Application of text mining techniques to the analysis of discourse in eWOM communications from a gender perspective http://researchonline.ljmu.ac.uk/id/eprint/8002/ Article LJMU has developed LJMU Research Online for users to access the research output of the University more effectively. Teso, E, Olmedilla, M, Martínez Torres, R and Toral, S (2018) Application of text mining techniques to the analysis of discourse in eWOM communications from a gender perspective. Technological Forecasting and Social Change.
Abstract:The emergence of online user-generated content has raised numerous questions about discourse gender differences as compared to face-to-face interactions. The intended gender-free equality of Internet has been challenged by numerous studies, and significant differences have been found in online communications. This paper proposes the application of text mining techniques to online gender discourse through the analysis of shared reviews in electronic word-of-mouth communities (eWOM), which is a form of user-generated content. More specifically, linguistic issues, sentiment analysis and 2
Nowadays electronic word-of-mouth (eWOM) communities symbolise a significant source of information that helps customers to make informed purchasing decisions. Through eWOM communities, a great audience of users is able to acquire knowledge from reviews concerning products and services that are less popular to the majority. The Long Tail effect is a manifestation of such redistribution of demand from popular products to niche products. In this paper, a new methodology that mathematically fits the relationship between the power-law distribution and the Long Tail from an eWOM community is developed. In addition, this paper defines a tool for finding niche products inaccessible through conventional channels. The results are consistent in showing that not all the categories fitting a power-law distribution are characterised by the Long Tail phenomenon, and conversely some of those having a Long Tail do not fit a power-law distribution.ARTICLE HISTORY
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.