A Model for Dynamic Game Content Using Semantic Web and Prolog

A common approach for developing video game content is to define it statically. The content is normally created during the game concept layout in order to enable fine control over decisions and story direction, without much space for emergent narrative. For educational games, the narrative can become outdated due to new scientific developments, and may have a low replay value after its concluded. In this paper, we propose a framework capable of collecting data using the semantic web in order to be used as a basis for creating relationships. To do so, we employ Prolog and define facts and rules based on data collected from the semantic web. The proposed approach follows the server-client architecture, allowing multiple clients to work on different data domains and relationships. To evaluate our approach, we developed Dyna Quiz, a trivia-like game that uses dynamically generated content from the semantic web through custom facts and rules considering four domain topics (country, movie, planet, and sport). In addition, we evaluate its latency over network and showed that it takes less than 8 milliseconds to perform 100 inferences at once using a local network, which is sufficient to provide an uninterrupted experience to the final user.