While the literature has reached a consensus on the awareness effect of online word-of-mouth (eWOM), this paper studies its persuasive effect—specifically, dimension-specific sentiment effects on product sales.We examine the sentiment information in eWOM along different product dimensions and reveal different persuasive effects on consumers’ purchase decisions based on consumers’ sentiment preference, which is defined as the relative importance that consumers place on various dimension-specific sentiments. We use an aspect-level sentiment analysis to derive dimension-specific sentiment and PVAR (panel vector auto-regression) models, and estimate their effects on product sales using a movie panel dataset. The findings show that three dimension-specific sentiments (star, genre, and plot) are positively related to movie sales.Regarding consumers’ sentiment preferences, we find a positive relationship to movie sales that is stronger for plot sentiment, relative to star sentiment for low-budget movies. For high-budget movies, we find a positive relationship to movie sales that is stronger for star sentiment, relative to plot or genre sentiment.
Online word-of-mouth (eWOM) disseminated on social media contains a considerable amount of important information that can predict sales. However, the accuracy of sales prediction models using big data on eWOM is still unsatisfactory. We argue that eWOM contains the heat and sentiments of product dimensions, which can improve the accuracy of prediction models based on multiattribute attitude theory. In this paper, we propose a dynamic topic analysis (DTA) framework to extract the heat and sentiments of product dimensions from big data on eWOM. Ultimately, we propose an autoregressive heat-sentiment (ARHS) model that integrates the heat and sentiments of dimensions into the benchmark predictive model to forecast daily sales. We conduct an empirical study of the movie industry and confirm that the ARHS model is better than other models in predicting movie box-office revenues. The robustness check with regard to predicting opening-week revenues based on a back-propagation neural network also suggests that the heat and sentiments of dimensions can improve the accuracy of sales predictions when the machine-learning method is used.
The accuracy of sales prediction models based on the big data of online word-of-mouth (eWOM) is still not satisfied. We argue that eWOM contains heat and sentiments of different product dimensions, which can improve the accuracy of these models. In this paper, we propose a dynamic topic analysis (DTA) framework in order to extract heat and sentiments of product dimensions from the big data of eWOM. Finally, we propose an autoregressive-heat-sentiment (ARHS) model, which integrates heat and sentiments of dimensions into the baseline predictive model. The empirical study in movie industry confirms that heat and sentiments of dimensions can improve the accuracy of sales prediction model. ARHS model is better for movie box-office revenue prediction than other models.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.