The Sentiment of Latin Poetry. Annotation and Automatic Analysis of the Odes of Horace

During the recent years, an always growing number of linguistic resources and automatic systems for sentiment analysis have been developed covering a wide range of languages. However, research in this field is still not much explored for texts written in Classical languages. Working on such languages means dealing with peculiar textual genres such as philosophical, historical or religious treatises, epic narratives, plays and poems. Poems are particularly suitable for sentiment analysis because they tell us about emotions and passions. In this paper, we describe the creation of the first small gold standard of Latin made of poems written by Horace and manually annotated with emotion polarity, but we also report about the results of a set of automatic classification experiments. In particular, we test both a lexicon-based approach, which uses a Latin polarity lexicon called LatinAffectus, and a zero-shot transfer method. We provide details about the methodology adopted for the annotation of the gold standard, the creation of LatinAffectus, the development of our experiments and we give details about the results and the limitations of the proposed approaches.