Cross-D-vectorizers: a set of feature-spaces for cross-domain sentiment analysis from consumer review

Supervised sentiment classification approaches require labeled training (source) and testing (target) dataset. Generation of such datasets demands substantial time and effort but cross-domain classification minimizes the effort by considering two different domains for source and target datasets. In this paper, we propose Cross-D-Vectorizers i.e., a set of three sentiment n-gram feature-spaces (Lexical-TFIDF, Lex-Delta-TFIDF and SEND) for the purpose of cross-domain analysis. We construct the features by extracting sentiment unigrams combination with intensifiers and negations from the source dataset. By utilizing an existing lexicon the scores of these features are computed in three different procedures. The scores for each feature are computed by multiplying sentiment value with corresponding TFIDF rating, Delta-TFIDF rating and feature-importance-values (FIV) respectively. Importance-value for each SEND (Sentiment wEight ofN-grams inDataset) feature is calculated by multiplying the number of times the feature appears in the review and the logarithm of its inverse frequency in the corpus. We experiment by using Maximum Entropy, Support Vector Machine and K-Nearest Neighbors classifiers on three benchmark datasets and one proposed dataset for cross-domain classification. Proposed approach show improved results in comparison with existing methods. The advantage of our approach is the complexity of system reduces by considering sentiment n-grams as domain independent features instead of any n-grams.