Mainstream media, through their decisions on what to cover and how to frame the stories they cover, can mislead readers without using outright falsehoods.Therefore, it is crucial to have tools that expose these editorial choices underlying media bias.In this paper, we introduce the Media Bias Detector, a tool for researchers, journalists, and news consumers.By integrating large language models, we provide near real-time granular insights into the topics, tone, political lean, and facts of news articles aggregated to the publisher level.We assessed the tool's impact by interviewing 13 experts from journalism, communications, and political science, revealing key insights into usability and functionality, practical applications, and AI's role in powering media bias tools.We explored this in more depth with a follow-up survey of 150 news consumers.This work highlights opportunities for AI-driven tools that empower users to critically engage with media content, particularly in politically charged environments.

The past 15 years have witnessed a remarkable increase in both the scale and scope of social and behavioral data available to researchers, leading some to herald the emergence of a new field: "computational social science." Against these exciting developments stands a stubborn fact: that in spite of many thousands of published papers, there has been surprisingly little progress on the "big" questions that motivated the field in the first place?questions concerning systemic risk in financial systems, problem solving in complex organizations, and the dynamics of epidemics or social movements, among others. In this talk I highlight some examples of research that would not have been possible just a handful of years ago and that illustrate the promise of CSS. At the same time, they illustrate its limitations. I then conclude with some thoughts on how CSS can bridge the gap between its current state and its potential.

How predictable is success in complex social systems? In spite of a recent profusion of prediction studies that exploit online social and information network data, this question remains unanswered, in part because it has not been adequately specified. In this paper we attempt to clarify the question by presenting a simple stylized model of success that attributes prediction error to one of two generic sources: insufficiency of available data and/or models on the one hand; and inherent unpredictability of complex social systems on the other. We then use this model to motivate an illustrative empirical study of information cascade size prediction on Twitter. Despite an unprecedented volume of information about users, content, and past performance, our best performing models can explain less than half of the variance in cascade sizes. In turn, this result suggests that even with unlimited data predictive performance would be bounded well below deterministic accuracy. Finally, we explore this potential bound theoretically using simulations of a diffusion process on a random scale free network similar to Twitter. We show that although higher predictive power is possible in theory, such performance requires a homogeneous system and perfect ex-ante knowledge of it: even a small degree of uncertainty in estimating product quality or slight variation in quality across products leads to substantially more restrictive bounds on predictability. We conclude that realistic bounds on predictive accuracy are not dissimilar from those we have obtained empirically, and that such bounds for other complex social systems for which data is more difficult to obtain are likely even lower.

Recommendation systems are an increasingly prominent part of the web, accounting for up to a third of all traffic on several of the world's most popular sites. Nevertheless, little is known about how much activity such systems actually cause over and above activity that would have occurred via other means (e.g., search) if recommendations were absent. Although the ideal way to estimate the causal impact of recommendations is via randomized experiments, such experiments are costly and may inconvenience users. In this paper, therefore, we present a method for estimating causal effects from purely observational data. Specifically, we show that causal identification through an instrumental variable is possible when a product experiences an instantaneous shock in direct traffic and the products recommended next to it do not. We then apply our method to browsing logs containing anonymized activity for 2.1 million users on Amazon.com over a 9 month period and analyze over 4,000 unique products that experience such shocks. We find that although recommendation click-throughs do account for a large fraction of traffic among these products, at least 75% of this activity would likely occur in the absence of recommendations. We conclude with a discussion about the assumptions under which the method is appropriate and caveats around extrapolating results to other products, sites, or settings.

Cooperation in repeated games has been widely studied in experimental settings; however, the duration over which players participate in such experiments is typically confined to at most hours, and often to a single game. Given that in real world settings people may have years of experience, it is natural to ask how behavior in cooperative games evolves over the long run. Here we analyze behavioral data from three distinct games involving 571 individual experiments conducted over a two-year interval. First, in the case of a standard linear public goods game we show that as players gain experience, they become less generous both on average and in particular towards the end of each game. Second, we analyze a multiplayer prisoner's dilemma where players are also allowed to make and break ties with their neighbors, finding that experienced players show an increase in cooperativeness early on in the game, but exhibit sharper "endgame" effects. Third, and finally, we analyze a collaborative search game in which players can choose to act selfishly or cooperatively, finding again that experienced players exhibit more cooperative behavior as well as sharper endgame effects. Together these results show consistent evidence of long-run learning, but also highlight directions for future theoretical work that may account for the observed direction and magnitude of the effects.

Agent-based models are a popular way to explore the dynamics of human interactions, but rarely are these models based on empirical observations of actual human behavior. Here we exploit data collected in an experimental setting where over 150 human players played in a series of almost a hundred public goods games. First, we fit a series of deterministic models to the data, finding that a reasonably parsimonious model with just three parameters performs extremely well on the standard test of predicting average contributions. This same model, however, performs extremely poorly when predicting the full distribution of contributions, which is strongly bimodal. In response, we introduce and test a corresponding series of stochastic models, thus identifying a model that both predicts average contribution and also the full distribution. Finally, we deploy this model to explore hypotheses about regions of the parameter space outside of what was experimentally accessible. In particular, we investigate (a) whether a previous conclusion that network topology does not impact contribution levels holds for much larger networks than could be studied in a lab; (b) to what extent observed contributions depend on average network degree and variance in the degree distribution, and (c) the dependency of contributions on degree assortativity as well as the correlation between the generosity of players and the degree of the nodes to which they are assigned.

The Internet and the Web have transformed society, spawning new industries, altering social and cultural practices, and challenging long-accepted notions of individual privacy, intellectual property, and national security. In this talk, I argue that social science is also being transformed. In particular, I describe how crowd sourcing sites like Amazon's Mechanical Turk are increasingly being used by researchers to create "virtual labs" in which they can conduct behavioral experiments on a scale and speed that would have been hard to imagine just a decade ago. To illustrate the point, I describe some recent experiments that showcase the advantages of virtual over traditional physical labs, as well as some of the limitations. I then discuss how this relatively new experimental capability may unfold in the near future, along with some implications for social and behavioral science.

Models of networked diffusion that are motivated by analogy with the spread of infectious disease have been applied to a wide range of social and economic adoption processes, including those related to new products, ideas, norms and behaviors. However, it is unknown how accurately these models account for the empirical structure of diffusion over networks. Here we describe the diffusion patterns arising from seven online domains, ranging from communications platforms to networked games to microblogging services, each involving distinct types of content and modes of sharing. We find strikingly similar patterns across all domains.

The natural tendency for humans to choose with whom to form new relationships and with whom to end established relationships is thought to facilitate the emergence of cooperation. Helping cooperators to mix assortatively is believed to reinforce the rewards accruing to mutual cooperation while simultaneously excluding defectors. However, the relationship between endogenous partner selection, assortativity, and cooperation has been largely unexplored experimentally. Here we report on a series of human subjects experiments in which groups of 24 participants played a multi-player prisoner's dilemma game where, critically, they were also allowed to propose and delete links to players of their own choosing at some variable rate. Over a wide variety of parameter settings and initial conditions, we found that endogenous partner selection significantly increased the level of cooperation, the average payoffs to players, and the assortativity between cooperators. Even relatively slow update rates were sufficient to produce large effects resulting in cooperation levels over 80%. Subsequent increases to the update rate still had a positive, although smaller, effect. For standard prisoner's dilemma payoffs, we also found that assortativity resulted predominantly from cooperators avoiding defectors, not by severing ties with defecting partners, and that cooperation correspondingly suffered. Finally, by modifying the payoffs to satisfy two novel conditions, we found that cooperators did punish defectors by severing ties, leading to levels of cooperation approaching 100% which persisted for longer.

In this paper we investigate the attributes and relative influence of 1.6M Twitter users by tracking 74 million diffusion events that took place on the Twitter follower graph over a two month interval in 2009. Unsurprisingly, we find that the largest cascades tend to be generated by users who have been influential in the past and who have a large number of followers. We also find that URLs that were rated more interesting and/or elicited more positive feelings by workers on Mechanical Turk were more likely to spread. In spite of these intuitive results, however, we find that predictions of which particular user or URL will generate large cascades are relatively unreliable. We conclude, therefore, that word-of-mouth diffusion can only be harnessed reliably by targeting large numbers of potential influencers, thereby capturing average effects. Finally, we consider a family of hypothetical marketing strategies, defined by the relative cost of identifying versus compensating potential "influencers." We find that although under some circumstances, the most influential users are also the most cost-effective, under a wide range of plausible assumptions the most cost-effective performance can be realized using "ordinary influencers"---individuals who exert average or even less-than-average influence.

We study several longstanding questions in media communications research, in the context of the microblogging service Twitter, regarding the production, flow, and consumption of information. To do so, we exploit a recently introduced feature of Twitter known as "lists" to distinguish between elite users - by which we mean celebrities, bloggers, and representatives of media outlets and other formal organizations - and ordinary users. Based on this classification, we find a striking concentration of attention on Twitter, in that roughly 50% of URLs consumed are generated by just 20K elite users, where the media produces the most information, but celebrities are the most followed. We also find significant homophily within categories: celebrities listen to celebrities, while bloggers listen to bloggers etc; however, bloggers in general rebroadcast more information than the other categories. Next we re-examine the classical "two-step flow" theory of communications, finding considerable support for it on Twitter. Third, we find that URLs broadcast by different categories of users or containing different types of content exhibit systematically different lifespans. And finally, we examine the attention paid by the different user categories to different news topics.

Social science is often concerned with the emergence of collective behavior out of the interactions of large numbers of individuals, but in this regard it has long suffered from a severe measurement problem - namely that individual-level behavior and interactions are hard to observe, especially at scale and over time. In this talk, I will argue that the technological revolution of the Internet is beginning to lift this constraint. To illustrate, I will describe several examples of internet-based research that would have been impractical to perform until recently, and that shed light on some longstanding sociological questions. Although internet-based research still faces serious methodological and procedural obstacles, I propose that the ability to study truly "social" dynamics at individual-level resolution will have dramatic consequences for social science.

Citing recent successes in forecasting elections, movies, products, and other outcomes, prediction market advocates call for widespread use of market-based methods for government and corporate decision making. Though theoretical and empirical evidence suggests that markets do often outperform alternative mechanisms, less attention has been paid to the magnitude of improvement. Here we compare the performance of prediction markets to conventional methods of prediction, namely polls and statistical models. Examining thousands of sporting and movie events, we find that the relative advantage of prediction markets is surprisingly small, as measured by squared error, calibration, and discrimination. Moreover, these domains also exhibit remarkably steep diminishing returns to information, with nearly all the predictive power captured by only two or three parameters. As policy makers consider adoption of prediction markets, costs should be weighed against potentially modest benefits.

Researchers increasingly use electronic communication data to construct and study large social networks, effectively inferring unobserved ties (e.g. i is connected to j) from observed communication events (e.g. i emails j). Often overlooked, however, is the impact of tie definition on the corresponding network, and in turn the relevance of the inferred network to the research question of interest. Here we study the problem of network inference and relevance for two email data sets of different size and origin. In each case, we generate a family of networks parameterized by a threshold condition on the frequency of emails exchanged between pairs of individuals. After demonstrating that different choices of the threshold correspond to dramatically different network structures, we then formulate the relevance of these networks in terms of a series of prediction tasks that depend on various network features. In general, we find: a) that prediction accuracy is maximized over a non-trivial range of thresholds corresponding to 5-10 reciprocated emails per year; b) that for any prediction task, choosing the optimal value of the threshold yields a sizable (~30%) boost in accuracy over naive choices; and c) that the optimal threshold value appears to be (somewhat surprisingly) consistent across data sets and prediction tasks. We emphasize the practical utility in defining ties via their relevance to the prediction task(s) at hand and discuss implications of our empirical results.

The increasing availability of electronic communication data, such as that arising from e-mail exchange, presents social and information scientists with new possibilities for characterizing individual behavior and, by extension, identifying latent structure in human populations. Here, we propose a model of individual e-mail communication that is sufficiently rich to capture meaningful variability across individuals, while remaining simple enough to be interpretable. We show that the model, a cascading non-homogeneous Poisson process, can be formulated as a double-chain hidden Markov model, allowing us to use an efficient inference algorithm to estimate the model parameters from observed data. We then apply this model to two e-mail data sets consisting of 404 and 6,164 users, respectively, that were collected from two universities in different countries and years. We find that the resulting best-estimate parameter distributions for both data sets are surprisingly similar, indicating that at least some features of communication dynamics generalize beyond specific contexts. We also find that variability of individual behavior over time is significantly less than variability across the population, suggesting that individuals can be classified into persistent "types". We conclude that communication patterns may prove useful as an additional class of attribute data, complementing demographic and network data, for user classification and outlier detection-a point that we illustrate with an interpretable clustering of users based on their inferred model parameters.

The "algorithmic small-world hypothesis" states that not only are pairs of individuals in a large social network connected by short paths, but that ordinary individuals can find these paths. Although theoretically plausible, empirical evidence for the hypothesis is limited, as most chains in "small-world" experiments fail to complete, thereby biasing estimates of "true" chain lengths. Using data from two recent small-world experiments, comprising a total of 162,328 message chains, and directed at one of 30 "targets" spread across 19 countries, we model heterogeneity in chain attrition rates as a function of individual attributes. We then introduce a rigorous way of estimating true chain lengths that is provably unbiased, and can account for empirically-observed variation in attrition rates. Our findings provide mixed support for the algorithmic hypothesis. On the one hand, it appears that roughly half of all chains can be completed in 6-7 steps--thus supporting the "six degrees of separation" assertion--but on the other hand, estimates of the mean are much longer, suggesting that for at least some of the population, the world is not "small" in the algorithmic sense. We conclude that search distances in social networks are fundamentally different from topological distances, for which the mean and median of the shortest path lengths between nodes tend to be similar.

Social networks are of interest to researchers in part because they are thought to mediate the flow of information in communities and organizations. Here we study the temporal dynamics of communication using on-line data, including e-mail communication among the faculty and staff of a large university over a two-year period. We formulate a temporal notion of "distance" in the underlying social network by measuring the minimum time required for information to spread from one node to another - a concept that draws on the notion of vector-clocks from the study of distributed computing systems. We find that such temporal measures provide structural insights that are not apparent from analyses of the pure social network topology. In particular, we define the network backbone to be the subgraph consisting of edges on which information has the potential to flow the quickest. We find that the backbone is a sparse graph with a concentration of both highly embedded edges and long-range bridges - a finding that sheds new light on the relationship between tie strength and connectivity in social networks.