In this paper, we present an automatic semantic video analysis system to support interdisciplinary research efforts in the field of psychology and media science. The psychological research question studied is whether and how playing violent content in computer games may induce aggression. To investigate this question, the extraction of meaningful content from computer games is required to gain insights into the interrelationship of violent game events and the underlying neurophysiologic basis (brain activity) of a player. Previously, human annotators had to index game content according to the current game state, which is a very time-consuming task. The automatic annotation of a large number of computer game recordings (i.e. videos) speeds up the experimentation process and allows researchers to analyze more experimental data on an objective basis. The proposed computer game video content analysis system for computer games extracts several audiovisual low-level as well as mid-level features and deduces semantic content via a machine learning approach. This system requires manual annotations for a single video only to facilitate the semi-supervised learning process. Finally, human experts are allowed to refine the annotation results via a graphical user interface. Experimental results demonstrate the feasibility of the proposed approach.