This paper presents our experimental work on a
new kind of domain specific feature-based heuristic for
aspect-level sentiment analysis of movie reviews. We have
devised an aspect oriented scheme that analyses the textual
reviews of a movie and assign it a sentiment label on each
aspect. The scores on each aspect from multiple reviews are
then aggregated and a net sentiment profile of the movie is
generated on all parameters. We have used a SentiWordNet
based scheme with two different linguistic feature selections
comprising of adjectives, adverbs and verbs and n-gram
feature extraction. We have also used our SentiWordNet
scheme to compute the document-level sentiment for each
movie reviewed and compared the results with results
obtained using Alchemy API. The sentiment profile of a
movie is also compared with the document-level sentiment
result. The results obtained show that our scheme produces
a more accurate and focused sentiment profile than the
simple document-level sentiment analysis.
Keywords: Sentiment Analysis, SentiWordNet, Aspect
Oriented Sentiment Analysis, Movie Review Mining.