4.7 Review

Do psychological attributes of online review play role in predicting rating? An empirical investigation

Journal

COMPUTERS IN HUMAN BEHAVIOR
Volume 148, Issue -, Pages -

Publisher

PERGAMON-ELSEVIER SCIENCE LTD
DOI: 10.1016/j.chb.2023.107895

Keywords

Online review; Rating prediction; Tobit regression; Product type; Multivariate adaptive regression splines; Linguistic inquiry and word count

Ask authors/readers for more resources

This study fills an important research gap by exploring and validating the role of four psychological attributes in review rating prediction. Tobit regression is used to investigate the relationship between psychological attributes and review rating, and coefficients and p-value statistics are used for experimental validation. Amazon datasets of twenty categories are chosen for establishing relationships and predicting the performance of review rating prediction. The study identifies U-shaped and Inverted U-shaped relationships between attributes and review rating, using Yerkes-Dodson law and diminishing marginal utility theory to explain these curvilinear relationships.
Rating provided by online customers is a process to summarize quality of the product consumed. Extant research on review rating prediction primarily considered the task as classification or regression problem where the objective is to enhance the prediction performance. A few research attempts to exploring the determinants influencing review rating. A major lacuna has been identified in this domain of research where the impact of psychological attributes of reviewers reflected from their writing style and usage of vocabulary have not been investigated much. This study bridges the gap by exploring and validating the role of four psychological attributes driving review rating prediction. Tobit regression has been utilized to investigate the underlying relationship between psychological attributes and review rating. The significance of experimental validation is measured using coefficients and p-value statistic. Amazon datasets of twenty categories are chosen to establish the relationship and predict the performance of the review rating prediction technique. The study identified Ushaped and Inverted U-shaped relationships between attributes and review rating. Yerkes-Dodson law and diminishing marginal utility theory has been utilized to explain the curvilinear relationships. This study paves the path of future research by extending this work to service industry and customer behaviour.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.7
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available