Evolving in-game mood-expressive music with MetaCompose

Marco Scirea, Peter Eklund, Julian Togelius, Sebastian Risi

Research output: Conference Article in Proceeding or Book/Report chapterArticle in proceedingsResearchpeer-review


MetaCompose is a music generator based on a hybrid evolutionary technique that combines FI-2POP and multi-objective optimization. In this paper we employ the MetaCompose music generator to create music in real-time that expresses different
mood-states in a game-playing environment (Checkers). In particular, this paper focuses on determining if differences in player experience can be observed when: (i) using affective-dynamic music compared to static music, and (ii) the music supports the game’s internal narrative/state. Participants were tasked to play two games of Checkers while listening to two (out of three) different set-ups of game-related
generated music. The possible set-ups were: static expression, consistent affective expression, and random affective expression. During game-play players wore a E4 Wristband, allowing various physiological measures to be recorded such as blood volume pulse (BVP) and electromyographic activity (EDA). The data collected confirms a hypothesis based on three out of four criteria (engagement, music quality, coherency with game excitement, and coherency with performance) that players prefer dynamic affective music when asked to reflect on the current game-state. In the future this system could allow designers/composers to easily create affective and dynamic soundtracks for interactive applications
Original languageEnglish
Title of host publicationAM'18 Proceedings of the Audio Mostly 2018 on Sound in Immersion and Emotion
Place of PublicationWrexham, United Kingdom
PublisherAssociation for Computing Machinery
Publication date2018
Article number8
ISBN (Print)978-1-4503-6609-0
Publication statusPublished - 2018
Series Audio Mostly


Dive into the research topics of 'Evolving in-game mood-expressive music with MetaCompose'. Together they form a unique fingerprint.

Cite this