Analysis on Opinion Words Extraction in Electronic Product Reviews

Literature Review

There have been many researches about opinion word extraction. Liu (2015) reported that identifies personal sentences and also determines their opinion trends. For subjectivity, supervised learning was applied. For the classification of feelings for each subjective sentence, use a similar method but with many keywords, and the score function is the probability ratio of the record. The same problem was also studied by Asghar et al. (2014) contemplating the qualities and using semi-supervised learning.

The lexicon-based approach (Qiu et al., 2011), and determines the sentiment or polarity of opinion via some function of opinion words in the document or the sentence. As discussed earlier, this method can result in low recall for our entity-level sentiment analysis.

Shariaty and Moghaddam (2011) and Aung and Wai (2018) proposed an approach to finding subjective adjectives using the results of word clustering according to their distributional similarity. However, they did not tackle the prediction of sentiment polarities of the found subjective adjectives.