Chuan Luo

Portrayal of electronic cigarettes on YouTube

BackgroundAs the most popular video sharing website in the world, YouTube has the potential to reach and influence a huge audience. This study aims to gain a systematic understanding of what e-cigarette messages people are being exposed to on YouTube by assessing the quantity, portrayal and reach of e-cigarette videos.MethodsResearchers identified the top 20 search results on YouTube by relevance and view count for the following search terms: “electronic cigarettes”, “e-cigarettes”, “ecigarettes”, “ecigs”, “smoking electronic cigarettes”, “smoking e-cigarettes”, “smoking ecigarettes”, “smoking ecigs”. A sample of 196 unique videos was coded for overall portrayal and genre. Main topics covered in e-cigarette videos were recorded and video statistics and viewer demographic information were documented.ResultsAmong the 196 unique videos, 94% (n = 185) were “pro” to e-cigarettes and 4% (n = 8) were neutral, while there were only 2% (n = 3) that were “anti” to e-cigarettes. The top 3 most prevalent genres of videos were advertisement, user sharing and product review. 84.3% of “pro” videos contained Web links for e-cigarette purchase. 71.4% of “pro” videos claimed that e-cigarettes were healthier than conventional cigarettes. Audience was primarily from the United States, the United Kingdom and Canada and “pro” e-cigarette videos were watched more frequently and rated much more favorably than “anti” ones.ConclusionsThe vast majority of information on YouTube about e-cigarettes promoted their use and depicted the use of e-cigarettes as socially acceptable. It is critical to develop appropriate health campaigns to inform e-cigarette consumers of potential harms associated with e-cigarette use.

Identifying peer influence in online social networks using transfer entropy

The past few years have witnessed the rapid growth of online social networks, which have become important hubs of social activity and conduits of information. Identifying social influence in these newly emerging platforms can provide us with significant insights to better understand the interaction behaviors among online users. However, it is difficult for us to measure the influence quantitatively among user peers, since many key factors such as homophily and heterogeneity, can not be observed in our real world conveniently. More recent work mainly focuses on developing theoretical models based on explicit causal knowledge. Nevertheless, such knowledge is usually not available and often needs to be discovered. In this paper, we introduce a model free approach to formulate causal inferences of behaviors among user peers. Experimental results show that influence measured by our approach could successfully reconstruct the underlying networks structure. Furthermore, two additional case studies based on this approach reveal that influentials wield power through specific venues, which constitute a comparatively small portion of the whole channels.

Exploring Entrainment Patterns of Human Emotion in Social Media.

Emotion entrainment, which is generally defined as the synchronous convergence of human emotions, performs many important social functions. However, what the specific mechanisms of emotion entrainment are beyond in-person interactions, and how human emotions evolve under different entrainment patterns in large-scale social communities, are still unknown. In this paper, we aim to examine the massive emotion entrainment patterns and understand the underlying mechanisms in the context of social media. As modeling emotion dynamics on a large scale is often challenging, we elaborate a pragmatic framework to characterize and quantify the entrainment phenomenon. By applying this framework on the datasets from two large-scale social media platforms, we find that the emotions of online users entrain through social networks. We further uncover that online users often form their relations via dual entrainment, while maintain it through single entrainment. Remarkably, the emotions of online users are more convergent in nonreciprocal entrainment. Building on these findings, we develop an entrainment augmented model for emotion prediction. Experimental results suggest that entrainment patterns inform emotion proximity in dyads, and encoding their associations promotes emotion prediction. This work can further help us to understand the underlying dynamic process of large-scale online interactions and make more reasonable decisions regarding emergency situations, epidemic diseases, and political campaigns in cyberspace.

Causal Inference in Social Media Using Convergent Cross Mapping

Revealing underlying causal structure in social media is critical to understanding how users interact, on which a lot of security intelligence applications can be built. Existing causal inference methods for social media usually rely on limited explicit causal context, pre-assume certain user interaction model, or neglect the nonlinear nature of social interaction, which could lead to bias estimations of causality. Inspired from recent advance in causality detection in complex ecosystems, we propose to take advantage of a novel nonlinear state space reconstruction based approach, namely Convergent Cross Mapping, to perform causal inference in social media. Experimental results on real world social media datasets show the effectiveness of the proposed method in causal inference and user behavior prediction in social media.

Time Critical Disinformation Influence Minimization in Online Social Networks

If a piece of disinformation released from a terrorist organization propagates on Twitter and this adversarial campaign is detected after a while, how emergence responders can wisely choose a set of source users to start the counter campaign to minimize the disruptive influence of disinformation in a short time? This practical problem is challenging and critical for authorities to make online social networks a more trustworthy source of information. In this work, we propose to study the time critical disinformation influence minimization problem in online social networks based on a continuous-time multiple campaign diffusion model. We show that the complexity of this optimization problem is NP-hard and provide a provable guaranteed approximation algorithm for this problem by proving several critical properties of the objective function. Experimental results on a sample of real online social network show that the proposed approximation algorithm outperforms various heuristics and the transmission temporal dynamics knowledge is vital for selecting the counter campaign source users, especially when the time window is small.

An Empirical Study of Information Diffusion in Micro-blogging Systems during Emergency Events

Understanding the rapid information diffusion process in social media is critical for crisis management. Most of existing studies mainly focus on information diffusion patterns under the word-of-mouth spread mechanism. However, to date, the mass-media spread mechanism in social media is still not well studied. In this paper, we take the emergency event of Wenzhou train crash as a case and conduct an empirical analysis, utilizing geospatial correlation analysis and social network analysis, to explore the mass-meida spread mechanism in social media. By using the approach of agent-based modeling, we further make a quantativiely comparison with the information diffusion patterns under the word-of-mouth spread mechanism. Our exprimental results show that the mass-meida spread mechanism plays a more important role than that of the word-of-mouth in the information diffusion process during emergency events. The results of this paper can provide significant potential implications for crisis management.

Discovering seasonal patterns of smoking behavior using online search information

Discovering temporal patterns and changes in tobacco use has important practical implications in tobacco control. This paper presents one of the first comprehensive international studies of seasonal smoking patterns based on online searches performed. Using periodogram and cross-correlation, we find that smoking-related search behavior shows strong seasonality effect across countries. In addition, there are significant pairwise associations between such seasonality in different countries.

Inferring social influence and meme interaction with Hawkes processes

Revealing underlying social influence among users in social media is critical to understanding how users interact, on which a lot of security intelligence applications can be built. Existing methods fail to take into account the interaction relationships among memes. In this paper, we propose to simultaneously model social influence and meme interaction in information diffusion with novel multidimensional Hawkes processes. Experimental results on both synthetic and real world social media data show the efficacy of the proposed approach.

Multivariate embedding based causaltiy detection with short time series

Existing causal inference methods for social media usually rely on limited explicit causal context, preassume certain user interaction model, or neglect the nonlinear nature of social interaction, which could lead to bias estimations of causality. Besides, they often require sufficiently long time series to achieve reasonable results. Here we propose to take advantage of multivariate embedding to perform causality detection in social media. Experimental results show the efficacy of the proposed approach in causality detection and user behavior prediction in social media.