Beschreibung von Forschungsthemen pro Forschungsleuchtturm
Forschungsleuchtturm
Institute for Applied Artificial Intelligence
The Institute for Applied Artificial Intelligence strives to bring AI into application, thus bridging the gap between research on the one hand and enterprises and society on the other. By keeping track, assessing recent research and understanding its potential for enterprise applications, the IAAI will help to establish AI as a key future technology.
Knowledge Graphs in the Visual Media Domain
The current research project “Japanese Visual Media Graph” aims to create a research database on Japanese visual media, including, but not limited to anime, manga, computer games and visual novels. It is aimed at researchers in Japan studies who focus on modern media and its expressions, themes, topics, characters and reception. We envision a graph-based, highly interconnected database structure, similar to the Google knowledge graph that is combined with a flexible search interface and analytic tools.
We intend to use the data on Japanese visual media that is being created and curated by the many enthusiast communities on the web. An initial survey of several larger community websites showed an incredible depth of information, a deep understanding of the source material as well as a high attention to details on part of the volunteer contributors. As such, making contact with these communities and learning about their needs and motivations is one of the main project elements. We intend to engage into a meaningful discussion with representatives and administrators of the community sites in order to establish a long-term cooperation that benefits both sides.
The architecture will be completely open source and feature a custom frontend.
We encourage applications with proposals for independent research in the context of this project. Possible topics include:
- Documenting best practices in working with online enthusiast communities
- Creating an ontology for parts of the visual media domain and implementing it using the existing data
- Search and retrieval solutions for specific research questions in the Japanese visual media domain
Name und Kontaktdaten: Prof. Magnus Pfeffer, pfeffer@hdm-stuttgart.de
Fachrichtung, Studiengänge: Informationswissenschaft, Informatik
Notwendiges Vorwissen: Programmierkenntnisse (idealerweise in Python), Grundlagen der Datenstrukturierung und Linked Open Data
Literatur / weiterführende Links:
Project homepage: https://jvmg.iuk.hdm-stuttgart.de/
Annett, Sandra. Anime fan communities: Transcultural flows and frictions. Springer, 2014.
Kiryakos, Senan, and Magnus Pfeffer. “The Benefits of RDF and External Ontologies for Heterogeneous Data: A Case Study Using the Japanese Visual Media Graph.” Information between Data and Knowledge. Information Science and Its Neighbors from Data Science to Digital Humanities. Proceedings of the 16th International Symposium of Information Science (ISI 2021), edited by Thomas Schmidt and Cristian Wolff, Glückstadt: Verlag Werner Hülsbusch, 2021, pp. 308–20, doi:10.5283/epub.44950.
Kiryakos, Senan, et al. "Towards a conceptual framework for superworks." Proceedings of the 7th Conference of Japanese Association for Digital Humanities. 2017.
Paulheim, Heiko. "Knowledge graph refinement: A survey of approaches and evaluation methods." Semantic web 8.3 (2017): 489-508.
Pfeffer, Magnus, and Martin Roth. “Japanese Visual Media Graph: Providing Researchers with Data from Enthusiast Communities.” 2019 Proceedings of the International Conference on Dublin Core and Metadata Applications, edited by Koraljka Golub et al., Dublin Core Metadata Initiative (DCMI), 2020, pp. 136–41, https://dcpapers.dublincore.org/pubs/article/view/4259/2453.
Steinberg, Marc. Anime's media mix: Franchising toys and characters in Japan. U of Minnesota Press, 2012.