Social Network Analysis
Budget: $30 – $250 USD
Covid 19 contact tracing
Covid 19 was declared a global pandemic due to which the whole world suffered. Contact tracing plays an important role in detecting people who are exposed to Covid 19. During this pandemic, contact tracing identifies people with Covid 19 who are exposed and may have infected others. Contact tracing can inform people to quarantine and take safety measures. Social Network Analysis provides healthcare workers with a network approach for analyzing contact records through a network graph. We will create a network using the data containing information related to the spread of covid from one person to another by considering patients as nodes and their contact as edges. We will explore more on how to identify the relation between patients.
We would like to explore the concept of community analysis with our data and apply all the methods, modularity, eigen vector, page rank, centralities and in-degree, out-degree between countries, etc to identify the community having highest number of cases. The network model will be based on the connection between the patients and their importance of spreading it to others. We would like to visualize the network using networkx and other existing libraries. But not pretty sure on what methods we can use to predict the spread. We will explore more on this.
Covid 19 was declared a global pandemic due to which the whole world suffered. Contact tracing plays an important role in detecting people who are exposed to Covid 19. During this pandemic, contact tracing identifies people with Covid 19 who are exposed and may have infected others. Contact tracing can inform people to quarantine and take safety measures. Social Network Analysis provides healthcare workers with a network approach for analyzing contact records through a network graph. We will create a network using the data containing information related to the spread of covid from one person to another by considering patients as nodes and their contact as edges. We will explore more on how to identify the relation between patients.
We would like to explore the concept of community analysis with our data and apply all the methods, modularity, eigen vector, page rank, centralities and in-degree, out-degree between countries, etc to identify the community having highest number of cases. The network model will be based on the connection between the patients and their importance of spreading it to others. We would like to visualize the network using networkx and other existing libraries. But not pretty sure on what methods we can use to predict the spread. We will explore more on this.