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.

This paper presents our experimental work on performance evaluation of the SentiWordNet approach for document-level sentiment classification of Movie reviews and Blog posts. We have implemented SentiWordNet approach with different variations of linguistic features, scoring schemes and aggregation thresholds. We used two pre-existing large datasets of Movie Reviews and two Blog post datasets on revolutionary changes in Libya and Tunisia. We have computed sentiment polarity and also its strength for both movie reviews and blog posts. The paper also presents an evaluative account of performance of the SentiWordNet approach with two popular machine learning approaches: Naïve Bayes and SVM for sentiment classification. The comparative performance of the approaches for both movie reviews and blog posts is illustrated through standard performance evaluation metrics of Accuracy, F-measure and Entropy.