Towards the Modeling of Polarity in a Latin Knowledge Base

In this paper, we describe the process of inclusion of a prior polarity lexicon of Latin lemmas, called LatinAffectus, in a knowledge base of interoperable linguistic resources developed within the LiLa: Linking Latin project. More specifically, a manually-curated list of lemma-sentiment pairs is linked to a comprehensive collection of Latin lemmas by using Semantic Web and Linked Data standards and practices. LatinAffectus is modeled relying on three formal representation frameworks: Lemon and Ontolex to describe the lexicon, and the Marl ontology to describe the sentiment properties of each of its lexical entries. We present the lexicon, the methodology and the results of the linking process, as well as a use case and the planned future work.