly emphasized in the regulations demonstrated no detectable statistical contribution to classification outcomes. These findings reveal a potential misalignment between the formal regulatory framework and the effective signals driving evaluation outcomes, suggesting that the practical evaluative signal is substantially more compact than officially stated and providing evidence-based insights for the refinement and transparency of research assessment policies.

cs.DL↗

arXiv2024

Machine learning and economic forecasting: the role of international trade networks

This study examines the effects of de-globalization trends on international trade networks and their role in improving forecasts for economic growth. Using section-level trade data from nearly 200 countries from 2010 to 2022, we identify significant shifts in the network topology driven by rising trade policy uncertainty. Our analysis highlights key global players through centrality rankings, with the United States, China, and Germany maintaining consistent dominance. Using a horse race of supervised regressors, we find that network topology descriptors evaluated from section-specific trade networks substantially enhance the quality of a country's GDP growth forecast. We also find that non-linear models, such as Random Forest, XGBoost, and LightGBM, outperform traditional linear models used in the economics literature. Using SHAP values to interpret these non-linear model's predictions, we find that about half of most important features originate from the network descriptors, underscoring their vital role in refining forecasts. Moreover, this study emphasizes the significance of recent economic performance, population growth, and the primary sector's influence in shaping economic growth predictions, offering novel insights into the intricacies of economic growth forecasting.

econ.GN↗

arXiv2023

Using citation networks to evaluate the impact of text length on the identification of relevant concepts

The identification of the most significant concepts in unstructured data is of critical importance in various practical applications. Despite the large number of methods that have been put forth to extract the main topics of texts, a limited number of studies have probed the impact of the text length on the performance of keyword extraction (KE) methods. In this study, we adopted a network-based approach to evaluate whether keywords extracted from paper abstracts are compatible with keywords extracted from full papers. We employed a community detection method to identify groups of related papers in citation networks. These paper clusters were then employed to extract keywords from abstracts. Our results indicate that while the various community detection methods employed in our KE approach yielded similar levels of accuracy, a correlation analysis revealed that these methods produced distinct keyword lists for each abstract. We also observed that all considered approaches, however, reach low values of accuracy. Surprisingly, text clustering approaches outperformed all citation-based methods. The findings suggest that using different sources of information to extract keywords can lead to significant differences in performance. This effect can play an important role in applications relying upon the identification of relevant concepts.

cs.DL↗

arXiv2022

Using virtual edges to extract keywords from texts modeled as complex networks

Detecting keywords in texts is important for many text mining applications. Graph-based methods have been commonly used to automatically find the key concepts in texts, however, relevant information provided by embeddings has not been widely used to enrich the graph structure. Here we modeled texts co-occurrence networks, where nodes are words and edges are established either by contextual or semantical similarity. We compared two embedding approaches -- Word2vec and BERT -- to check whether edges created via word embeddings can improve the quality of the keyword extraction method. We found that, in fact, the use of virtual edges can improve the discriminability of co-occurrence networks. The best performance was obtained when we considered low percentages of addition of virtual (embedding) edges. A comparative analysis of structural and dynamical network metrics revealed the degree, PageRank, and accessibility are the metrics displaying the best performance in the model enriched with virtual edges.

cs.CL↗

arXiv2020

Modeling Supply-Chain Networks with Firm-to-Firm Wire Transfers

We study a novel economic network (supply chain) comprised of wire transfers (electronic payment transactions) among the universe of firms in Brazil (6.2 million firms). We construct a directed and weighted network in which vertices represent cities and edges connote pairwise economic dependence between cities. Cities (vertices) represent the collection of all firms in that location and links denote intercity wire transfers. We find a high degree of economic integration among cities in the trade network, which is consistent with the high degree of specialization found across Brazilian cities. We are able to identify which cities have a dominant role in the entire supply chain process using centrality network measures. We find that the trade network has a disassortative mixing pattern, which is consistent with the power-law shape of the firm size distribution in Brazil. After the Brazilian recession in 2014, we find that the disassortativity becomes even stronger as a result of the death of many small firms and the consequent concentration of economic flows on large firms. Our results suggest that recessions have a large impact on the trade network with meaningful and heterogeneous economic consequences across municipalities. We run econometric exercises and find that courts efficiency plays a dual role. From the customer perspective, it plays an important role in reducing contractual frictions as it increases economic transactions between different cities. From the supplier perspective, cities that are central suppliers to the supply chain seem to use courts inefficiency as a lawsuit barrier from their customers.

cs.SI↗

arXiv2020

Comparing the impact of subfields in scientific journals

The impact factor has been extensively used in the last years to assess journals visibility and prestige. While the impact factor is useful to compare journals, the specificities of subfields visibility in journals are overlooked whenever visibility is measured only at the journal level. In this paper, we analyze the subfields visibility in a subset of over 450,000 Physics papers. We show that the visibility of subfields is not regular in the considered dataset. In particular years, the variability in subfields impact factor in a journal reached 75% of the average subfields impact factor. We also found that the difference of subfields visibility in the same journal can be even higher than the difference of visibility between different journals. Our results show that subfields impact is an important factor accounting for journals visibility.

cs.DL↗

arXiv2013

Discriminating word senses with tourist walks in complex networks

Patterns of topological arrangement are widely used for both animal and human brains in the learning process. Nevertheless, automatic learning techniques frequently overlook these patterns. In this paper, we apply a learning technique based on the structural organization of the data in the attribute space to the problem of discriminating the senses of 10 polysemous words. Using two types of characterization of meanings, namely semantical and topological approaches, we have observed significative accuracy rates in identifying the suitable meanings in both techniques. Most importantly, we have found that the characterization based on the deterministic tourist walk improves the disambiguation process when one compares with the discrimination achieved with traditional complex networks measurements such as assortativity and clustering coefficient. To our knowledge, this is the first time that such deterministic walk has been applied to such a kind of problem. Therefore, our finding suggests that the tourist walk characterization may be useful in other related applications.

cs.CL↗

arXiv2013

Network-based stochastic competitive learning approach to disambiguation in collaborative networks

Many patterns have been uncovered in complex systems through the application of concepts and methodologies of complex networks. Unfortunately, the validity and accuracy of the unveiled patterns are strongly dependent on the amount of unavoidable noise pervading the data, such as the presence of homonymous individuals in social networks. In the current paper, we investigate the problem of name disambiguation in collaborative networks, a task that plays a fundamental role on a myriad of scientific contexts. In special, we use an unsupervised technique which relies on a particle competition mechanism in a networked environment to detect the clusters. It has been shown that, in this kind of environment, the learning process can be improved because the network representation of data can capture topological features of the input data set. Specifically, in the proposed disambiguating model, a set of particles is randomly spawned into the nodes constituting the network. As time progresses, the particles employ a movement strategy composed of a probabilistic convex mixture of random and preferential walking policies. In the former, the walking rule exclusively depends on the topology of the network and is responsible for the exploratory behavior of the particles. In the latter, the walking rule depends both on the topology and the domination levels that the particles impose on the neighboring nodes. This type of behavior compels the particles to perform a defensive strategy, because it will force them to revisit nodes that are already dominated by them, rather than exploring rival territories. Computer simulations conducted on the networks extracted from the arXiv repository of preprint papers and also from other databases reveal the effectiveness of the model, which turned out to be more accurate than traditional clustering methods.

cs.SI↗

arXiv2013

Word sense disambiguation via high order of learning in complex networks

Complex networks have been employed to model many real systems and as a modeling tool in a myriad of applications. In this paper, we use the framework of complex networks to the problem of supervised classification in the word disambiguation task, which consists in deriving a function from the supervised (or labeled) training data of ambiguous words. Traditional supervised data classification takes into account only topological or physical features of the input data. On the other hand, the human (animal) brain performs both low- and high-level orders of learning and it has facility to identify patterns according to the semantic meaning of the input data. In this paper, we apply a hybrid technique which encompasses both types of learning in the field of word sense disambiguation and show that the high-level order of learning can really improve the accuracy rate of the model. This evidence serves to demonstrate that the internal structures formed by the words do present patterns that, generally, cannot be correctly unveiled by only traditional techniques. Finally, we exhibit the behavior of the model for different weights of the low- and high-level classifiers by plotting decision boundaries. This study helps one to better understand the effectiveness of the model.

physics.soc-ph↗