Study & Explain the Sentiment feature

[alexwalterbos]

The sentiment analysis computes the sentiment intensity in a sentence by using the algorithms proposed in [gilbert2014vader]:

@inproceedings{gilbert2014vader,
  title={Vader: A parsimonious rule-based model for sentiment analysis of social media text},
  author={Gilbert, CJ Hutto Eric},
  booktitle={Eighth International Conference on Weblogs and Social Media (ICWSM-14). Available at (20/04/16) http://comp. social. gatech. edu/papers/icwsm14. vader. hutto. pdf},
  year={2014}
}

Vader stands for 'Valence Aware Dictionary for sEntiment Reasoning'. The algorithm depends on a pre-constructed list list of lexical features and associated sentiment intensity measures, specifically attuned to sentiment in microblog-like contexts [gilbert2014vader]. These lexical features are combined with consideration for five general rules that embody grammatical and syntactical conventions for expressing and emphasizing sentiment intensity [gilbert2014vader]. This algorithm has been implemented in the nltk library. Talos uses this library to get the compound, neg, neu, pos scores which stand for respectively:

• The summarized score
• The score for negative valence
• The score for neutral valence
• The score for positive valence

Talos' solution uses the nltk implementation of 'Vader' to get the 4 described sentiment scores for every sentence in every headline and articleBody. This is the feature vector that is returned.