Making linked data observatories accessible to bioscience researchers by blending graphical and conversational interfaces backed by large language models.
Linked data is a set of design principles for structuring information so that it becomes accessible and machine readable. When the data are linked, the resulting graph becomes traversable and nodes are connected through meaningful relationships. Linked data breaks down the information silos that exist between formats and brings down the fences between sources. In addition, linked data follows a specific schema that makes it easier for both machines and humans to understand. Unfortunately, even though the data can be human readable, it is challenging for non-expert users to retrieve it because linked data often requires an understanding of semantic queries such as SPARQL.
This project explores how to make linked data more accessible by allowing non-technical end users—such as bioscience researchers and wildlife conservationists—to perform their work more efficiently. We aim to combine graphical interfaces with conversational AI techniques to facilitate efficient and effective linked data retrieval. Naive users will not need experience using SPARQL or any other query language, and expert users can perform their jobs more quickly.
Omar Mussa, Omer Rana, Benoît Goossens, Pablo Orozco-terWengel, and Charith Perera, *Towards Enhancing Linked Data Retrieval in Conversational UIs using Large Language Models*, Web Information Systems Engineering (WISE 2024), Lecture Notes in Computer Science, Springer Nature Singapore, 2025, pp. 246–261.
Omar Mussa, Omer Rana, Benoît Goossens, Pablo Orozco-terWengel, and Charith Perera, *ForestQB: Enhancing Linked Data Exploration through Graphical and Conversational UIs Integration*, ACM Journal on Computing and Sustainable Societies (JCSS), Volume 2, Issue 3, Article 32, September 2024, pp. 1–33.
Omar Mussa, Omer Rana, Benoît Goossens, Pablo Orozco-terWengel, and Charith Perera, *ForestQB: An Adaptive Query Builder to Support Wildlife Research*, 21st International Semantic Web Conference (Posters & Demonstrations Track), Hangzhou, China, 2022.