Quantum Semantic Correlations in Hate and Non-Hate Speeches
This is an incremental approach for natural language processing researchers, applying quantum concepts to text analysis without clear practical impact.
The paper tackled the problem of characterizing semantic relations between keywords in hate and non-hate speeches using quantum geometry and correlation, comparing it to classical cosine similarity to explore 'similar meaning'.
This paper aims to apply the notions of quantum geometry and correlation to the typification of semantic relations between couples of keywords in different documents. In particular we analysed texts classified as hate / non hate speeches, containing the keywords "women", "white", and "black". The paper compares this approach to cosine similarity, a classical methodology, to cast light on the notion of "similar meaning".