In the study titled "Emotions in Online Content Diffusion," authors Yifan Yu, Shan Huang, Yuchen Liu, and Yong Tan explore how emotional expressions, specifically negative discrete emotions such as anxiety, sadness, anger and disgust influence the spread of online content in social media networks. By incorporating social network theories and using a computational approach, the researchers aim to understand the differential diffusion patterns associated with these emotional expressions. The study focuses on analyzing the structural properties of diffusion cascades including size, depth, maximum breadth and structural virality. Additionally it examines individual characteristics such as age gender and network degree as well as social ties (strong and weak) involved in the cascading process. The researchers utilize a sample of over six million unique individuals who transmitted 387 486 randomly selected articles within the WeChat online social network. To detect emotional expressions embedded in these articles accurately a domain-specific and up-to-date emotion lexicon is generated. The researchers then employ a partial-linear instrumental variable approach with a double machine learning framework to causally identify the impact of negative discrete emotions on online content diffusion. The findings reveal that articles with higher expressions of anxiety tend to spread to a larger number of individuals and have deeper and broader diffusion cascades with greater structural virality. On the other hand expressions of anger and sadness are found to reduce cascade size and maximum breadth. Furthermore the study demonstrates that articles with varying degrees of negative emotional expressions exhibit different spreading patterns based on individual characteristics and social ties. Overall this research sheds light on content marketing strategies by utilizing negative emotional expressions effectively. It also has implications for content regulation in social media networks. By understanding how emotions shape thoughts and actions through online information transmission via social media platforms like WeChat this study provides valuable insights into optimizing content dissemination strategies.
This study looked at how feeling sad or angry can affect how information spreads on social media. The researchers used a special way of studying social networks and computers to understand why some things get shared more than others. They looked at the structure of how information spreads and what kind of people are involved. They studied over six million people who shared articles on WeChat, a popular social media platform. They also made a list of words that show different emotions in articles. They found that when people feel anxious, the information they share gets spread more widely and quickly. But when people feel angry or sad, the information doesn't get spread as much. Different people and their relationships with others also affect how information spreads. This research helps us understand how to make sure important information gets shared on social media."
Definitions
- Negative emotions: Feelings like sadness or anger.
- Online content diffusion: How information spreads on the internet.
- Social media networks: Websites or apps where people can connect with each other and share things.
- Computational approach: Using computers to help understand something.
- Diffusion cascades: How information spreads from person to person.
- Individual characteristics: Things about a person that make them unique, like their age or interests.
- Emotion lexicon: A list of words that show different feelings in writing.
- Virality: How popular something becomes online.
- Spreading patterns: How things spread from one person to another.
- Content dissemination strategies: Ways to make sure important information gets shared
Exploring the Impact of Negative Emotions on Online Content Diffusion
In a recent study titled "Emotions in Online Content Diffusion," authors Yifan Yu, Shan Huang, Yuchen Liu, and Yong Tan explore how emotional expressions influence the spread of online content in social media networks. By incorporating social network theories and using a computational approach, the researchers aim to understand the differential diffusion patterns associated with negative discrete emotions such as anxiety, sadness, anger and disgust.
Analyzing Structural Properties of Diffusion Cascades
The study focuses on analyzing the structural properties of diffusion cascades including size, depth, maximum breadth and structural virality. Additionally it examines individual characteristics such as age gender and network degree as well as social ties (strong and weak) involved in the cascading process. The researchers utilize a sample of over six million unique individuals who transmitted 387 486 randomly selected articles within the WeChat online social network. To detect emotional expressions embedded in these articles accurately a domain-specific and up-to-date emotion lexicon is generated.
Employing Partial-Linear Instrumental Variable Approach
The researchers then employ a partial-linear instrumental variable approach with a double machine learning framework to causally identify the impact of negative discrete emotions on online content diffusion. The findings reveal that articles with higher expressions of anxiety tend to spread to a larger number of individuals and have deeper and broader diffusion cascades with greater structural virality. On the other hand expressions of anger and sadness are found to reduce cascade size and maximum breadth. Furthermore the study demonstrates that articles with varying degrees of negative emotional expressions exhibit different spreading patterns based on individual characteristics and social ties.
Implications for Content Marketing Strategies
Overall this research sheds light on content marketing strategies by utilizing negative emotional expressions effectively. It also has implications for content regulation in social media networks. By understanding how emotions shape thoughts and actions through online information transmission via social media platforms like WeChat this study provides valuable insights into optimizing content dissemination strategies
Social media-transmitted online information, which is associated with emotional expressions, shapes our thoughts and actions. In this study, we incorporate social network theories and analyses and use a computational approach to investigate how emotional expressions, particularly \textit{negative discrete emotional expressions} (i.e., anxiety, sadness, anger, and disgust), lead to differential diffusion of online content in social media networks. We rigorously quantify diffusion cascades' structural properties (i.e., size, depth, maximum breadth, and structural virality) and analyze the individual characteristics (i.e., age, gender, and network degree) and social ties (i.e., strong and weak) involved in the cascading process. In our sample, more than six million unique individuals transmitted 387,486 randomly selected articles in a massive-scale online social network, WeChat. We detect the expression of discrete emotions embedded in these articles, using a newly generated domain-specific and up-to-date emotion lexicon. We apply a partial-linear instrumental variable approach with a double machine learning framework to causally identify the impact of the negative discrete emotions on online content diffusion. We find that articles with more expressions of anxiety spread to a larger number of individuals and diffuse more deeply, broadly, and virally. Expressions of anger and sadness, however, reduce cascades' size and maximum breadth. We further show that the articles with different degrees of negative emotional expressions tend to spread differently based on individual characteristics and social ties. Our results shed light on content marketing and regulation, utilizing negative emotional expressions.
