The analysis of dynamic emotional contagion in online brand community

Dewen Liu, Sikang Zhang, Qi LiFrontiers in Psychology 2022 · DOI

Abstract

Online brand communities (OBCs) are vital strategic assets for firms, facilitating direct interaction and consumer feedback. A positive emotional atmosphere is essential for community health and member retention, yet the dynamic evolution of these emotions is often misunderstood. This study investigates emotional contagion among three sources: original posters, other community members, and official firm feedback. By analyzing longitudinal data from the MIUI forum using machine learning and Vector Autoregressive (VAR) modeling, the research examines both emotional valence (mean mood) and volatility (mood stability). The findings reveal that while firm feedback is a primary driver of community sentiment, these emotional contagions are remarkably fleeting, typically dissipating within 72 hours.

Introduction

Maintaining a healthy "vibe" in an Online Brand Community is more than just a PR exercise; it is essential for long-term customer loyalty. However, emotions in these digital spaces are not static. They ripple through the community as members interact with each other and with the brand. Despite its importance, the dynamic nature of how these emotions spread—a process known as emotional contagion—has remained under-explored. This paper fills that gap by mapping the multidimensional emotional interactions between posters, peers, and official staff.

Methodology

The researchers developed a multi-stage analytical pipeline to track emotional "ping-pong" over time:

  1. Sentiment Analysis: Utilizing the Jieba library for Chinese word segmentation and a dictionary-based machine learning approach, the team calculated scores for both valence (positivity/negativity) and volatility (fluctuation of sentiment) across 17,622 posts and nearly 100,000 replies.
  2. Vector Autoregressive (VAR) Modeling: This time-series method captured the causal, reciprocal relationships between the emotional states of the three sources.
  3. Impulse Response Function (IRF): This allowed for the simulation of "shocks"—such as a sudden burst of official positivity—to observe how the community reacts over a 10-day window.

Data and Model Reliability

The study utilized data from the MIUI forum, Xiaomi’s official user community. To ensure the data reflected standard emotional contagion rather than external crises, the researchers selected a stable period between major software updates. To ensure the findings were statistically sound, the researchers confirmed the stability of the VAR model.

The stability condition of the VAR model shows all eigenvalues within the unit circle, confirming that the observed emotional patterns are reliable and stationary.

Key Findings

The Power of the Firm

Variance decomposition analysis revealed that after a source's own emotional history, the firm's official feedback is the most significant external driver of member sentiment. Specifically, official responses explained approximately 8.8% of the variance in member post valence—the highest contribution from any external source. This underscores the high ROI of active, positive community management.

Volatility is Contagious

The study found that it isn't just what people feel that spreads, but how stably they feel it. High emotional volatility in one group (e.g., erratic feedback from other members) can trigger instability in the original poster’s sentiment. Managing the "calmness" of a community is as important as managing its positivity.

The Fleeting Nature of Contagion

Perhaps the most critical finding for community managers is the short lifespan of emotional shocks. Whether a shock is positive or negative, its impact peaks quickly and typically returns to baseline within three days.

An Impulse Response Function (IRF) plot illustrating how an emotional shock to member sentiment peaks early and returns to baseline within a few days.

Practical Implications

For brands, these results offer two clear directives:

  1. Proactive Shaping: Firms can and should proactively influence community mood by carefully designing their official feedback. Because the firm acts as an emotional anchor, its "voice" carries significant weight in stabilizing and boosting member sentiment.
  2. Consistency is Key: Because emotional contagion is fleeting, community management cannot be a sporadic effort. To maintain a positive atmosphere, firms must engage consistently. A single positive interaction will not sustain a community for a week; frequent, daily engagement is required to keep the "vibe" alive.

Conclusion

By distinguishing between emotional sources and examining both valence and volatility, this study provides a granular map of digital emotional contagion. While the fleeting nature of these interactions presents a challenge for consistency, it also offers a "reset" button for communities facing temporary negativity, provided the firm remains an active and positive participant in the conversation.

Summary updated

Abstract

Online brand communities (OBCs) could benefit firms in many usages, ranging from collecting consumers’ suggestions or advice to interacting with community members directly and transparently. Creating a positive emotional atmosphere is essential for such communities’ healthy development as its boosts the continuous involvement of each member. However, the dynamic cross-influences and evolution of emotions in OBCs have not been fully explored, which was the research gap this paper tried to fill. Based on emotional contagion theory, this study identifies three sources of textual sentiment through machine learning methods in OBCs: member’s posts, other members’ feedback, and the focal firm’s official feedback. This study further tested the dynamic emotional contagion process among these sources on valence (mean) and volatility (dispersion), namely how they affected each other. Data was collected from the MIUI forum, a large forum launched by Xiaomi corporate on August 1, 2011, which contained 17,622 posts and 99,426 feedback. Results showed that: (1) in the emotional contagion process, there existed differences in the influence of emotional valence and volatility from different sources; (2) all emotional interactions were temporary and mostly lasted no more than three days; (3) the most significant contributor of each sources’ emotion was itself, which could be explained by lagged effect; (4) the valence of focal firm’s emotion (focal firm’s official feedback) was the second contributor of the valence of member’s emotion (member’s posts) and other members’ emotion (other members’ feedback). Three sources of emotion in OBCs and emotional valence/volatility should be considered when firms try to guide the emotional changes in such communities. Furthermore, firms could proactively influence members’ emotions by carefully designing the feedback to members’ posts. Besides, since all interactions are temporary, firms need to engage in online communities frequently, like consistently offering feedback.
BibTeX
@inproceedings{liu2022analysis,
  author = {Dewen Liu and Sikang Zhang and Qi Li},
  title = {{The analysis of dynamic emotional contagion in online brand community}},
  booktitle = {Frontiers in Psychology},
  year = {2022},
  doi = {10.3389/fpsyg.2022.946666},
}
Figure