Social Advertising Effectiveness Using a Large-Scale Randomized Field Experiment
Study 1: Social Advertising Effectiveness
Study 2: Social Advertising Effectiveness Across Products
Study 3: Identifying Subgroups with Enhanced Peer Influence Using High-dimensional Data
We examine social advertising effectiveness and its heterogeneous effects across products, individuals, and social ties, by identifying the causal relationships among social influence, products, and network-embedded human behaviors. Social advertising places social cues (e.g., likes) in ads, utilizing the power of social influence (the effects of social cues in ads) to encourage ad engagement. We collaborate with a world-known social networking app for a large-scale randomized field experiment on its social ads. In the experiment, the presence and the number of social cues were randomly assigned among 57 million ad-user pairs (more than 37 million subjects and across 71 products in 25 product categories). Integrating the experimental evidence and the data of individuals, products, ads and network structures, our studies also address the incentives, magnitude, contagion patterns and viral factors (i.e., characteristics of products, behaviors, and individuals) of social influence in social advertising and product adoptions.
How Emotions Impact Online Content Spread in a Massive Social Network
This study investigates how emotions impact the spread of online content. Using a very large sample randomly collected from one of the world largest digital social networks, we analyzed the content of 387,486 online articles and their diffusion cascades, which involved more than 6 million unique individuals. We detected eight discrete emotions (i.e. surprise, joy, expect, love, anxiety, sadness, anger, and disgust) embedded in these online articles using a newly generated domain-specific emotion lexicon. Our results demonstrate that emotionality level significantly increases articles' cascades' depth, size, maximum breadth, and structural virality but decreases cascades' speed, and the effects are very heterogeneous across thirty distinct topics of articles. Breaking down the emotions into eight discrete emotions, we find that love and anxiety significantly and largely increase cascading breath, size, depth, and structural virality, while sadness significantly but negatively impacts these cascade dimensions. The trade-off between cascades' scale (i.e., depth, size, maximum breadth, and structural virality) and the speed of information transmission exists for love and sadness, but not for anxiety and surprise. We identified and showed the most contagious articles considering their embedded emotions and various kinds of article features using the casual tree model. Our results not only contribute to developing the theories of discrete emotions and information diffusion but provide useful insights and guidance for authors to produce highly contagious articles through optimally combining emotions and other article-level and publisher-level factors.