A key aspect that affect many deep underground mines over the world is the rockburst phenomenon, which can have a strong impact in terms of costs and lives. Accordingly, it is important their understanding in order to support decision makers when such events occur. One way to obtain a deeper and better understanding of the mechanisms of rockburst is through laboratory experiments. Hence, a database of rockburst laboratory tests was compiled, which was then used to develop predictive models for rockburst maximum stress and rockburst risk indexes through the application of soft computing techniques. The next step is to explore data gathered from in situ cases of rockburst. This study focusses on the analysis of such in situ information in order to build influence diagrams, enumerate the factors that interact in the occurrence of rockburst, and understand the relationships between them. In addition, the in situ rockburst data were also analyzed using different soft computing algorithms, namely artificial neural networks (ANNs). The aim was to predict the type of rockburst, that is, the rockburst level, based on geologic and construction characteristics of the mine or tunnel. One of the main observations taken from the study is that a considerable percentage of accidents occur as a result of excessive loads, generally at depths greater than 1000 m. In addition, it was also observed that soft computing algorithms can give an important contribution on determination of rockburst level, based on geologic and construction-related parameters.