Automated Text Analysis for Consumer Research

Abstract

The amount of digital text available for analysis by consumer researchers has risen dramatically. Consumer discussions on the internet, product reviews, and digital archives of news articles and press releases are just a few potential sources for insights about consumer attitudes, interaction, and culture. Drawing from linguistic theory and methods, this article presents an overview of automated text analysis, providing integration of linguistic theory with constructs commonly used in consumer research, guidance for choosing amongst methods, and advice for resolving sampling and statistical issues unique to text analysis. We argue that although automated text analysis cannot be used to study all phenomena, it is a useful tool for examining patterns in text that neither researchers nor consumers can detect unaided. Text analysis can be used to examine psychological and sociological constructs in consumer-produced digital text by enabling discovery or by providing ecological validity.

Co‐presence and mobile apps: Technology's impact on being with others

“…Firstly, we rely on software content analysis using an algorithm proposed by psychologists (Linguistic Inquiry and Word Count – LIWC), which helps identify a text's linguistic structure around certain dimensions: social, cognitive, emotional, perceptual, and linguistic (Boyd & Pennebaker, ; Pennebaker, Boyd, Jordan, & Blackburn, ). Inspired by linguistic theory and methods, the marketing literature has recently highlighted the relevance of automated text analysis (Humphreys & Wang, ). In particular, the authors note that LIWC is very useful when examining text content that neither researchers nor consumers can detect without additional support.…”

“…In the same vein, data analysis is based on triangulating analytical methods to dissect the respondents' discourse. Thus, as suggested by Kahn, Tobin, Massey, and Anderson (2007) and by Humphreys and Wang (2017), we complete the manual content analysis with a computerized textual analysis using LIWC software, which, as detailed below, is particularly suitable for measuring a speech's emotional, cognitive, and social dimensions (Kahn et al, 2007).…”

Unfolding the characteristics of incentivized online reviews

“…By analyzing language for its meaning, NLP systems have successfully performed tasks such as correcting grammar, converting speech to text and automatically translating between languages (Church and Rau 1995). By using NLP, it is possible to organize and structure knowledge to perform several tasks such as translation, relationship extraction, speech recognition, topic segmentation, and sentiment analysis (Humphreys and Wang, 2017;Villarroel Ordenes et al, 2017). An active research area of NLP is sentiment analysis (Cambria et al 2015), which can be traced back to early 2000s when artificial intelligence researchers unleashed its power to understand user behavioral patterns (Nasukawa and Yi 2003).…”

Does involvement in corporate social irresponsibility affect the linguistic features of corporate social responsibility reports?

“…To this end, we used the Linguistic Inquiry and Word Count (LIWC) 2015 software, which relies on underlying linguistic scales that have frequently been used in psychology, marketing, and language research, among others (Akpinar et al, 2018;Aleti, Pallant, Tuan, & van Laer, 2019;Humphreys & Wang, 2018;Ludwig et al, 2013;Tausczik & Pennebaker, 2010). Approximately 90 variables or combinations of variables are included in LIWC, and they can be employed to measure several important aspects of texts.…”