Analyzing scientific context of researchers and communities by using complex network and semantic technologies

Horta, Vitor; Ströele, Victor; Braga, Regina; David, José; Campos, Fernanda

doi:10.1016/j.future.2018.07.012

Cited by 12 publications

(3 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…A social network reflects a social structure that can be represented by individuals or organizations and their relationships. Through this social structure, data, and information exchanged between individuals or organizations can be studied and analyzed at different levels of detail (Horta et al 2018).…”

Section: Structure Analysismentioning

confidence: 99%

“…Scientific Social Networks are specific types of social networks that represent the social interactions of researchers that occur in the scientific environment (Horta et al, 2018). They are very popular in the academic community as a way of understanding the structure of the research community and identifying the top researchers in that community.…”

Section: Structure Analysismentioning

confidence: 99%

See 1 more Smart Citation

A computational literature review of football performance analysis through probabilistic topic modeling

et al. 2021

View full text Add to dashboard Cite

A computational literature review of football performance analysis through probabilistic topic modeling AbstractThis research aims to illustrate the potential use of concepts, techniques, and mining process tools to improve the systematic review process. Therefore, we performed a review on two online databases (Scopus and ISI Web of Science) from 2012 to 2019. We identified 9,649 studies that were analyzed by probabilistic topic modeling procedures in a machine learning approach. The Latent Dirichlet Allocation (LDA) method, chosen for modeling required the stages: 1) data cleansing, 2) data modeling into topics for coherence and perplexity analysis. All research was conducted according to the standards of the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) in a fully computerized way. The computational literature review (CLR) is an integral part of a broader literature review process. The results presented met three criteria: (1) literature review for a research area, (2) analysis and classification of journals, and (3) analysis and classification of academic and individual research teams. A contribution of the article is to demonstrate how the publication's network formed in this particular field of research, and the content of the abstracts can be automatically analyzed to provide a set of research topics for quick understanding and application in future projects. Keywords Football; Performance Analysis; Literature review; Computational literature review; Topic models; LDA IntroductionOver time, methods for conducting systematic reviews have become more rigorous, further prolonging the completion of reviews (Pham et al. 2018), due to finite resources concerning time and effort (Jennex 2015). Among this, a researcher, a doctoral student, or both, to better understanding a research area, needs to quickly get an overview of the literature associated with which journals have the most significant impact and what are the most recent and frequent topics (Mortenson and Vidgen 2016). Thus, researchers contribute to knowledge generation based on searches and promote education. For this, the use of text analysis is beneficial, given the significant increase in the number of electronic research materials in this new era (Lee et al. 2014).Brings scientists new challenges and opportunities due to the characteristics related to the volume, variety, speed of data creation (Chen, Zhong, and Yuan 2016). The systematic literature review (SLR) provides reliable means and established methods for carrying out a comprehensive and robust literature review (Felizardo et al. 2011). However, conducting this researches becomes quite costly due to the studies' growth of 8 to 9% each year, as reported by Bornmann and Mutz (2015). Besides, to being more significant than they used to be, bibliometric datasets are becoming more complex (McLevey and McIlroy-Young 2017).This abundant data requires computational skills to access these vast bibliometric data. Several programming languages used to make access more acces...

show abstract

Section: Structure Analysismentioning

confidence: 99%

Section: Structure Analysismentioning

confidence: 99%

A computational literature review of football performance analysis through probabilistic topic modeling

et al. 2021

View full text Add to dashboard Cite

show abstract

“…The use of complex networks and semantic technologies was explored by Horta et al [10] for the analysis of scientific social networks. They were able to detect overlapping communities based on an algorithm that relies on bidirectional graphs.…”

Section: Carneiro Et Almentioning

confidence: 99%

Special Issue: Big Data for context-aware applications and intelligent environments

Preuveneers

Ilie‐Zudor

2019

Future Generation Computer Systems

View full text Add to dashboard Cite

Disruptive paradigm shifts such as the Internet of Things (IoT) and Cyber-Physical Systems (CPS) are creating a wealth of streaming context information. Large-scale context-awareness combining IoT and Big Data drive the creation of smarter application ecosystems in diverse vertical domains, including smart health, finance, smart grids and cities, transportation, Industry 4.0, etc. This special issue addresses core topics on the design, the use and the evaluation of Big Data enabling technologies to build next-generation context-aware applications and computing systems for future intelligent environments.

show abstract

Extracting knowledge from Deep Neural Networks through graph analysis

Horta

Tiddi

Little

et al. 2021

Future Generation Computer Systems

View full text Add to dashboard Cite

Analyzing scientific context of researchers and communities by using complex network and semantic technologies

Cited by 12 publications

References 17 publications

A computational literature review of football performance analysis through probabilistic topic modeling

A computational literature review of football performance analysis through probabilistic topic modeling

Special Issue: Big Data for context-aware applications and intelligent environments

Extracting knowledge from Deep Neural Networks through graph analysis

Contact Info

Product

Resources

About