Graduation presentations (data music, mood-based movie recommenders, ...)
All are welcome to the graduation presentations of Media Technology MSc graduates Aurimas Bavarskis, Tijl Kindt and Roberto Ramadhin.
Wednesday June 26th, 14h40- 17h00
Snellius building room B2, Niels Bohrweg 1, 2333CA Leiden
14.45 - 15.20h Aurimas Bavarskis
15.30 - 16.05h Roberto Ramadhin
16.15 - 16.50h Tijl Kindt
Data Music—Creating Machine Interpretable Musical Structures Using Data-Modulated Audio Signals
ABSTRACT: This paper discusses a way of creating musical structures by generating and combining data-modulated signals. Those can be analyzed and decoded by a machine interpreter. Audio Frequency Shift Keying modulation technique is used to demonstrate how data can be translated into music. The goal of such exploration is to show that sound as a medium is capable of storing about any information possible. Thereby, music composition as an artistic practice may stretch beyond the borders of conventional techniques of sound organization towards a data driven approach.
Supervisor: Edwin van der Heide
Determining a movie’s affective influence for use in mood-based movie recommenders
ABSTRACT: Finding a good movie to watch is getting more difficult in this day and age because of the huge availability. Movie recommendations are thus getting more important. Mood-based and context-aware recommenders could help improve these by taking your mood and context into account. In this paper, we constructed affective ‘profiles’ for movies that potentially characterize their affective influence on viewer’s moods. We then gathered data about people’s moods before and after watching movies to use these affective profiles in predicting viewer’s moods after the movie. We found that a linear model armed with these affective profiles and information about people’s mood and an estimated score for the movie could explain 22% of the variance in moods. While not perfect, we believe this shows that affective movie profiles combined with traditional recommender systems could successfully use people’s moods to improve movie recommendations.
Supervisor: Maarten Lamers