Collective Emotions Online and Their Influence on Community Life
Author Information
Author(s): Chmiel Anna, Sienkiewicz Julian, Thelwall Mike, Paltoglou Georgios, Buckley Kevan, Kappas Arvid, Hołyst Janusz A.
Hypothesis
Could emotions in Internet exchanges affect others and systematically influence quantitative and qualitative aspects of the trajectory of e-communities?
Conclusion
Overall, our results prove that collective emotional states can be created and modulated via Internet communication and that emotional expressiveness is the fuel that sustains some e-communities.
Supporting Evidence
- Emotions in online discussions can influence the emotional responses of other participants.
- Longer discussions tend to start with higher emotional levels, which can sustain the conversation.
- Negative emotions can prolong discussions but may also harm cooperation among community members.
Takeaway
When people talk online, their feelings can spread to others, making everyone feel similar emotions, which helps keep conversations going.
Methodology
The study analyzed over 4 million posts from blogs, BBC forums, and Digg using sentiment analysis to detect emotional valences and measure emotional interactions.
Potential Biases
The method of data collection and sentiment classification may introduce biases that affect the interpretation of emotional interactions.
Limitations
The sentiment analysis classifiers may have errors that could affect the results, and the study's findings may not apply universally across all e-communities.
Participant Demographics
Data was collected from users of blogs, BBC forums, and Digg, but specific demographic information about participants was not provided.
Digital Object Identifier (DOI)
Want to read the original?
Access the complete publication on the publisher's website