The VADER (Valence Aware Dictionary and sEntiment Reasoner) Sentiment Lexicon is now available in GCAM. Unlike the base and NLTK implementations, we are currently using only the VADER lexicon, not the accompanying reasoning logic, and thus are operating the lexicon in classic "bag of words" mode. This means that the order dependent features of VADER such as negation and boosting are currently disabled in the scores generated by GCAM, which rely purely on the order independent summation of appearances of words from the dictionary.
For more information on VADER see its entry on GitHub. When using the VADER scores cite as:
- Hutto, C.J. & Gilbert, E.E. (2014). VADER: A Parsimonious Rule-based Model for Sentiment Analysis of Social Media Text. Eighth International Conference on Weblogs and Social Media (ICWSM-14). Ann Arbor, MI, June 2014.