Link prediction accuracy on real-world networks under non-uniform missing-edge patterns.

Real-world network datasets are typically obtained in ways that fail to capture all edges. The patterns of missing data are often non-uniform as they reflect biases and other shortcomings of different data collection methods. Nevertheless, uniform missing data is a common assumption made when no additional information is available about the underlying missing-edge pattern, and link prediction methods are frequently tested against uniformly missing edges. To investigate the impact of different missing-edge patterns on link prediction accuracy, we employ 9 link prediction algorithms from 4 different families to analyze 20 different missing-edge patterns that we categorize into 5 groups. Our comparative simulation study, spanning 250 real-world network datasets from 6 different domains, provides a detailed picture of the significant variations in the performance of different link prediction algorithms in these different settings. With this study, we aim to provide a guide for future researchers to help them select a link prediction algorithm that is well suited to their sampled network data, considering the data collection process and application domain.

The structure and function of antagonistic ties in village social networks.

Negative or antagonistic relationships are common in human social networks, but they are less often studied than positive or friendly relationships. The existence of a capacity to have and to track antagonistic ties raises the possibility that they may serve a useful function in human groups. Here, we analyze empirical data gathered from 24,770 and 22,513 individuals in 176 rural villages in Honduras in two survey waves 2.5 y apart in order to evaluate the possible relevance of antagonistic relationships for broader network phenomena. We find that the small-world effect is more significant in a positive world with negative ties compared to an otherwise similar hypothetical positive world without them. Additionally, we observe that nodes with more negative ties tend to be located near network bridges, with lower clustering coefficients, higher betweenness centralities, and shorter average distances to other nodes in the network. Positive connections tend to have a more localized distribution, while negative connections are more globally dispersed within the networks. Analysis of the possible impact of such negative ties on dynamic processes reveals that, remarkably, negative connections can facilitate the dissemination of information (including novel information experimentally introduced into these villages) to the same degree as positive connections, and that they can also play a role in mitigating idea polarization within village networks. Antagonistic ties hold considerable importance in shaping the structure and function of social networks.

Causally estimating the effect of YouTube's recommender system using counterfactual bots.

In recent years, critics of online platforms have raised concerns about the ability of recommendation algorithms to amplify problematic content, with potentially radicalizing consequences. However, attempts to evaluate the effect of recommenders have suffered from a lack of appropriate counterfactuals-what a user would have viewed in the absence of algorithmic recommendations-and hence cannot disentangle the effects of the algorithm from a user's intentions. Here we propose a method that we call "counterfactual bots" to causally estimate the role of algorithmic recommendations on the consumption of highly partisan content on YouTube. By comparing bots that replicate real users' consumption patterns with "counterfactual" bots that follow rule-based trajectories, we show that, on average, relying exclusively on the YouTube recommender results in less partisan consumption, where the effect is most pronounced for heavy partisan consumers. Following a similar method, we also show that if partisan consumers switch to moderate content, YouTube's sidebar recommender "forgets" their partisan preference within roughly 30 videos regardless of their prior history, while homepage recommendations shift more gradually toward moderate content. Overall, our findings indicate that, at least since the algorithm changes that YouTube implemented in 2019, individual consumption patterns mostly reflect individual preferences, where algorithmic recommendations play, if anything, a moderating role.

Sequential stacking link prediction algorithms for temporal networks.

Link prediction algorithms are indispensable tools in many scientific applications by speeding up network data collection and imputing missing connections. However, in many systems, links change over time and it remains unclear how to optimally exploit such temporal information for link predictions in such networks. Here, we show that many temporal topological features, in addition to having high computational cost, are less accurate in temporal link prediction than sequentially stacked static network features. This sequential stacking link prediction method uses 41 static network features that avoid detailed feature engineering choices and is capable of learning a highly accurate predictive distribution of future connections from historical data. We demonstrate that this algorithm works well for both partially observed and completely unobserved target layers, and on two temporal stochastic block models achieves near-oracle-level performance when combined with other single predictor methods as an ensemble learning method. Finally, we empirically illustrate that stacking multiple predictive methods together further improves performance on 19 real-world temporal networks from different domains.

The enmity paradox.

The "friendship paradox" of social networks states that, on average, "your friends have more friends than you do". Here, we theoretically and empirically explore a related and overlooked paradox we refer to as the "enmity paradox". We use empirical data from 24,678 people living in 176 villages in rural Honduras. We empirically show that, for a real negative undirected network (created by symmetrizing antagonistic interactions), the paradox exists as it does in the positive world. Specifically, a person's enemies have more enemies, on average, than a person does. Furthermore, in a mixed world of positive and negative ties, we study the conditions for the existence of the paradox, which we refer to as the "mixed-world paradox", both theoretically and empirically, finding that, for instance, a person's friends typically have more enemies than a person does. We also confirm the "generalized" enmity paradox for non-topological attributes in real data, analogous to the generalized friendship paradox (e.g., the claim that a person's enemies are richer, on average, than a person is). As a consequence, the naturally occurring variance in the degree distribution of both friendship and antagonism in social networks can skew people's perceptions of the social world.

Examining the consumption of radical content on YouTube.

Although it is under-studied relative to other social media platforms, YouTube is arguably the largest and most engaging online media consumption platform in the world. Recently, YouTube's scale has fueled concerns that YouTube users are being radicalized via a combination of biased recommendations and ostensibly apolitical "anti-woke" channels, both of which have been claimed to direct attention to radical political content. Here we test this hypothesis using a representative panel of more than 300,000 Americans and their individual-level browsing behavior, on and off YouTube, from January 2016 through December 2019. Using a labeled set of political news channels, we find that news consumption on YouTube is dominated by mainstream and largely centrist sources. Consumers of far-right content, while more engaged than average, represent a small and stable percentage of news consumers. However, consumption of "anti-woke" content, defined in terms of its opposition to progressive intellectual and political agendas, grew steadily in popularity and is correlated with consumption of far-right content off-platform. We find no evidence that engagement with far-right content is caused by YouTube recommendations systematically, nor do we find clear evidence that anti-woke channels serve as a gateway to the far right. Rather, consumption of political content on YouTube appears to reflect individual preferences that extend across the web as a whole.

Stacking models for nearly optimal link prediction in complex networks.

Most real-world networks are incompletely observed. Algorithms that can accurately predict which links are missing can dramatically speed up network data collection and improve network model validation. Many algorithms now exist for predicting missing links, given a partially observed network, but it has remained unknown whether a single best predictor exists, how link predictability varies across methods and networks from different domains, and how close to optimality current methods are. We answer these questions by systematically evaluating 203 individual link predictor algorithms, representing three popular families of methods, applied to a large corpus of 550 structurally diverse networks from six scientific domains. We first show that individual algorithms exhibit a broad diversity of prediction errors, such that no one predictor or family is best, or worst, across all realistic inputs. We then exploit this diversity using network-based metalearning to construct a series of "stacked" models that combine predictors into a single algorithm. Applied to a broad range of synthetic networks, for which we may analytically calculate optimal performance, these stacked models achieve optimal or nearly optimal levels of accuracy. Applied to real-world networks, stacked models are superior, but their accuracy varies strongly by domain, suggesting that link prediction may be fundamentally easier in social networks than in biological or technological networks. These results indicate that the state of the art for link prediction comes from combining individual algorithms, which can achieve nearly optimal predictions. We close with a brief discussion of limitations and opportunities for further improvements.