Diego Sáez-Trumper

Finding trendsetters in information networks

Influential people have an important role in the process of information diffusion. However, there are several ways to be influential, for example, to be the most popular or the first that adopts a new idea. In this paper we present a methodology to find trendsetters in information networks according to a specific topic of interest. Trendsetters are people that adopt and spread new ideas influencing other people before these ideas become popular. At the same time, not all early adopters are trendsetters because only few of them have the ability of propagating their ideas by their social contacts through word-of-mouth. Differently from other influence measures, a trendsetter is not necessarily popular or famous, but the one whose ideas spread over the graph successfully. Other metrics such as node in-degree or even standard Pagerank focus only in the static topology of the network. We propose a ranking strategy that focuses on the ability of some users to push new ideas that will be successful in the future. To that end, we combine temporal attributes of nodes and edges of the network with a Pagerank based algorithm to find the trendsetters for a given topic. To test our algorithm we conduct innovative experiments over a large Twitter dataset. We show that nodes with high in-degree tend to arrive late for new trends, while users in the top of our ranking tend to be early adopters that also influence their social contacts to adopt the new trend.

Measuring Urban Deprivation from User Generated Content

Measuring socioeconomic deprivation of cities in an accurate and timely fashion has become a priority for governments around the world, as the massive urbanization process we are witnessing is causing high levels of inequalities which require intervention. Traditionally, deprivation indexes have been derived from census data, which is however very expensive to obtain, and thus acquired only every few years. Alternative computational methods have been proposed in recent years to automatically extract proxies of deprivation at a fine spatio-temporal level of granularity; however, they usually require access to datasets (e.g., call details records) that are not publicly available to governments and agencies. To remedy this, we propose a new method to automatically mine deprivation at a fine level of spatio-temporal granularity that only requires access to freely available user-generated content. More precisely, the method needs access to datasets describing what urban elements are present in the physical environment; examples of such datasets are Foursquare and OpenStreetMap. Using these datasets, we quantitatively describe neighborhoods by means of a metric, called Offering Advantage, that reflects which urban elements are distinctive features of each neighborhood. We then use that metric to (i) build accurate classifiers of urban deprivation and (ii) interpret the outcomes through thematic analysis. We apply the method to three UK urban areas of different scale and elaborate on the results in terms of precision and recall.

Leveraging Social Context for Modeling Topic Evolution

Topic discovery and evolution (TDE) has been a problem which has gained long standing interest in the research community. The goal in topic discovery is to identify groups of keywords from large corpora so that the information in those corpora are summarized succinctly. The nature of text corpora has changed dramatically in the past few years with the advent of social media. Social media services allow users to constantly share, follow and comment on posts from other users. Hence, such services have given a new dimension to the traditional text corpus. The new dimension being that todays corpora have a social context embedded in them in terms of the community of users interested in a particular post, their profiles etc. We wish to harness this social context that comes along with the textual content for TDE. In particular, our goal is to both qualitatively and quantitatively analyze when social context actually helps with TDE. Methodologically, we approach the problem of TDE by a proposing non-negative matrix factorization (NMF) based model that incorporates both the textual information and social context information. We perform experiments on large scale real world dataset of news articles, and use Twitter as the platform providing information about the social context of these news articles. We compare with and outperform several state-of-the-art baselines. Our conclusion is that using the social context information is most useful when faced with topics that are particularly difficult to detect.

Beyond CPM and CPC: determining the value of users on OSNs

Not all of the over one billion users of online social networks (OSNs) are equally valuable to the OSNs. The current business model of monetizing advertisements targeted to users does not appear to be based on any visible grouping of the users. The primary metrics remain CPM (cost per mille---i.e., thousand impressions) and CPC (cost per click) of ads that are shown to users. However, there is significant diversity in the actions of users---some users upload interesting content triggering additional views and comments leading to further cascades of action. Beyond direct impressions, a users action can generate indirect impressions by actions induced on friends and other users. Identifying the valuable user segments requires examination of profile data, friendships, and most importantly, their activity. Here we explore an alternate approach for measuring the value of users in OSNs by proposing a framework from the viewpoint of a popular OSN. Using a real dataset on the social network and activities of users, we show that a small subset of actions are likely to be key indicators of a users value. Additionally, by examining the current targeting demographics available in Facebook, we are able to explore the relative (monetary) value that different users represent to the OSN.

A comparison of two different types of online social network from a data privacy perspective

We consider two distinct types of online social network, the first made up of a log of writes to wall by users in Facebook, and the second consisting of a corpus of emails sent and received in a corporate environment (Enron). We calculate the statistics which describe the topologies of each network represented as a graph. Then we calculate the information loss and risk of disclosure for different percentages of perturbation for each dataset, where perturbation is achieved by randomly adding links to the nodes. We find that the general tendency of information loss is similar, although Facebook is affected to a greater extent. For risk of disclosure, both datasets also follow a similar trend, except for the average path length statistic. We find that the differences are due to the different distributions of the derived factors, and also the type of perturbation used and its parameterization. These results can be useful for choosing and tuning anonymization methods for different graph datasets.

Wisdom of the Crowd or Wisdom of a Few?: An Analysis of Users' Content Generation

In this paper we analyze how user generated content (UGC) is created, challenging the well known it wisdom of crowds concept. Although it is known that user activity in most settings follow a power law, that is, few people do a lot, while most do nothing, there are few studies that characterize well this activity. In our analysis of datasets from two different social networks, Facebook and Twitter, we find that a small percentage of active users and much less of all users represent 50% of the UGC. We also analyze the dynamic behavior of the generation of this content to find that the set of most active users is quite stable in time. Moreover, we study the social graph, finding that those active users area a highly connected among them. This implies that most of the wisdom comes from a few users challenging the independence assumption needed to have a wisdom of crowds. We also address the content that is never seen by any people (the digital desert), which challenges the assumption that the content of every person should be taken in account in the collective decision. At the end this is not surprising, as the Web is a reflection of our own society, where economical or political power also is in the hands of minorities

Who Are My Audiences? A Study of the Evolution of Target Audiences in Microblogs

User behavior in online social media is not static, it evolves through the years. In Twitter, we have witnessed a maturation of its platform and its users due to endogenous and exogenous reasons. While the research using Twitter data has expanded rapidly, little work has studied the change/evolution in the Twitter ecosystem itself. In this paper, we use a taxonomy of the types of tweets posted by around 4M users during 10 weeks in 2011 and 2013. We classify users according to their tweeting behavior, and find 5 clusters for which we can associate a different dominant tweeting type. Furthermore, we observe the evolution of users across groups between 2011 and 2013 and find interesting insights such as the decrease in conversations and increase in URLs sharing. Our findings suggest that mature users evolve to adopt Twitter as a news media rather than a social network.

A Day of Your Days: Estimating Individual Daily Journeys Using Mobile Data to Understand Urban Flow

Travel surveys provide rich information about urban mobility and commuting patterns. But, at the same time, they have drawbacks: they are static pictures of a dynamic phenomena, are expensive to make, and take prolonged periods of time to finish. Nowadays, the availability of mobile usage data (Call Detail Records) makes the study of urban mobility possible at spatiotemporal granularity levels that surveys do not reach. This has been done in the past with good results -- mobile data makes possible to find and understand aggregated mobility patterns. In this paper, we propose to analyze mobile data at individual level by estimating daily journeys, and use those journeys to build Origin-Destiny matrices to understand urban flow. We evaluate this approach with large anonymized CDRs from Santiago, Chile, and find that our method has a high correlation (ρ = 0.89) with the current travel survey, and that it captures external anomalies in daily travel patterns, making our method suitable for inclusion into urban computing applications.