Online communities offer many potential sources of value to individuals and organisations. However, the effectiveness of online communities in delivering benefits such as knowledge sharing depends on the network of social relations within a community. Research in this area aims to understand and op-timize such networks. Researchers in this area employ diverse network creation methods, with little focus on the selection process, the fit of the selected method, or its relative accuracy. In this study we evaluate and compare the performance of four network creation methods. First we review the litera-ture to identify four network creation methods (algorithms) and their underlying assumptions. Using several data sets from an online community we test and compare the accuracy of each method against a baseline (‘actual’) network determined by content analysis. We use visual inspection, network cor-relation analysis and sensitivity analysis to highlight similarities and differences between the methods, and find some differences significant enough to impact study results. Based on our observations we argue for more careful selection of network creation methods. We propose two key guidelines for re-search into social networks that uses unstructured data from online communities. The study contrib-utes to the rigour of methodological decisions underpinning research in this area.