Analysis on Opinion Words Extraction in Electronic Product Reviews

Analysis on Opinion Words Extraction in Electronic Product Reviews

Sint Sint Aung (University of Computer Studies, Yangon, Myanmar)
DOI: 10.4018/IJSSSP.2019010103

Abstract

Online user reviews are increasingly becoming important for measuring the quality of different products and services. Sentiment classification or opinion mining involves studying and building a system that collects data from online and examines the opinions. Sentiment classification is also defined as opinion extraction as the computational research area of subjective information towards different products. Opinion mining or sentiment classification has attracted in many research areas because of its usefulness in natural language processing and other area of applications. Extracting opinion words and product features are also important tasks in opinion mining. In this work an unsupervised approach was proposed to extract opinions and product features without training examples. To obtain the dependency relation between the product aspects and opinions, this work used StanfordCoreNLP dependency parser. From these relations, rules are predified to extract product and opinions. The main advantage of this approach is that there is no need for training data and it has domain independence. Acoording to the experimental results, the modified algorithm gets better results than the double propagation algorithm.
Article Preview
Top

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.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 11: 2 Issues (2020): Forthcoming, Available for Pre-Order
Volume 10: 2 Issues (2019): 1 Released, 1 Forthcoming
Volume 9: 4 Issues (2018)
View Complete Journal Contents Listing