Hier finden Sie wissenschaftliche Publikationen aus den Fraunhofer-Instituten.

ENDA: Insights into building a chatbot for open government data

: Meiners, Fritz; Kirstein, Fabian

Fulltext urn:nbn:de:0011-n-6218579 (701 KByte PDF)
MD5 Fingerprint: adbb0555656cb588f71a6dc2ee30dbc5
(CC) by
Created on: 30.1.2021

Virkar, Shefali (Ed.) ; International Federation for Information Processing -IFIP-; International Federation for Information Processing -IFIP-, Working Group Information Systems in Public Administration:
Ongoing Research, Practitioners, Posters, Workshops, and Projects at EGOV-CeDEM-ePart 2020. Proceedings. Online resource : Co-located with the IFIP WG 8.5 International Conference EGOV-CeDEM-ePart 2020, Linköping University, Sweden (Online), 31 August-2 September 2020
Online im WWW, 2020 (CEUR Workshop Proceedings 2797)
International Conference on Electronic Government (EGOV) <2020, Online>
Conference for E-Democracy and Open Government Conference (CeDEM) <2020, Online>
International Conference on eParticipation (ePart) <2020, Online>
Conference Paper, Electronic Publication
Fraunhofer FOKUS ()
Chatbot; linked open data; DCAT-AP

The frictionless access to Open Data via portals and traditional search paradigms currently lacks usability. In order to tackle this problem, we developed a prototype of a chatbot for Open Government Data called ENDA, which is based on the ChatScript framework and the Linked Data specification for public sector datasets DCAT-AP. User requests are mapped to corresponding SPARQL queries using pattern-matching techniques. The initial requirements were derived via a Wizard-of-Oz study involving potential users. During evaluation against the European Data Portal it was revealed that existing limitations hinder the development of a production-grade chatbot.