The ARNReduced classifies according to a cosine similarity in
a weighted Vector Space Model with co-occurrences, which are assumed to
capture the style in text.
The EmotionalKeywordSpotter abstract class defines the general structure to perform the
Emotional Keyword Spotting (EKS) process, which detects the words with an affective
content and assigns them the pertinent emotional dimensions.
The EmotionalKeywordSpotterANLW class performs the
Emotional Keyword Spotting (EKS) process using the Affective
Norms Language Words (ANLW) dictionary.
The ExtractCoincidences class checks the coincidences between the
two input emotion tag categorisations and creates one file with these
matches, another file with the predictions produced by EmoLib and a file
containing the original sentences for further study (relation with its
dimensions).
The POSTagger abstract class defines the general structure to perform the
Part-Of-Speech (POS) tagging process, which determines the correct function of a word
in a sentence.
The Tokenizer abstract class defines the general structure to perform the
tokenisation process, which splits a text string into individual units, called tokens.
The WordSenseDisambiguator abstract class defines the general structure to perform the
Word Sense Disambiguation process, which determines the correct sense of polysemous words in context.