2023
DOI: 10.30827/digibug.79779
|View full text |Cite
|
Sign up to set email alerts
|

‘Big data’ y ciencias sociales. Una mirada comparativa a las publicaciones de antropología, sociología y trabajo social

Abstract: Este artículo revisa la bibliografía internacional sobre big data y explora comparativamente la evolución, características y temáticas de las investigaciones que sobre este tema se encuadran en las áreas de antropología, sociología y trabajo social. Se emplean métodos cuantitativos para la descripción y una estrategia analítica de aprendizaje automático no supervisado al objeto de identificar y agrupar los principales tópicos o temáticas de los artículos. Los resultados confirman que el interés sobre los macro… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
1
1

Citation Types

0
2
0
1

Year Published

2024
2024
2024
2024

Publication Types

Select...
2
1
1

Relationship

0
4

Authors

Journals

citations
Cited by 4 publications
(3 citation statements)
references
References 17 publications
0
2
0
1
Order By: Relevance
“…The LDA algorithm is widely used in text mining to identify patterns in word usage, which in turn enables the labelling and categorisation of text sets according to the topics addressed. The choice to carry out clustering before the implementation of topic modeling was based on empirical evidence of improved results, as documented in previous research (Gualda, Taboada-Villamarín and Rebollo-Díaz, 2023). Finally, the deduction of the titles assigned to each topic is based on the keywords that the model suggests as the most relevant (see Table 2).…”
Section: Topic Classifi Cation and Modelingmentioning
confidence: 99%
“…The LDA algorithm is widely used in text mining to identify patterns in word usage, which in turn enables the labelling and categorisation of text sets according to the topics addressed. The choice to carry out clustering before the implementation of topic modeling was based on empirical evidence of improved results, as documented in previous research (Gualda, Taboada-Villamarín and Rebollo-Díaz, 2023). Finally, the deduction of the titles assigned to each topic is based on the keywords that the model suggests as the most relevant (see Table 2).…”
Section: Topic Classifi Cation and Modelingmentioning
confidence: 99%
“…After the text corpus was tokenized and vectorized, our approach involved a preliminary step before topic modeling. Following the evidence of improved results, we applied the K-means algorithm (Gualda Caballero et al 2023). This unsupervised classification algorithm allows data to be grouped into different clusters based on their proximity, resulting in greater consistency in the prominent words highlighted by the topic modeling.…”
Section: Clustering Using K-meansmentioning
confidence: 99%
“…Desde la perspectiva del científico social, los big data se refieren a la totalidad de los rastros digitales generados por las interacciones entre seres humanos, entre humanos y máquinas, y entre máquinas en el espacio virtual. Investigaciones previas (Gualda et al, 2023) han resaltado que el análisis de texto se ha convertido en uno de los enfoques metodológicos más populares al combinar tecnologías big data con las ciencias sociales. Esta elección se debe principalmente a que un considerable porcentaje de estos rastros digitales se almacena en formato de texto.…”
unclassified