Measuring Emotional Contagion in Social Media (1506.06021v1)

Abstract: Social media are used as main discussion channels by millions of individuals every day. The content individuals produce in daily social-media-based micro-communications, and the emotions therein expressed, may impact the emotional states of others. A recent experiment performed on Facebook hypothesized that emotions spread online, even in absence of non-verbal cues typical of in-person interactions, and that individuals are more likely to adopt positive or negative emotions if these are over-expressed in their social network. Experiments of this type, however, raise ethical concerns, as they require massive-scale content manipulation with unknown consequences for the individuals therein involved. Here, we study the dynamics of emotional contagion using Twitter. Rather than manipulating content, we devise a null model that discounts some confounding factors (including the effect of emotional contagion). We measure the emotional valence of content the users are exposed to before posting their own tweets. We determine that on average a negative post follows an over-exposure to 4.34% more negative content than baseline, while positive posts occur after an average over-exposure to 4.50% more positive contents. We highlight the presence of a linear relationship between the average emotional valence of the stimuli users are exposed to, and that of the responses they produce. We also identify two different classes of individuals: highly and scarcely susceptible to emotional contagion. Highly susceptible users are significantly less inclined to adopt negative emotions than the scarcely susceptible ones, but equally likely to adopt positive emotions. In general, the likelihood of adopting positive emotions is much greater than that of negative emotions.

Measuring Emotional Contagion in Social Media

The research paper titled "Measuring Emotional Contagion in Social Media" by Emilio Ferrara and Zayao Yang explores the phenomenon of emotional contagion in the context of Twitter. Emotional contagion refers to the transmission of moods and feelings from one person to another, a process well-documented in face-to-face interactions. The paper leverages computational social science methods to understand how these dynamics manifest in online environments, specifically through social media platforms where direct non-verbal cues are absent.

Methodological Approach

Utilizing Twitter as the paper platform, the authors investigate the spread of emotional content without engaging in direct content manipulation. Unlike previous experimental studies, such as one conducted on Facebook that involved ethical concerns over user manipulation, this research adopts an observational approach. To isolate emotional contagion effects, a null model is constructed that discounts certain confounding factors, effectively accounting for the natural dissemination of content without direct intervention.

The paper employs sentiment analysis using SentiStrength, a well-suited tool for parsing the sentiment of short, informal text characteristic of social media communications. The positive and negative emotions of tweets are computed, facilitating the quantification of emotional valence—defined as the polarity score difference between positive and negative sentiment values.

Key Findings

Through analysis, it is observed that users are more likely to post negative tweets following a 4.34% increased exposure to negative content and positive tweets after a 4.50% increased exposure to positive content, relative to predicted baseline figures. This underscores a linear relationship between the emotional stimuli users encounter and their own resultant posting behavior, indicating clear patterns of emotional contagion on Twitter.

Furthermore, the paper identifies two user groups based on susceptibility to emotional contagion: highly susceptible and scarcely susceptible. Highly susceptible users are notably less likely to express negative emotions compared to their scarcely susceptible counterparts, though they show equal likelihood in adopting positive emotions. Generally, the propensity to adopt positive emotions is significantly higher than negative ones within both groups.

Implications and Future Directions

The findings of this paper carry important implications for understanding the emotional dynamics governing social media interactions. Practically, recognizing the patterns of emotional contagion can inform strategies for content moderation, marketing, and mental health interventions on social platforms. Theoretically, these results contribute to the broader discourse on how digital communication impacts emotional health and social behavior.

The paper also paves the way for future research that could further dissect the interplay between homophily and emotional contagion, as noted in theoretical concerns raised by prior literature. Longitudinal and cross-platform studies, perhaps integrating other social media data, could aid in delineating the extent to which these two phenomena interact and influence online social structures.

By employing a robust data-driven foresight approach devoid of experimental manipulation, this research sets a benchmark for ethical inquiry into the psychological impacts of social media use while providing a quantitative foundation for evaluating emotional transmission in digital settings.