arXiv subjects

Diego R. Amancio

Publications and source records attributed to Diego R. Amancio.

At least 19 recordsLinked to original sources

arXiv2026

From Node2Vec to GPT-based GraphRAG: scientific impact prediction across graph and language models

Identifying which newly published scientific papers are likely to become highly cited is important for prioritizing research attention, supporting editorial decisions, and guiding the allocation of scientific resources, particularly under cold-start conditions where little direct evidence is available at publication time. In this work, we formulate impact prediction as a cohort-normalized top-P% classification task and compare graph-based and LLM-based approaches under a unified framework. We construct citation and textual-similarity graphs under temporal constraints and generate Node2Vec representations, either alone or combined with OpenAI text embeddings. The best supervised configuration combines directed citation graphs with textual embeddings, reaching approximately 0.84-0.85 AUC. We also evaluate a GPT-based GraphRAG setup, using GPT 5.5 and 5.4 Nano, in which graph neighborhoods are used as contextual evidence for prediction. Although the LLM-based approach achieves high performance, retrieved context does not consistently improve results; target-only prompts often perform as well as or better than GraphRAG prompts achieving the 0.87 mark. These findings indicate that structural and textual signals are complementary for supervised prediction, while retrieval augmentation must be carefully evaluated against simpler LLM baselines.

cs.DL↗

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↗

arXiv2025

Recovering link-weight structure in complex networks with weight-aware random walks

Using edge weights is essential for modeling real-world systems where links possess relevant information, and preserving this information in low-dimensional representations is relevant for classification and prediction tasks. This paper systematically investigates how different random walk strategies - traditional unweighted, strength-based, and fully weight-aware - keeps edge weight information when generating node embeddings. Using network models, real-world graphs, and networks subjected to low-weight edge removal, we measured the correlation between original edge weights and the similarity of node pairs in the embedding space generated by random walk strategies. Our results consistently showed that weight-aware random walks significantly outperform other strategies, achieving correlations above 0.90 in network models. However, performance in real-world networks was more heterogeneous, influenced by factors like topology and weight distribution. Our analysis also revealed that removing weak edges via thresholding can initially improve correlation by reducing noise, but excessive pruning degrades representation quality. Our findings suggest that simply using a weight-aware random walk is generally the best approach for preserving node weight information in embeddings, but it is not a universal solution.

cs.SI↗

arXiv2025

Leveraging GANs for citation intent classification and its impact on citation network analysis

Citations play a fundamental role in the scientific ecosystem, serving as a foundation for tracking the flow of knowledge, acknowledging prior work, and assessing scholarly influence. In scientometrics, they are also central to the construction of quantitative indicators. Not all citations, however, serve the same function: some provide background, others introduce methods, or compare results. Therefore, understanding citation intent allows for a more nuanced interpretation of scientific impact. In this paper, we adopted a GAN-based method to classify citation intents. Our results revealed that the proposed method achieves competitive classification performance, closely matching state-of-the-art results with substantially fewer parameters. This demonstrates the effectiveness and efficiency of leveraging GAN architectures combined with contextual embeddings in intent classification task. We also investigated whether filtering citation intents affects the centrality of papers in citation networks. Analyzing the network constructed from the unArXiv dataset, we found that paper rankings can be significantly influenced by citation intent. All four centrality metrics examined- degree, PageRank, closeness, and betweenness - were sensitive to the filtering of citation types. The betweenness centrality displayed the greatest sensitivity, showing substantial changes in ranking when specific citation intents were removed.

cs.DL↗

arXiv2025

Graph machine learning for flight delay prediction due to holding manouver

Flight delays due to holding maneuvers are a critical and costly phenomenon in aviation, driven by the need to manage air traffic congestion and ensure safety. Holding maneuvers occur when aircraft are instructed to circle in designated airspace, often due to factors such as airport congestion, adverse weather, or air traffic control restrictions. This study models the prediction of flight delays due to holding maneuvers as a graph problem, leveraging advanced Graph Machine Learning (Graph ML) techniques to capture complex interdependencies in air traffic networks. Holding maneuvers, while crucial for safety, cause increased fuel usage, emissions, and passenger dissatisfaction, making accurate prediction essential for operational efficiency. Traditional machine learning models, typically using tabular data, often overlook spatial-temporal relations within air traffic data. To address this, we model the problem of predicting holding as edge feature prediction in a directed (multi)graph where we apply both CatBoost, enriched with graph features capturing network centrality and connectivity, and Graph Attention Networks (GATs), which excel in relational data contexts. Our results indicate that CatBoost outperforms GAT in this imbalanced dataset, effectively predicting holding events and offering interpretability through graph-based feature importance. Additionally, we discuss the model's potential operational impact through a web-based tool that allows users to simulate real-time delay predictions. This research underscores the viability of graph-based approaches for predictive analysis in aviation, with implications for enhancing fuel efficiency, reducing delays, and improving passenger experience.

cs.LG↗

arXiv2024

Probing the statistical properties of enriched co-occurrence networks

Recent studies have explored the addition of virtual edges to word co-occurrence networks using word embeddings to enhance graph representations, particularly for short texts. While these enriched networks have demonstrated some success, the impact of incorporating semantic edges into traditional co-occurrence networks remains uncertain. This study investigates two key statistical properties of text-based network models. First, we assess whether network metrics can effectively distinguish between meaningless and meaningful texts. Second, we analyze whether these metrics are more sensitive to syntactic or semantic aspects of the text. Our results show that incorporating virtual edges can have positive and negative effects, depending on the specific network metric. For instance, the informativeness of the average shortest path and closeness centrality improves in short texts, while the clustering coefficient's informativeness decreases as more virtual edges are added. Additionally, we found that including stopwords affects the statistical properties of enriched networks. Our results can serve as a guideline for determining which network metrics are most appropriate for specific applications, depending on the typical text size and the nature of the problem.

cs.CL↗

arXiv2024

Predicting citation impact of research papers using GPT and other text embeddings

The impact of research papers, typically measured in terms of citation counts, depends on several factors, including the reputation of the authors, journals, and institutions, in addition to the quality of the scientific work. In this paper, we present an approach that combines natural language processing and machine learning to predict the impact of papers in a specific journal. Our focus is on the text, which should correlate with impact and the topics covered in the research. We employed a dataset of over 40,000 articles from ACS Applied Materials and Interfaces spanning from 2012 to 2022. The data was processed using various text embedding techniques and classified with supervised machine learning algorithms. Papers were categorized into the top 20% most cited within the journal, using both yearly and cumulative citation counts as metrics. Our analysis reveals that the method employing generative pre-trained transformers (GPT) was the most efficient for embedding, while the random forest algorithm exhibited the best predictive power among the machine learning algorithms. An optimized accuracy of 80\% in predicting whether a paper was among the top 20% most cited was achieved for the cumulative citation count when abstracts were processed. This accuracy is noteworthy, considering that author, institution, and early citation pattern information were not taken into account. The accuracy increased only slightly when the full texts of the papers were processed. Also significant is the finding that a simpler embedding technique, term frequency-inverse document frequency (TFIDF), yielded performance close to that of GPT. Since TFIDF captures the topics of the paper we infer that, apart from considering author and institution biases, citation counts for the considered journal may be predicted by identifying topics and "reading" the abstract of a paper.

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

Comparing biased random walks in graph embedding and link prediction

Random walks find extensive application across various complex network domains, including embedding generation and link prediction. Despite the widespread utilization of random walks, the precise impact of distinct biases on embedding generation from sequence data and their subsequent effects on link prediction remain elusive. In this study, we conduct a comparative analysis of several random walk strategies, each rooted in different biases: true self-avoidance, unbiased randomness, bias towards node degree, and inverse node degree bias. Furthermore, we explore diverse adaptations of the node2vec algorithm to induce distinct exploratory behaviors. Our empirical findings demonstrate that despite the varied behaviors inherent in these embeddings, only slight performance differences manifest in the context of link prediction. This implies the resilient recovery of network structure, regardless of the specific walk heuristic employed to traverse the network. Consequently, the results suggest that data generated from sequences governed by unknown mechanisms can be successfully reconstructed.

cs.SI↗

arXiv2023

Using Full-Text Content to Characterize and Identify Best Seller Books

Artistic pieces can be studied from several perspectives, one example being their reception among readers over time. In the present work, we approach this interesting topic from the standpoint of literary works, particularly assessing the task of predicting whether a book will become a best seller. Dissimilarly from previous approaches, we focused on the full content of books and considered visualization and classification tasks. We employed visualization for the preliminary exploration of the data structure and properties, involving SemAxis and linear discriminant analyses. Then, to obtain quantitative and more objective results, we employed various classifiers. Such approaches were used along with a dataset containing (i) books published from 1895 to 1924 and consecrated as best sellers by the Publishers Weekly Bestseller Lists and (ii) literary works published in the same period but not being mentioned in that list. Our comparison of methods revealed that the best-achieved result - combining a bag-of-words representation with a logistic regression classifier - led to an average accuracy of 0.75 both for the leave-one-out and 10-fold cross-validations. Such an outcome suggests that it is unfeasible to predict the success of books with high accuracy using only the full content of the texts. Nevertheless, our findings provide insights into the factors leading to the relative success of a literary work.

cs.CL↗

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

Identifying the perceived local properties of networks reconstructed from biased random walks

Many real-world systems give rise to a time series of symbols. The elements in a sequence can be generated by agents walking over a networked space so that whenever a node is visited the corresponding symbol is generated. In many situations the underlying network is hidden, and one aims to recover its original structure and/or properties. For example, when analyzing texts, the underlying network structure generating a particular sequence of words is not available. In this paper, we analyze whether one can recover the underlying local properties of networks generating sequences of symbols for different combinations of random walks and network topologies. We found that the reconstruction performance is influenced by the bias of the agent dynamics. When the walker is biased toward high-degree neighbors, the best performance was obtained for most of the network models and properties. Surprisingly, this same effect is not observed for the clustering coefficient and eccentric, even when large sequences are considered. We also found that the true self-avoiding displayed similar performance as the one preferring highly-connected nodes, with the advantage of yielding competitive performance to recover the clustering coefficient. Our results may have implications for the construction and interpretation of networks generated from sequences.

cs.SI↗

arXiv2022

Recovering network topology and dynamics via sequence characterization

Sequences arise in many real-world scenarios; thus, identifying the mechanisms behind symbol generation is essential to understanding many complex systems. This paper analyzes sequences generated by agents walking on a networked topology. Given that in many real scenarios, the underlying processes generating the sequence is hidden, we investigate whether the reconstruction of the network via the co-occurrence method is useful to recover both the network topology and agent dynamics generating sequences. We found that the characterization of reconstructed networks provides valuable information regarding the process and topology used to create the sequences. In a machine learning approach considering 16 combinations of network topology and agent dynamics as classes, we obtained an accuracy of 87% with sequences generated with less than 40% of nodes visited. Larger sequences turned out to generate improved machine learning models. Our findings suggest that the proposed methodology could be extended to classify sequences and understand the mechanisms behind sequence generation.

cs.SI↗

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↗

arXiv2022

Text characterization based on recurrence networks

Several complex systems are characterized by presenting intricate characteristics taking place at several scales of time and space. These multiscale characterizations are used in various applications, including better understanding diseases, characterizing transportation systems, and comparison between cities, among others. In particular, texts are also characterized by a hierarchical structure that can be approached by using multi-scale concepts and methods. The multiscale properties of texts constitute a subject worth further investigation. In addition, more effective approaches to text characterization and analysis can be obtained by emphasizing words with potentially more informational content. The present work aims at developing these possibilities while focusing on mesoscopic representations of networks. More specifically, we adopt an extension to the mesoscopic approach to represent text narratives, in which only the recurrent relationships among tagged parts of speech (subject, verb and direct object) are considered to establish connections among sequential pieces of text (e.g., paragraphs). The characterization of the texts was then achieved by considering scale-dependent complementary methods: accessibility, symmetry and recurrence signatures. In order to evaluate the potential of these concepts and methods, we approached the problem of distinguishing between literary genres (fiction and non-fiction). A set of 300 books organized into the two genres was considered and were compared by using the aforementioned approaches. All the methods were capable of differentiating to some extent between the two genres. The accessibility and symmetry reflected the narrative asymmetries, while the recurrence signature provided a more direct indication about the non-sequential semantic connections taking place along the narrative.

cs.CL↗

arXiv2021

Analyzing the influence of prolific collaborations on authors productivity and visibility

Science has become more collaborative over the past years, a phenomenon that is related to the increase in the number of authors per paper and the emergence of interdisciplinary works featuring specialists of different fields. In such a environment, it is not trivial to quantify the individual impact of researchers. Here we analyze how the most prolific collaboration tie (in terms of co-produced works) of an established researcher influences their productivity and visibility metrics. In particular, we check how the number of produced works, citations and h-index rank of an researcher changes when their works also coauthored by their prolific collaborators are not considered. We observed different patterns of prolific collaborator influence across the major fields of knowledge. More specifically, in formal and applied sciences, the prolific collaborators seem to play an important role to the visibility metrics of authors even when they are among the highly cited. Such a results can help stakeholders to better understand the collaboration patterns and draw measures of success that also consider collaboration ties.

cs.DL↗

arXiv2021

A pattern recognition approach for distinguishing between prose and poetry

Poetry and prose are written artistic expressions that help us to appreciate the reality we live. Each of these styles has its own set of subjective properties, such as rhyme and rhythm, which are easily caught by a human reader's eye and ear. With the recent advances in artificial intelligence, the gap between humans and machines may have decreased, and today we observe algorithms mastering tasks that were once exclusively performed by humans. In this paper, we propose an automated method to distinguish between poetry and prose based solely on aural and rhythmic properties. In other to compare prose and poetry rhythms, we represent the rhymes and phones as temporal sequences and thus we propose a procedure for extracting rhythmic features from these sequences. The classification of the considered texts using the set of features extracted resulted in a best accuracy of 0.78, obtained with a neural network. Interestingly, by using an approach based on complex networks to visualize the similarities between the different texts considered, we found that the patterns of poetry vary much more than prose. Consequently, a much richer and complex set of rhythmic possibilities tends to be found in that modality.

cs.CL↗

arXiv2021

On predicting research grants productivity

Understanding the reasons associated with successful proposals is of paramount importance to improve evaluation processes. In this context, we analyzed whether bibliometric features are able to predict the success of research grants. We extracted features aiming at characterizing the academic history of Brazilian researchers, including research topics, affiliations, number of publications and visibility. The extracted features were then used to predict grants productivity via machine learning in three major research areas, namely Medicine, Dentistry and Veterinary Medicine. We found that research subject and publication history play a role in predicting productivity. In addition, institution-based features turned out to be relevant when combined with other features. While the best results outperformed text-based attributes, the evaluated features were not highly discriminative. Our findings indicate that predicting grants success, at least with the considered set of bibliometric features, is not a trivial task.

cs.DL↗