Manuel Cebrian

Expecting to be HIP: Hawkes Intensity Processes for Social Media Popularity

Modeling and predicting the popularity of online content is a significant problem for the practice of information dissemination, advertising, and consumption. Recent work analyzing massive datasets advances our understanding of popularity, but one major gap remains: To precisely quantify the relationship between the popularity of an online item and the external promotions it receives. This work supplies the missing link between exogenous inputs from public social media platforms, such as Twitter, and endogenous responses within the content platform, such as YouTube. We develop a novel mathematical model, the Hawkes intensity process, which can explain the complex popularity history of each video according to its type of content, network of diffusion, and sensitivity to promotion. Our model supplies a prototypical description of videos, called an endo-exo map. This map explains popularity as the result of an extrinsic factor -- the amount of promotions from the outside world that the video receives, acting upon two intrinsic factors -- sensitivity to promotion, and inherent virality. We use this model to forecast future popularity given promotions on a large 5-months feed of the most-tweeted videos, and found it to lower the average error by 28.6% from approaches based on popularity history. Finally, we can identify videos that have a high potential to become viral, as well as those for which promotions will have hardly any effect.Explaining and predicting the popularity of online multimedia content is an important problem for the practice of information dissemination and consumption. Recent work advances our understanding of popularity, but one important gap remains: to precisely quantify the relationship between the popularity of an online item and the external promotions it receives. This work supplies the missing link between exogenous inputs from public social media platforms (Twitter) and endogenous responses within video content platforms (Youtube). This is done via a novel mathematical model, the Hawkes intensity process, which is able to explain the complex popularity history of each video according to its content, network, and sensitivity to promotion. This model supplies a prototypical description of videos, called an endo-exo map, which allows us to explain the popularity as the joint effects of two intrinsic measures and the amount of discussions from the outside world. This model also allows us to forecast the effects of future promotions more accurately than approaches based on popularity history alone, and to identify videos that have a high potential to become viral, or those for which promotions will have hardly any effect.

Quantifying long-term evolution of intra-urban spatial interactions.

Understanding the long-term impact that changes in a citys transportation infrastructure have on its spatial interactions remains a challenge. The difficulty arises from the fact that the real impact may not be revealed in static or aggregated mobility measures, as these are remarkably robust to perturbations. More generally, the lack of longitudinal, cross-sectional data demonstrating the evolution of spatial interactions at a meaningful urban scale also hinders us from evaluating the sensitivity of movement indicators, limiting our capacity to understand the evolution of urban mobility in depth. Using very large mobility records distributed over 3 years, we quantify the impact of the completion of a metro line extension: the Circle Line (CCL) in Singapore. We find that the commonly used movement indicators are almost identical before and after the project was completed. However, in comparing the temporal community structure across years, we do observe significant differences in the spatial reorganization of the affected geographical areas. The completion of CCL enables travellers to re-identify their desired destinations collectively with lower transport cost, making the community structure more consistent. These changes in locality are dynamic and characterized over short timescales, offering us a different approach to identify and analyse the long-term impact of new infrastructures on cities and their evolution dynamics.

A column-generation approach for joint mobilization and evacuation planning

Large-scale evacuations require authorities to decide and stage evacuation routes, mobilize resources, and issue evacuation orders under strict time constraints. These decisions must consider both the capacity of the road network and the evolution of the threat (e.g., a bushfire or a flood). This paper proposes, for the first time, an optimization model that jointly optimizes the mobilization and evacuation planning, taking into account the behavioral response of evacuees and the allocation of resources for communicating and implementing evacuation orders. From a technical standpoint, the model is solved by a column generation algorithm that jointly decides the evacuation route, evacuation time, and the resource allocation for each evacuated area in order to maximize the number of evacuees reaching safety and minimize the total duration of the evacuation.

The benefits of social influence in optimized cultural markets.

Social influence has been shown to create significant unpredictability in cultural markets, providing one potential explanation why experts routinely fail at predicting commercial success of cultural products. As a result, social influence is often presented in a negative light. Here, we show the benefits of social influence for cultural markets. We present a policy that uses product quality, appeal, position bias and social influence to maximize expected profits in the market. Our computational experiments show that our profit-maximizing policy leverages social influence to produce significant performance benefits for the market, while our theoretical analysis proves that our policy outperforms in expectation any policy not displaying social signals. Our results contrast with earlier work which focused on showing the unpredictability and inequalities created by social influence. Not only do we show for the first time that, under our policy, dynamically showing consumers positive social signals increases the expected profit of the seller in cultural markets. We also show that, in reasonable settings, our profit-maximizing policy does not introduce significant unpredictability and identifies “blockbusters”. Overall, these results shed new light on the nature of social influence and how it can be leveraged for the benefits of the market.

Beyond viral

The proliferation of social media usage has not resulted in significant social change.

Assortment optimization under a multinomial logit model with position bias and social influence

Motivated by applications in retail, online advertising, and cultural markets, this paper studies the problem of finding an optimal assortment and positioning of products subject to a capacity constraint in a setting where consumers preferences can be modeled as a discrete choice under a multinomial logit model that captures the intrinsic product appeal, position biases, and social influence. For the static problem, we prove that the optimal assortment and positioning can be found in polynomial time. This is despite the fact that adding a product to the assortment may increase the probability of selecting the no-choice option, a phenomenon not observed in almost all models studied in the literature. We then consider the dynamics of such a market, where consumers are influenced by the aggregate past purchases. In this dynamic setting, we provide a small example to show that the natural and often used policy known as popularity ranking, that ranks products in decreasing order of the number of purchases, can reduce the expected profit as times goes by. We then prove that a greedy policy that applies the static optimal assortment and positioning at each period, always benefits from the popularity signal and outperforms any policy where consumers cannot observe the number of past purchases (in expectation).

Predicting a Community's Flu Dynamics with Mobile Phone Data

Human interactions that are sensed ubiquitously by mobile phones can improve a significant number of public health problems, particularly helping to track the spread of disease. In this paper, we evaluate multiple avenues for the integration of high-resolution face to face Bluetooth-sensed interaction networks into standard epidemic models. Our goal is to evaluate the capacity of the different avenues of integration to track the spread of seasonal influenza on a real-world community of 72 individuals over a period of 17 weeks. The dataset considered contains real-time tracking of individual flu symptoms over the whole observation period, providing a concrete individualized source for evaluation. We obtain an error of less than 2 infected people on average for predicting the total number of individuals affected by the flu and precision of approximately 30% when predicting exactly which individual will become infected at a given time. To the best of our knowledge, this is the first study considering mobile phone Bluetooth-sensed interaction data for dynamic infectious disease simulation that is evaluated against real human influenza occurrence. Our remarkable results indicate that high-resolution mobile phone data can increase the predictive power of even the simplest of epidemic models.