1,720,961 research outputs found
Rilevamento delle comunità nelle reti complesse: limitazioni e nuovi approcci per migliorare la stabilità delle soluzioni
No full textQuesta tesi presenta la ricerca svolta nell'ambito del programma di dottorato in Applied Data Science and Artificial Intelligence, con l'obiettivo di evidenziare come l'analisi delle reti possa fornire una visione quantitativa delle collaborazioni che sono alla base dell'innovazione.
L'innovazione rappresenta una strategia importante per l'industria, la ricerca e per i decisori politici, e la collaborazione tra diverse organizzazioni è spesso un fattore abilitante che è importante conoscere e misurare. Tuttavia, studiare le dinamiche di collaborazione risulta complesso a causa della scarsa disponibilità di dati strutturati. La metodologia proposta in questa tesi segmenta i dati in intervalli temporali, rappresenta le collaborazioni come reti pesate e applica tecniche di analisi delle reti per identificare le organizzazioni più influenti (attraverso misure di centralità) e le comunità coese (mediante algoritmi di community detection). Il confronto tra le reti in periodi successivi permette di osservare e quantificare l'evoluzione delle collaborazioni.
La metodologia è stata inizialmente testata su reti artificiali per verificarne l'efficacia e facilitare la comprensione dei risultati. Questo ha permesso di mettere in luce alcune problematiche, tra cui la variabilità dei risultati prodotti dagli algoritmi di community detection, la necessità di validare tali risultati e la dipendenza dall'ordine di inserimento dei dati in ingresso (input ordering bias).
La ricerca ha portato a una ridefinizione del ruolo dell'algoritmo di community detection, sottolineando come non sia corretto considerare i risultati ottenuti come soluzione, ma piuttosto come un punto all'interno di uno spazio delle soluzioni. Di conseguenza, il processo di individuazione delle comunità segue un flusso di lavoro articolato che prevede: generazione delle soluzioni, verifica della stabilità dei risultati e, in caso di soluzioni multiple, applicazione di una procedura di consenso per ottenere una soluzione univoca. Inoltre, il processo introduce coefficienti di incertezza a livello di nodo e diverse modalità di gestione degli outliers.
I risultati della ricerca includono la pubblicazione di una libreria in linguaggio R e alcuni dataset, con licenza CC-BY in repository aperti. La metodologia e il software sono stati applicati a due casi di studio: le collaborazioni tra industria e ricerca in Friuli Venezia Giulia e i progetti Horizon nel settore dell'idrogeno. Questi studi dimostrano l'efficacia dell'analisi delle reti nel rivelare le dinamiche collaborative.This thesis presents research conducted as part of the PhD program in Applied Data Science and Artificial Intelligence, with the aim of demonstrating how network analysis can offer a quantitative understanding of collaborations that drive innovation.
Innovation is a fundamental strategy for many organizations and policymakers, with collaboration between companies, research centers, and universities playing a crucial role in this process. However, studying collaboration dynamics is challenging due to the lack of structured data and the complexity of the analysis. The proposed methodology segments the data into temporal periods, represents collaborations as weighted networks, and applies network analysis techniques to identify the most influential organizations (using centrality measures) and cohesive groups (through community detection algorithms). By comparing these networks over time, the evolution of collaborations can be observed and quantified.
The methodology was first tested on artificial networks to verify its effectiveness and improve clarity of exposition. This revealed several issues, including the variability of results produced by community detection algorithms, the need to validate the outputs, and the dependence on the order in which input data is provided. The research redefined the role of community detection algorithms, showing that they do not provide the solution, but rather one point within a solution space. Consequently, the process of identifying communities in networks follows a more nuanced approach: generating possible solutions, verifying their stability, and, in cases of multiple solutions, applying a consensus procedure to reach a definitive result. The process also introduces node-level uncertainty coefficients and different strategies for managing outliers.
Research results include an R library and open access datasets published in open repositories. The methodology and software were applied to two case studies: collaborations between industry and research in Friuli Venezia Giulia and Horizon projects in the hydrogen sector. These studies demonstrate the effectiveness of network analysis in revealing collaboration dynamics
A comprehensive framework for solution space exploration in community detection
Full text linkCommunity detection algorithms are essential tools for understanding complex networks, yet their results often vary between runs and are affected by node input order and the presence of outliers, undermining reproducibility and interpretation. This paper addresses these issues by introducing a framework for systematic exploration of the solution space, obtained through repeated runs of a given algorithm with permuted node orders. A Bayesian model assesses convergence, estimates solution probabilities, and provides a defensible stopping rule that balances accuracy and computational cost. Building on this process, we propose a taxonomy of solution spaces that offers clear diagnostics of partition reliability across algorithms and a shared vocabulary for interpretation. Applied to a real-world network, the approach shows that different algorithms produce various types of solution space, highlighting the importance of systematic exploration of the solutions before drawing scientific conclusions
Mapping leadership and communities in EU-funded research through network analysis
No full textBackground: Horizon 2020 and Horizon Europe are flagship programs of the European Union aimed at supporting research and innovation, fostering collaboration among companies, academic institutions, and research organizations. Comprehensive data on projects, objectives, participants, funding details, and results of Horizon projects is available through the open access portal CORDIS (Community Research and Development Information Service). This paper introduces a novel methodology for utilizing CORDIS data to reveal collaborations, leadership roles, and their evolution over time. Methods: The methodology is based on network analysis. Data is downloaded from the CORDIS portal, enriched, segmented by year and transformed into weighted networks representing collaborations between organizations. Centrality measures are used to assess the influence of individual organizations, while community detection algorithms are used to identify stable collaborations. Temporal analysis tracks the evolution of these roles and communities over time. To ensure robust and reliable results, the methodology addresses challenges such as input-ordering bias and result variability, while the exploration of the solution space enhances the accuracy of identified collaboration patterns. Results: To illustrate the approach, the methodology is applied to a specific case: analyse the evolution of collaborations in hydrogen valleys, in the broader frame of “hydrogen energy” research and innovation projects funded by Horizon programmes. Conclusions: The proposed methodology effectively identifies influential organizations and tracks the stability of research collaborations. The insights gained are valuable for policy-makers and organizations seeking to foster innovation through sustained partnerships. This approach can be extended to other sectors, offering a framework for understanding the impact of EU research funding on collaboration and leadership dynamics
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Full text linkWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Dispelling the Myths Behind First-author Citation Counts
Full text linkWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
koamabayili/VECTRON-author-checklist: VECTRON author checklist
No full textWe have done our best to complete the author checklist relating to the use of animals in the hut study. Note that the objective for the hut study was to evaluate the IRS treatment applications for residual efficacy against Anopheles mosquitoes, including the local An. coluzzii mosquito population. Cows were only used to attract mosquitoes into the huts and no tests were carried out directly on the cows. The author checklist is intended for use with studies where experiments are carried out on animals, which is why we have had such difficulty in completing this for the hut study, as many of the questions do not relate to how the cows were used
- …
