This year, Kraków is the venue of the international Digital Humanities conference. The Media Informatics Group from Regensburg will present two projects on the computer-based analysis of music and movies.

The complete conference proceedings are available here: http://dh2016.adho.org/abstracts/

1. Computer-based Analysis of Movies

Beyond Shot Lengths – Using Language Data and Color Information as Additional Parameters for Quantitative Movie Analysis

Film studies make use of both, qualitative as well as quantitative methods. While there is a large variety of qualitative approaches to analyze movies, most quantitative attempts seem to be focused on the analysis of the length and frequency of a film’s shots. Cinemetrics been suggested as a term to describe these quantitative, shot-based approaches for analyzing movies. For a comprehensive overview of Cinemetrics-related research cf. the bibliography compiled by Mike Baxter. Cinemetrics is also the name of a large online database that contains information about shot lengths and frequencies for several thousand films.

In our  project we suggest to go „beyond shot lengths“, which means to enhance the existing, shot-focused approaches to quantitative movie analysis by considering additional parameters, such as language and color use.

We present a prototype that can be used to automatically extract and analyze these parameters from movies and that makes the results accessible in an interactive visualization.

Resources

• Full poster (PDF)
• Abstract (online proceedings / PDF)
• Tool demo

2. Computer-based Analysis of Music

Tool-based Identification of Melodic Patterns in MusicXML Documents

Computer-based methods in musicology have been around at least since the 1980s. Typically, quantitative analyses of music rely on music information retrieval (MIR) systems, which can be used to search collections of songs according to different musicological parameters. There are many examples for existing MIR systems, all with specific strengths and weaknesses. Among the main downsides of such systems are:

• Usability problems, i.e. tools are cumbersome to use, as they oftentimes only provide a command-line interface and also require some basic programming skills to utilize them; example: Humdrum
• Restricted scope of querying, i.e. tools can only be used to search for musical incipits; examples: RISM, HymnQuest
• Restricted song collection, i.e. tools can only be used for specific collections of music files; various examples of MIR tools for specific collections are described in Typke et al. (2005)

To make up for these existing downsides, we designed MusicXML Analyzer, a generic MIR system that allows for the analysis of arbitrary documents encoded in MusicXML format.

http://www.youtube.com/watch?v=vHC533ebb1A

Frameworks used for MusiXML Analyzer

• Laravel: PHP framework
• jQuery: JavaScript framework
• Bootstrap: CSS framework
• D3.js: JavaScript library for visualization / diagrams
• Typed.js: JavaScript library for status messages
• Dropzone.js: JavaScript library for file upload
• jsPDF: JavaScript library for PDF export
• Vexflow: JavaScript library for the creation of virtual scores
• Midi.js: JavaScript library for the creation of midi files

References

Typke, R., Wiering, F. and Veltkamp, R. C. (2005). A survey of music information retrieval systems. Proceedings of the 6th International Conference on Music Information Retrieval (ISMIR) 2005, pp. 153–160.

Resources

• Abstract (online proceedings / PDF)
• MusicXML Analyzer on GitHub
• Tool demo