Abstract
We present a user interface (UI) for browsing collections of
web pages about music artists. Given such a collection, we use a term list
to index its contents and to derive term co-occurrences. Based on these
co-occurrences, we create a UI that employs a variant of the Sunburst visualization
technique. The UI is embedded in CoMIRVA, our framework
for music information retrieval and visualization.
We use two dictionaries of musically relevant terms and derive information
about which terms occur on which web pages. Based on this
information, subsets of the web page collection are created according to
the terms that occur most frequently in the collection. The generated
UI, which we call the Co-Occurrence Browser (COB), thus allows for associating
each artist with its most important (descriptive) terms and for
browsing the respective web pages. To assess the usability of the COB,
we carried out a small qualitative user study. Furthermore, different term
weighting functions used to create the UI were tested and evaluated in
a quantitative user study.
| Original language | German (Austria) |
|---|---|
| Title of host publication | Proceedings of the 2nd Workshop on Learning the Semantics of Audio Signals (LSAS 2008), Paris, France. |
| Number of pages | 14 |
| Publication status | Published - 2008 |
Fields of science
- 102 Computer Sciences
- 102001 Artificial intelligence
- 102003 Image processing
- 102015 Information systems
- 202002 Audiovisual media