A large body of research aims to detect the spread of something through a social network. This research often entails measuring multiple kinds of relationships among a group of people and then aggregating them into a single social network to use for analysis. The aggregation is typically done by taking a union of the various tie types. Although this has intuitive appeal, we show that in many realistic cases, this approach adds sufficient error to mask true network effects. We show that this can be the case, and demonstrate that the problem depends on: (1) whether the effect diffuses generically or in a tie-specific way, and (2) the extent of overlap between the measured network ties. Aggregating ties when diffusion is tie-specific and overlap is low will negatively bias and potentially mask network effects that are in fact present.
CITATION STYLE
Larson, J. M., & Rodríguez, P. L. (2023). Sometimes Less Is More: When Aggregating Networks Masks Effects. In Studies in Computational Intelligence (Vol. 1077 SCI, pp. 214–223). Springer Science and Business Media Deutschland GmbH. https://doi.org/10.1007/978-3-031-21127-0_18
Mendeley helps you to discover research relevant for your work.