Listening in on Social Media: A Joint Model of Sentiment and Venue Format Choice

Abstract

In this research, the authors jointly model the sentiment expressed in social media posts and the venue format to which it was posted as two interrelated processes in an effort to provide a measure of underlying brand sentiment. Using social media data from firms in two distinct industries, they allow the content of the post and the underlying sentiment toward the brand to affect both processes. The results show that the inferences marketing researchers obtain from monitoring social media are dependent on where they “listen” and that common approaches that either focus on a single social media venue or ignore differences across venues in aggregated data can lead to misleading brand sentiment metrics. The authors validate the approach by comparing their model-based measure of brand sentiment with performance measures obtained from external data sets (stock prices for both brands and an offline brand-tracking study for one brand). They find that their measure of sentiment serves as a leading indicator of the changes observed in these external data sources and outperforms other social media metrics currently used.

She Said, She Said: Differential Interpersonal Similarities Predict Unique Linguistic Mimicry in Online Word of Mouth

“…We ran the models above using only such data (N = 9271) to address issues of causality, self-selection, and prior behavior/learning (e.g., previous posting frequency; Schweidel and Moe 2014). These results were slightly weaker as a result of the smaller sample size, but were consistent with the results reported above.…”

“…Second, the consequences of linguistic mimicry for consumers' social and digital connections could be examined more broadly. For example, consumers' engagement with a given community could be tracked longitudinally as a function of mimicking (or being mimicked), or their engagement across communities or online channels (Schweidel and Moe 2014) Future research could also examine other aspects of personal or status similarity. For example, although we focus on the role of similarity in determining how individuals reply to a post (i.e., in terms of mimicry), these variables likely also affect whether individuals reply to a post.…”

The effect of social media interactions on customer relationship management

“…54 % have positive to neutral tonality). Though the found effects hold despite this large share of negative comments, future research may more closely examine the role of sentiment (Schweidel and Moe 2014). Such additional data would also help to account for heterogeneity, particularly in those exploratory studies that are currently based on simple mean comparisons.…”

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

“…Third, we underscore the necessity of considering the message development itself (van Dijk 1997) and contribute to conceptualizations of sentiment dynamics (Schweidel and Moe 2014) by exploring how discourse patterns within reviews reflect consumers' sentiments. A consumer's overall sentiment is likely negative if the positivity of the sentiment expressions (explicit and implicit) are incoherent across the sequence of sentences in a review.…”

“…Few consumer research studies acknowledge the importance of speech act features for deriving consumer intentions though (Thomas 1992), and existing consumer research on sentiment analysis neglects the inherent strength aspects. Past research has used binary, positive versus negative (Homburg, Ehm, and Artz 2015;Tirunillai and Tellis 2012) or ternary, positive/negative/neutral (Das and Chen 2007;Schweidel and Moe 2014) sentiment schemes (see table 1). …”