Spatio-Temporal Parsing in Spatial Hypermedia
Abstract
Spatial hypertext represents associations between chunks of information by spatial or visual attributes (such as proximity, color, shape, etc.). This supports expressing information structures implicitly and in an intuitive way. However, automatic recognition of such informal, implicitly encoded structures by a machine (a so-called spatial parser) is still a challenge. Conventional parsers are conceptually restricted by their underlying source of information. Due to this limitation there are various possible structures that cannot be recognized properly, as the machine has no means to detect them. This inevitably limits both the quality of parser output and hence parser performance. In this paper we show that considering temporal aspects in spatial parser design will lead to significant increase in parsing accuracy, detection of richer structures and thus higher parser performance. We call machines that consider such spatial and temporal information spatio-temporal parsers.
For the purpose of providing evidence, parsers for recognizing spatial, visual, and temporal object relations have been implemented and tested in a series of user surveys. One aim was to find out how "close" the machine interpretetation of structures get to human interpretation. It turned out that in none of the test cases pure spatial or visual parser could outperform the spatio-temporal parser. Instead, the spatio-temporal parser was able to compensate limitations of conventional parsers. Furthermore, we have statistically tested parsing accuracy. The results indicate a non-trivial effect that is recognizable by humans. This shows that spatio-temporal parsers produce output that is significantly closer to what knowledge workers intend to express compared to traditional spatial parsers.
mehrMehr zum Titel
| Titel | Spatio-Temporal Parsing in Spatial Hypermedia |
|---|---|
| Medien | Proceedings of the 27th ACM Conference on Hypertext and Social Media (HT'16) |
| Verlag | ACM |
| Heft | --- |
| Band | --- |
| ISBN | --- |
| Verfasser/Herausgeber | Prof. Dr. Thomas Schedel, Prof. Dr. Claus Atzenbeck |
| Seiten | 149–157 |
| Veröffentlichungsdatum | 10.07.2016 |
| Projekttitel | --- |
| Zitation | Schedel, Thomas; Atzenbeck, Claus (2016): Spatio-Temporal Parsing in Spatial Hypermedia. Proceedings of the 27th ACM Conference on Hypertext and Social Media (HT'16), S. 149–157. DOI: 10.1145/2914586.2914596 |