The effect of aggregation methods on sentiment classification in Persian reviews

One of the most essential parts of every sentiment analysis application is the aggregation mechanism used to combine results obtained from a lower granularity level into an overall result. In this paper, the effects of the sentiment lexicon, aggregation level, and aggregation method on the sentiment polarity and rating classification of Persian reviews are investigated. To this aim, a new sentiment aggregation method based on the cross-ratio operator is proposed. The results on four Persian review data sets show that the review-level aggregation can improve rating classification, although this approach does not have a positive impact on polarity classification.