Researching integrated explicit and implicit offensive language taxonomy
The STSM “Researching integrated explicit and implicit offensive language taxonomy” held during the period from 05/07/2022 to 10/07/2022 was a perfect opportunity to prepare the dissemination of the use case task 4.1.1 research.
The purpose of the STSM was providing the taxonomy for linguistic processing of offensive language identification by working on refining the annotation model of explicit and implicit offensive language tagging.
First, the integrated model of explicit and implicit offensive language taxonomy was applied to perform the semantic annotation on web-based hate speech datasets in the INCEpTION tool. Then, the experiment data was processed refining our annotation categories. The results led to the more refined offensive explicitness and implicitness categorization criteria. So during the STSM we produced the the refined integrated model of explicit and implicit offensive language taxonomy semantically interoperable and applicable in multilingual contexts. The results of the experiment of refining offensive explicitness and implicitness categorization were presented at the Braga conference on hate speech research (https://sites.google.com/view/hate-speech-conference/call-for-papers). I also learnt a lot about the rich culture of the city of Porto and established new research contacts for scientific collaboration.