Score embedding, a CNN initialized with per-class word frequencies, reaches about 69% accuracy on ACA tweets and 46% on SST, but its central public-opinion finding is confounded by the imbalanced training labels.
Sentiwordnet 3.0: an enhanced lex- ical resource for sentiment analysis and opinion mining
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2019 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Twitter Sentiment on Affordable Care Act using Score Embedding
Score embedding, a CNN initialized with per-class word frequencies, reaches about 69% accuracy on ACA tweets and 46% on SST, but its central public-opinion finding is confounded by the imbalanced training labels.