A Topic Modeling Approach for Exploring Attraction of Dark Souls Series Reviews on Steam

Abstract

The Dark Souls series has always been a landmark masterpiece, and the analysis of its success is meaningful and inspiring for game developers. However, few studies have investigated the attraction of the Dark Souls series from the players’ perspective. Therefore, this research uses a topic model on massive review data of the Dark Souls series to reveal players’ concerns. In this paper, we first collected approximately 130,000 reviews from Steam. Then we used the LDA model to categorize reviews and uncovered 14 and 15 topics from DS3 and DS1, respectively. Among them, we used common 13 topics to find out topics with high frequencies and positive ratings. The results indicate that most game players are satisfied with item and boss fight topics but discontent with the device. Generally, the analysis results from this research provide high interpretability that can further support other studies in this field.