A text mining and topic modelling perspective of ethnic marketing research

Abstract

This study presents an enhanced automated approach based on literature analysis and synthesis for establishing the dimensions of the ethnic marketing literature, covering a set of 239 journal articles published by nine major publishers. The approach reported is enhanced by two novel procedures to address previously identified limitations, namely: definition of a relevant dictionary based on both a sufficient lexicon extracted from a definition of the core theme and a conditional dictionary, with related but non-core terms; and a visually appealing pictorial representation to summarize the discovered topics. The application of the method to ethnic marketing indicates that ethnic marketing research is characterised by high conceptual heterogeneity, although a clear definition of "ethnic marketing" is imperative for research development. Overall, the paper advances an approach with considerable scalability advantages when compared with extant approaches, an important issue to consider when textual sources become big data.

Text Mining in Big Data Analytics

“…A similar study by Amado et al [203], based on the study of Moro et al [202], outlined a research literature analysis based on the text mining approach over a total of 1560 articles framed in the 2010-2015 period with the objective of identifying the primary trends on big data in marketing. Furthermore, Moro et al [204] summarized the literature collected on ethnic marketing in the period 2005-2015 using LDA.…”

Empowered learning through microworlds and teaching methods: a text mining and meta-analysis-based systematic review

“…Furthermore, at least two experts would need to validate each article to mitigate the known human assessment subjectivity (Santos, Laureano, and Moro 2019). Therefore, an approach based on standard text mining techniques can be an alternative to automatically select those articles that are relevant to the studied subject (Moro et al 2019), and help in defining and executing inclusion criteria. This approach consists in identifying a lexicon that enables to correctly categorize each article, and then in running a text mining script that builds a document-term matrix that quantifies how many times each of the terms from the lexicon occurs within each article (Cortez et al 2018).…”

One More Tweet: Firms Challenge a Sustainable Future

“…Some scholars suggest that a combination of methods or a comparison of techniques through different instruments can be more appropriate for performing text mining analysis (Toldo, 2013;Moro et al, 2019), as it offers the opportunity to detect data from unstructured documents that can be from different sources (Vijayarani and Janani, 2016).…”

“…When different sources are mixed, the analysis could not be very objective, as the researcher must find a way to compare the sources and extract relevant and significant information. Automated tools allow for the converting of unstructured information such as words and sentences into quantitative and numerical values in databases (Vijayarani and Janani, 2016;Amini et al, 2018) and for the implementing of iterative queries to identify and quantify textual relationships and frequencies (Jacobs, 1992;Jacobs and Rau, 1993), leading to an objective research process and undistorted (Toldo, 2013;Moro et al, 2019).…”

“…For instance, Guo et al (2017) highlighted some limitations regarding topics set aside because of their low usage rate in customers' reviews. More recently, Moro et al (2019) called for new approaches to research on papers with a focus limited to the key sections.…”