A learning scheme based on similarity functions for affective common-sense reasoning

This paper explores the theory of learning with similarity functions in the context of common-sense reasoning and natural language processing. Based on this theory, the proposed approach (called Sim-Predictor) is characterized by the process of remapping the input space into a new space which is able to convey the similarity between the input pattern and a number of landmarks, i.e., a subset of patterns randomly extracted from the training set. The new learning scheme exhibits the interesting property of relating the dimensionality of the remapped space to the learning abilities of the eventual predictor in a formal fashion. The evaluation phase shows that Sim-Predictor compares positively with ELM and SVM, when addressing the problem of polarity detection in the sentic computing framework, a novel approach to big social data analysis based on the interpretation of the cognitive and affective information associated with natural language (affective common-sense reasoning).