Unveiling What Is Written in the Stars: Analyzing Explicit, Implicit, and Discourse Patterns of Sentiment in Social Media

Abstract

Deciphering consumers’ sentiment expressions from big data (e.g., online reviews) has become a managerial priority to monitor product and service evaluations. However, sentiment analysis, the process of automatically distilling sentiment from text, provides little insight regarding the language granularities beyond the use of positive and negative words. Drawing on speech act theory, this study provides a fine-grained analysis of the implicit and explicit language used by consumers to express sentiment in text. An empirical text-mining study using more than 45,000 consumer reviews demonstrates the differential impacts of activation levels (e.g., tentative language), implicit sentiment expressions (e.g., commissive language), and discourse patterns (e.g., incoherence) on overall consumer sentiment (i.e., star ratings). In two follow-up studies, we demonstrate that these speech act features also influence the readers’ behavior and are generalizable to other social media contexts, such as Twitter and Facebook. We contribute to research on consumer sentiment analysis by offering a more nuanced understanding of consumer sentiments and their implications.

How online word‐of‐mouth impacts receivers

“…A WOM message may communicate positivity or negativity about product outcomes via star ratings, text content, or both. The causal relationship between these two aspects of valence is bidirectional and nuanced (Ordenes, Ludwig, De Ruyter, Grewal, & Wetzels, ; Rocklage & Fazio, ; Rocklage, Rucker, & Nordgren, , , ). Regardless, reviews with negative star ratings or text can send negative product signals that increase receivers’ subsequent search behavior (Varga & Albuquerque, ) and helpfulness ratings (Cao et al, ), but decrease purchase likelihood (Varga & Albuquerque, ) and brand equity (Bambauer‐Sachse & Mangold, ).…”

Do cognitive and affective expressions matter in purchase conversion? A live chat perspective

“…First, we acknowledge that SAT is proposed and empirically tested in the context of live chat communication, in which the dialog is one-to-one and private in nature. However, the extension of this theory can be found in some recent literature (for instance, Ordenes et al, 2017). Second, a shopper who commits to a purchase may be affected by other factors, such as demographic and psychological characteristics, which are beyond the scope of a dialog with a retailer.…”

“…Text analysis is a major technique of interpreting various types of CMC contents in the recent literature. Studies in information science (for instance, Bandaragoda, De Silva, Alahakoon, Ranasinghe, & Bolton, 2018), information systems (for instance, Zhang, Kang, Jiang, & Pei, 2018), marketing (for instance, Ludwig et al, 2013;Ordenes, Ludwig, De Ruyter, Grewal, & Wetzels, 2017), finance (for instance, Chen, De, Hu, & Hwang, 2014), and many other fields adopt text analysis to analyze CMC content and make predictions. They consistently validate that text analysis, especially sentiment analysis, contributes to detecting the underlying meaning of CMC content.…”

What Happens in Vegas Stays on TripAdvisor? A Theory and Technique to Understand Narrativity in Consumer Reviews

“…In contrast to more typical narrative forms-such as novels, movies, or TV series-the short length of reviews does not encourage consumers to forget that the setting is pure fiction. Some recent research into reviews acknowledges though that narrative elements, such as time (Chen and Lurie 2013) and emotion words (Villarroel Ordenes et al 2017), influence consumer behavior. Yet, narrativity, or the extent to which a text tells a story (Sturgess 1992), remains an overlooked feature of reviews.…”

“…Second, where recent advances in automated text analysis provide new, more efficient ways of gauging consumers' behavior from their use of natural language (Humphreys and Wang 2018), including techniques that detect levels of analytical thinking (Pennebaker et al 2015), consumer sentiment (Cohn, Mehl, and Pennebaker 2004;Villarroel Ordenes et al 2017), deception (Ludwig et al 2016;Newman et al 2003), and social orientation (Kacewicz et al 2014), these approaches do not allow the assessment of narrativity. Consumer researchers could depend on such a technique to indicate this linguistic feature time and again.…”