EPJ Data Science最新文献

Understanding stock market instability is a key question in financial management as practitioners seek to forecast breakdowns in long-run asset co-movement patterns which expose portfolios to rapid and devastating collapses in value. These disruptions are linked to changes in the structure of market wide stock correlations which increase the risk of high volatility shocks. The structure of these co-movements can be described as a network where companies are represented by nodes while edges capture correlations between their price movements. Co-movement breakdowns then manifest as abrupt changes in the topological structure of this network. Measuring the scale of this change and learning a timely indicator of breakdowns is central in understanding both financial stability and volatility forecasting. We propose to use the edge reconstruction accuracy of a graph auto-encoder as an indicator for how homogeneous connections between assets are, which we use, based on the literature of financial network analysis, as a proxy to infer market volatility. We show, through our experiments on the Standard and Poor's index over the 2015-2022 period, that the reconstruction errors from our model correlate with volatility spikes and can be used to improve out-of-sample autoregressive modeling of volatility. Our results demonstrate that market instability can be predicted by changes in the homogeneity in connections of the financial network which expands the understanding of instability in the stock market. We discuss the implications of this graph machine learning-based volatility estimation for policy targeted at ensuring financial market stability.

Credibility signals represent a wide range of heuristics typically used by journalists and fact-checkers to assess the veracity of online content. Automating the extraction of credibility signals presents significant challenges due to the necessity of training high-accuracy, signal-specific extractors, coupled with the lack of sufficiently large annotated datasets. This paper introduces Pastel (Prompted weAk Supervision wiTh crEdibility signaLs), a weakly supervised approach that leverages large language models (LLMs) to extract credibility signals from web content, and subsequently combines them to predict the veracity of content without relying on human supervision. We validate our approach using four article-level misinformation detection datasets, demonstrating that Pastel outperforms zero-shot veracity detection by 38.3% and achieves 86.7% of the performance of the state-of-the-art system trained with human supervision. Moreover, in cross-domain settings where training and testing datasets originate from different domains, Pastel significantly outperforms the state-of-the-art supervised model by 63%. We further study the association between credibility signals and veracity, and perform an ablation study showing the impact of each signal on model performance. Our findings reveal that 12 out of the 19 proposed signals exhibit strong associations with veracity across all datasets, while some signals show domain-specific strengths.

Supplementary information: The online version contains supplementary material available at 10.1140/epjds/s13688-025-00534-0.

The Covid-19 pandemic, caused by the SARS-Cov2- virus, has transformed our lives. To combat the spread of the infection, remote work has become a widespread practice. However, this shift has led to various work-related problems, including prolonged working hours, mental health issues, and communication difficulties. One particular challenge faced by team members is the inability to accurately gauge the work engagement (WE) levels of subordinates, such as their absorption, dedication, and vigor, due to the limited number of in-person interactions that occur in remote work settings. To address this issue, online communication systems utilizing text-based chat tools such as Slack and Microsoft Teams have gained popularity as substitutes for face-to-face communication. In this paper, we propose a novel approach that uses graph neural networks (GNNs) to estimate the work engagement levels (WELs) of users on text-based chat platforms. Specifically, our method involves embedding users in a feature space based solely on the structural information of the utilized communication network, without considering the contents of the conversations that take place. We conduct two studies using Slack data to evaluate our proposal. The first study reveals that the properties of communication networks play a more significant role when estimating WELs than do conversation contents. Building upon this result, the second study involves the development of a machine learning model that estimates WELs using only the architectural features of the employed communication network. In this network representation, each node corresponds to a human user, and edges represent communication logs; i.e., if person A talks to person B, the edge between node A and node B is stretched. Notably, our model achieves a correlation coefficient of 0.60 between the observed and predicted WEL values. Importantly, our proposed approach relies solely on communication network data and does not require linguistic information. This makes it particularly valuable for real-world business situations.

There are examples of how unconscious bias can influence actions of people. In the judiciary, however, despite some examples there is no general theory on whether different demographic attributes such as gender, seniority or ethnicity affect case sentencing. We aim to gain insight into this issue by analyzing over 100k decisions of three different areas of law with the goal of understanding whether judge identity or judge attributes such as gender and seniority can be inferred from decision documents. We find that stylistic features of decisions are predictive of judge identities, their gender and their seniority, a finding that is aligned with results from analysis of written texts outside the judiciary. Surprisingly, we find that features based on legislation cited are also predictive of judge identities and attributes. While own content reuse by judges can explain our ability to predict judge identities, no specific reduced set of features can explain the differences we find in the legislation cited of decisions when we group judges by gender or seniority. Our findings open the door for further research on how these differences translate into how judges apply the law and, ultimately, to promote a more transparent and fair judiciary system.

As nations progress, the impact of climate change on food prices becomes increasingly substantial. While the influence of climate change on the yields of major agricultural products is widely recognized, its specific effect on food prices remains uncertain. This study delves into the impact of the North Atlantic Oscillation (NAO) index, a well-established climate indicator, on global food prices. To accomplish this, a robust bivariate Hurst exponent (robust bHe) is applied. The study employs a sliding windows approach across various time scales to produce a color map of this coefficient, presenting a time-varying version. Furthermore, variable-lag transfer entropy with a sliding windows approach is utilized to discern causal relationships between the NAO index and international food prices. The findings reveal that significant increases in the NAO index are correlated with noteworthy upswings in various international food prices over both short and long-term periods. Additionally, variable-lag transfer entropy confirms the causal role of the NAO index in influencing international food prices.

The Ego Network Model (ENM) is a model for the structural organisation of relationships, rooted in evolutionary anthropology, that is found ubiquitously in social contexts. It takes the perspective of a single user (Ego) and organises their contacts (Alters) into a series of (typically 5) concentric circles of decreasing intimacy and increasing size. Alters are sorted based on their tie strength to the Ego, however, this is difficult to measure directly. Traditionally, the interaction frequency has been used as a proxy but this misses the qualitative aspects of connections, such as signs (i.e. polarity), which have been shown to provide extremely useful information. However, the sign of an online social relationship is usually an implicit piece of information, which needs to be estimated by interaction data from Online Social Networks (OSNs), making sign prediction in OSNs a research challenge in and of itself. This work aims to bring the ENM into the signed networks domain by investigating the interplay of signed connections with the ENM. This paper delivers 2 main contributions. Firstly, a new and data-efficient method of signing relationships between individuals using sentiment analysis and, secondly, we provide an in-depth look at the properties of Signed Ego Networks (SENs), using 9 Twitter datasets of various categories of users. We find that negative connections are generally over-represented in the active part of the Ego Networks, suggesting that Twitter greatly over-emphasises negative relationships with respect to “offline” social networks. Further, users who use social networks for professional reasons have an even greater share of negative connections. Despite this, we also found weak signs that less negative users tend to allocate more cognitive effort to individual relationships and thus have smaller ego networks on average. All in all, even though structurally ENMs are known to be similar in both offline and online social networks, our results indicate that relationships on Twitter tend to nurture more negativity than offline contexts.

The extensive data generated on social media platforms allow us to gain insights over trending topics and public opinions. Additionally, it offers a window into user behavior, including their content engagement and news sharing habits. In this study, we analyze the relationship between users’ political ideologies and the news they share during Argentina’s 2019 election period. Our findings reveal that users predominantly share news that aligns with their political beliefs, despite accessing media outlets with diverse political leanings. Moreover, we observe a consistent pattern of users sharing articles related to topics biased to their preferred candidates, highlighting a deeper level of political alignment in online discussions. We believe that this systematic analysis framework can be applied to similar scenarios in different countries, especially those marked by significant political polarization, akin to Argentina.

Social influence pervades our everyday lives and lays the foundation for complex social phenomena, such as the spread of misinformation and the polarization of communities. A disconnect appears between psychology approaches, generally performed and tested in controlled lab experiments, and quantitative methods, which are usually data-driven and rely on network and event analysis. The former are slow, expensive to deploy, and typically do not generalize well to topical issues; the latter often oversimplify the complexities of social influence and ignore psychosocial literature. This work bridges this gap by introducing a human-in-the-loop active learning method that empirically quantifies social influence by crowdsourcing pairwise influence comparisons. We develop simulation and fitting tools, allowing us to estimate the required budget based on the design features and the worker’s decision accuracy. We perform a series of pilot studies to quantify the impact of design features on worker accuracy. We deploy our method to estimate the influence ranking of 500 X/Twitter users. We validate our measure by showing that the obtained empirical influence is tightly linked with agency and communion, the Big Two of social cognition, with agency being the most important dimension for influence formation.

Networks to distribute goods, from raw materials to food and medicines, are the backbone of a functioning economy. They are shaped by several supply relations connecting manufacturers, distributors, and final buyers worldwide. We present a network-based model to describe the mechanisms underlying the emergence and growth of distribution networks. In our model, firms consider two practices when establishing new supply relations: centralization, the tendency to choose highly connected partners, and multi-sourcing, the preference for multiple suppliers. Centralization enhances network efficiency by leveraging short distribution paths; multi-sourcing fosters resilience by providing multiple distribution paths connecting final buyers to the manufacturer. We validate the proposed model using data on drug shipments in the US. Drawing on these data, we reconstruct 22 nationwide pharmaceutical distribution networks. We demonstrate that the proposed model successfully replicates several structural features of the empirical networks, including their out-degree and path length distributions as well as their resilience and efficiency properties. These findings suggest that the proposed firm-level practices effectively capture the network growth process that leads to the observed structures.

With the increasing pervasiveness of Information and Communication Technology (ICT) in the fabric of economic activities, the corporate digital divide has become a crucial issue for the assessment of Information Technology (IT) competencies and the digital gap between firms and territories. With little granular data available to measure the phenomenon, most studies have used survey data. To address this empirical gap, we scanned the homepages of 182,705 Italian companies and extracted ten characteristics related to their digital footprint to develop a new index for the corporate digital assessment. Our results show a significant digital divide between Italian companies according to size, sector and geographical location, opening new perspectives for monitoring and data-driven analysis.