User review helpfulness assessment based on sentiment analysis

This paper aims to investigate the relationship between sentiment and review helpfulness and develop a method to fully use sentiment features in review helpfulness assessment. In addition, this paper explores whether product type influences evaluating review helpfulness.

First, a high-quality data set with a manually coded helpfulness score was constructed. Second, detailed research question methods were conducted. Finally, methods were applied to the data set to extract information gain and sentiment scores. Gradient boosting and random forest methods were used to classify the data set with these features through recall, precision and F-measure to understand the research questions.

Review sentiment has a deep relationship with review helpfulness, and it can be a strong predictor of review helpfulness by refining it into more detailed scores; a combination of sentiment scores and information gain works very well on classification for two product types. Product type does not show a significant influence on helpfulness assessment.

This paper provides a different perspective for measuring review sentiment by clarifying the relationship between sentiment and review helpfulness, analysing the role of product type in review helpfulness assessment, and proposing a high-value feature combination. In addition, the author believes that the assessment method can be effectively applied to practical works.