In last few weeks of Social Network Analysis, I have read briefly about node centrality measures and their significance in SNA. Node centrality measures help us to identify important nodes within the network and researchers often use these measures to predict the outcome of a specific node within a network (Robins, 2015). Centrality measures help us understand how each individual or node within the network may have an impact on others as well as whole network. There are different types of centralities that measure actor’s position with the network. These centralities are degree centrality, closeness centrality, Betweenness centrality, eigenvector centrality, and beta centrality (Robins, 2015). Each type of measuring centrality analyzes an actor in different aspects such as their position, access to other actors, the power they may hold, and a number of connections the hold within the network.
Previously, many studies have used node centrality measures in their research methodology and analysis. The one that caught my attention is a study titled “Applying Social Network Analysis, Centrality Measures in Identification of Climate Change Adaptation Opinion Leaders”. This study was conducted by researchers Othieno Joseph, Mugivane I Fred, Nyaga Philip, Ogara William, and Muchemi Gerald in 2016. The study applies social network analysis using a NodeXL computer program to generate the socio-grams that display the patterns of information flow regarding climate change. The data was collected by using self-administered questionnaires, observation, and key informant interviews.The data collection started from interviewing a farmer who is implementing climate change adaptation agricultural techniques. Then other participants were recruited by utilizing snowball sampling. The goal of this sampling was to identify opinion leaders in the villages who may have a strong influence over other farmer’s decisions to implement climate change adaptation agricultural techniques. The in-degree and out-degree measures of centrality were used to identify opinion leaders from the directed network.
The actors with high in-degree and out-degree centralities were later identified as opinion leaders. Later, researchers interviewed five opinion leaders to understand how they may be influencing information flow within farmer’s communities. They found out that opinion leaders have a unique position within the network as they have great exposure to mass media, consequently, they have access to information related to climate change adaptation. The opinion leaders were also identified as educated as well as respected and trustworthy members of local farming groups. They possessed information and knowledge about modern farming practices, making them very influential in the network of farmers.
The other study which I found interesting is titled “Semantic network analysis of vaccine sentiment in online social media”. The study was conducted by Gloria J. Kang, Sinclair R. Ewing-Nelson, Lauren Mackey, James T. Schlitt, Achla Marathe, Kaja M. Abbas, and Samarth Swarup in 2017. The study “examines the current vaccine sentiment on social media by constructing and analyzing networks of vaccine information from highly shared websites of Twitter users in the United States; and to assist public health communication of vaccines” (Kang et al, 2017). I found this study really interesting as utilizes Twitter data, which is still a new method of collecting data in social and behavioral research. For data collection, the researchers created semantic networks of vaccine-related information that was found on articles shared by Twitter users in the United States.
They analyzed the patterns and most significant concepts that emerged from this data that expressed positive, negative, and neutral sentiments about vaccination. Then, various measures of centralities including degree centrality, Betweenness centrality, closeness centrality, and eigenvector centrality was used to measure the significance and influence of each concept within the semantic network. The result of their study suggested that “positive sentiment network centered around parents and focused on communicating health risks and benefits, highlighting medical concepts such as measles, autism, HPV vaccine, vaccine-autism link, meningococcal disease, and MMR vaccine”. On the other hand, negative network centered around children and focused on skepticism of government organizations that publish scientific evidence that supports positive benefits of the vaccines.
Joseph, O., Fred, M. I., Philip, N., William, O., & Gerald, M. (2016). Applying social network analysis, centrality measures in identification of climate change adaptation opinion leaders. International Journal of Agricultural Research, Innovation and Technology,6(1), 1. doi:10.3329/ijarit.v6i1.29188
Kang, G. J., Ewing-Nelson, S. R., Mackey, L., Schlitt, J. T., Marathe, A., Abbas, K. M., & Swarup, S. (2017). Semantic network analysis of vaccine sentiment in online social media. Vaccine,35(29), 3621-3638. doi:10.1016/j.vaccine.2017.05.052
Robins, G. (2015). Doing social network research: network-based research design for social scientists. Los Angeles, CA: Sage.