Identification of cohesive subgroups in a university hall of residence during the COVID-19 pandemic using a social network analysis approach

• URL: http://arxiv.org/abs/2402.09213v1
• Date: Wed, 14 Feb 2024 14:48:28 GMT
• Title: Identification of cohesive subgroups in a university hall of residence during the COVID-19 pandemic using a social network analysis approach
• Authors: Pilar Marqu\'es-S\'anchez, Arrate Pinto-Carral, Tania Fern\'andez-Villa, Ana V\'azquez-Casares, Cristina Li\'ebana-Presa and Jos\'e Alberto Ben\'itez-Andrades
• Abstract summary: During the COVID-19 pandemic, young university students have experienced significant changes in their relationships. Previous research has shown the importance of relationship structure in contagion processes. The study provides evidence on the importance of gender, race and the building where they live in creating network structures that favor, or not, contagion during a pandemic.
• Score: 0.0
• License: http://creativecommons.org/licenses/by-nc-nd/4.0/
• Abstract: The aims: (i) analyze connectivity between subgroups of university students, (ii) assess which bridges of relational contacts are essential for connecting or disconnecting subgroups and (iii) to explore the similarities between the attributes of the subgroup nodes in relation to the pandemic context. During the COVID-19 pandemic, young university students have experienced significant changes in their relationships, especially in the halls of residence. Previous research has shown the importance of relationship structure in contagion processes. However, there is a lack of studies in the university setting, where students live closely together. The case study methodology was applied to carry out a descriptive study. The participation consisted of 43 university students living in the same hall of residence. Social network analysis has been applied for data analysis. Factions and Girvan Newman algorithms have been applied to detect the existing cohesive subgroups. The UCINET tool was used for the calculation of the SNA measure. A visualization of the global network will be carried out using Gephi software. After applying the Girvan-Newman and Factions, in both cases it was found that the best division into subgroups was the one that divided the network into 4 subgroups. There is high degree of cohesion within the subgroups and a low cohesion between them. The relationship between subgroup membership and gender was significant. The degree of COVID-19 infection is related to the degree of clustering between the students. College students form subgroups in their residence. Social network analysis facilitates an understanding of structural behavior during the pandemic. The study provides evidence on the importance of gender, race and the building where they live in creating network structures that favor, or not, contagion during a pandemic.

Related papers

• Unsupervised Learning Approaches for Identifying ICU Patient Subgroups: Do Results Generalise? [0.0]
  The use of unsupervised learning to identify patient subgroups has emerged as a potentially promising direction to improve ICU efficiency. It is unclear whether common patient subgroups exist across different ICUs, which would determine whether ICU restructuring could be operationalised in a standardised manner. We extracted 16 features representing medical resource need and used consensus clustering to derive patient subgroups.
  arXiv  Detail & Related papers  (2024-03-05T13:16:37Z)
• A case study of university student networks and the COVID-19 pandemic using a social network analysis approach in halls of residence [0.32985979395737786]
  The aim of our research is to describe the structural behaviour of students in university residences during the COVID-19 pandemic. The leadership on the university residence was measured using centrality measures. Students with higher social reputations experience higher levels of pandemic contagion in relation to COVID-19 infection.
  arXiv  Detail & Related papers  (2024-02-14T14:57:25Z)
• Adolescent relational behaviour and the obesity pandemic: A descriptive study applying social network analysis and machine learning techniques [0.0]
  Aim: To study the existence of subgroups by exploring the similarities between the attributes of the nodes of the groups. Aim: To analyse the connectivity between groups based on aspects of similarities between them through SNA and artificial intelligence techniques.
  arXiv  Detail & Related papers  (2024-02-04T09:19:56Z)
• Language Knowledge-Assisted Representation Learning for Skeleton-Based Action Recognition [71.35205097460124]
  How humans understand and recognize the actions of others is a complex neuroscientific problem. LA-GCN proposes a graph convolution network using large-scale language models (LLM) knowledge assistance.
  arXiv  Detail & Related papers  (2023-05-21T08:29:16Z)
• Ranking-based Group Identification via Factorized Attention on Social Tripartite Graph [68.08590487960475]
  We propose a novel GNN-based framework named Contextualized Factorized Attention for Group identification (CFAG) We devise tripartite graph convolution layers to aggregate information from different types of neighborhoods among users, groups, and items. To cope with the data sparsity issue, we devise a novel propagation augmentation layer, which is based on our proposed factorized attention mechanism.
  arXiv  Detail & Related papers  (2022-11-02T01:42:20Z)
• The Group Loss++: A deeper look into group loss for deep metric learning [65.19665861268574]
  Group Loss is a loss function based on a differentiable label-propagation method that enforces embedding similarity across all samples of a group. We show state-of-the-art results on clustering and image retrieval on four datasets, and present competitive results on two person re-identification datasets.
  arXiv  Detail & Related papers  (2022-04-04T14:09:58Z)
• Inclusive Study Group Formation At Scale [3.5981839346635125]
  We present a scalable system that removes structural obstacles faced by underrepresented students. We aim to provide students from underrepresented groups an experience that is similar in quality to that of students from majority groups.
  arXiv  Detail & Related papers  (2022-02-12T06:38:55Z)
• Heterogeneous Federated Learning via Grouped Sequential-to-Parallel Training [60.892342868936865]
  Federated learning (FL) is a rapidly growing privacy-preserving collaborative machine learning paradigm. We propose a data heterogeneous-robust FL approach, FedGSP, to address this challenge. We show that FedGSP improves the accuracy by 3.7% on average compared with seven state-of-the-art approaches.
  arXiv  Detail & Related papers  (2022-01-31T03:15:28Z)
• Joint estimation of multiple Granger causal networks: Inference of group-level brain connectivity [8.122270502556374]
  This paper considers joint learning of multiple Granger graphical models to discover underlying differential Granger causality structures across multiple time series. Our methods were also applied to available resting-state fMRI time series from the ADHD-200 data sets to learn the differences of causality mechanisms.
  arXiv  Detail & Related papers  (2021-05-15T10:29:02Z)
• Learning Spatial Context with Graph Neural Network for Multi-Person Pose Grouping [71.59494156155309]
  Bottom-up approaches for image-based multi-person pose estimation consist of two stages: keypoint detection and grouping. In this work, we formulate the grouping task as a graph partitioning problem, where we learn the affinity matrix with a Graph Neural Network (GNN) The learned geometry-based affinity is further fused with appearance-based affinity to achieve robust keypoint association.
  arXiv  Detail & Related papers  (2021-04-06T09:21:14Z)
• Social Interactions Clustering MOOC Students: An Exploratory Study [57.822523354358665]
  Comments were categorized based on how students interacted with them, e.g., how a student's comment received replies from peers. Statistical modelling and machine learning were used to analyze comment categorization, resulting in 3 strong and stable clusters.
  arXiv  Detail & Related papers  (2020-08-10T09:32:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.