Funding for this research was provided by:
UK Research and Innovation (UKRI grant EP/W011212/1)
H2020 European Research Council (European Union – Horizon 2020 Program under the scheme “INFRAIA-01-2018-2019 – Integrating Activities for Advanced Communities” - Grant Agreement n.871042(“SoBigData++: European Integrated Infrastructure for Social Mining and BigData Analytics” (http://www.sobigdata.eu)).)
Article History
Received: 11 September 2023
Accepted: 1 December 2023
First Online: 13 December 2023
Declarations
:
: This research has received ethics approval by the Sheffield University Ethics Board. While this paper involves generating false claims for research purposes, its overarching goal is to develop effective techniques for identifying already debunked narratives. The synthetically generated false claims dataset is solely for evaluation and will only be made available to academic researchers following careful vetting and a signed contract, in order to prevent public harm or spreading of misinformation. Furthermore, the research demonstrates that <tt>UTDRM</tt> is an effective method for training debunked-narrative retrieval models without the need for annotations, which are often time-consuming, expensive, and limited in scale. The overall aim is to promote ethical technology use and advance misinformation debunking efforts for the benefit of fact-checkers and users in general.
: Not applicable.
: The authors declare that they have no competing interests.