From English
To English
Estimating arousal, valence, age, gender, big 5 personality traits from audio.
Face detection, arousal and valence for detected faces, body stance estimation.
Uses the WordNet-Affect emotion lexical resource and English part of speech tagging, producing values for 5 basic emotion categories.
Uses the Affective Norms for English Text emotion lexicon, producing VAD emotion estimates.
Distant learning models for emotion detection based on Twitter hash tags for Ekmans six emotions.
A lexicon based emotion detection model providing baseline emotion detection in multiple languages. It uses translations of Princeton wordnet (two character language codes) the open multilingual wordnet (three character language codes).
Sentiment analysis models using LSTM neural networks trained on Stanford treebank movie review data.
Sentiment140 is an open source sentiment detection model.
Uses "Senti-WordNet", a text sentiment lexical resource, to produce sentiment values.
VADER is an open source sentiment detection algorithm utilising gramatical rules and sentiment lexicons.
Java wrapper around several sentiment analysis tools, that was created for MixedEmotions project.
Models to identify suggestions in text.
Spanish topic extraction
Spanish entity extraction.
Entity recognition and linking with Wikipedia entities.