In medicine, treatments often influence multiple, interdependent outcomes, such as primary endpoints, complications, adverse events, or other secondary endpoints. Hence, to make optimal treatment decisions, clinicians are interested in learning the distribution of multi-dimensional treatment outcomes. However, the vast majority of machine learning methods for predicting treatment effects focus on single-outcome settings, despite the fact that medical data often include multiple, interdependent outcomes. To address this limitation, we propose a novel diffusion-based method called DIME to learn the joint distribution of multiple outcomes of medical treatments. Our DIME method addresses three challenges relevant in medical practice: (i) our method is tailored to learn the joint interventional distribution of multiple medical outcomes, which enables reliable decision-making with uncertainty quantification rather than relying solely on point estimates; (ii) our method explicitly captures the dependence structure between outcomes; and (iii) our method can handle outcomes of mixed type, including binary, categorical, and continuous variables. In our method, we take into account the fundamental problem of causal inference, where only outcomes for the assigned treatment are observed, through causal masking. For training, our method decomposes the joint distribution into a series of conditional distributions with a customized conditional masking to account for the dependence structure across outcomes. For inference, our method auto-regressively generates predictions. This allows our method to move beyond point estimates of causal quantities and thus learn the joint interventional distribution. To the best of our knowledge, DIME is the first neural method tailored to learn the joint, multi-outcome distribution of medical treatments. Across various experiments, we demonstrate that our method effectively learns the joint distribution and captures shared information among multiple outcomes.

Hate speech on social media threatens the mental and physical well-being of individuals and contributes to real-world violence. Resharing is an important driver behind the spread of hate speech on social media. Yet, little is known about who reshares hate speech and what their characteristics are. In this paper, we analyze the role of user characteristics in hate speech resharing across different types of hate speech (e.g., political hate). For this, we first cluster hate speech posts using large language models into different types of hate speech. Then we model the effects of user attributes on users' probability to reshare hate speech using an explainable machine learning model. To do so, we apply debiasing to control for selection bias in our observational social media data and further control for the latent vulnerability of users to hate speech. We find that, all else equal, users with fewer followers, fewer friends, fewer posts, and older accounts share more hate speech. This shows that users with little social influence tend to share more hate speech. Further, we find substantial heterogeneity across different types of hate speech. For example, racist and misogynistic hate is spread mostly by users with little social influence. In contrast, political anti-Trump and anti-right-wing hate is reshared by users with larger social influence. Overall, understanding the factors that drive users to share hate speech is crucial for detecting individuals at risk of engaging in harmful behavior and for designing effective mitigation strategies. Disclaimer: This work contains terms that are offensive and hateful.

The Sustainable Development Goals (SDGs) of the United Nations provide a blueprint of a better future by "leaving no one behind", and, to achieve the SDGs by 2030, poor countries require immense volumes of development aid. In this paper, we develop a causal machine learning framework for predicting heterogeneous treatment effects of aid disbursements to inform effective aid allocation. Specifically, our framework comprises three components: (i) a balancing autoencoder that uses representation learning to embed high-dimensional country characteristics while addressing treatment selection bias; (ii) a counterfactual generator to compute counterfactual outcomes for varying aid volumes to address small sample-size settings; and (iii) an inference model that is used to predict heterogeneous treatment-response curves. We demonstrate the effectiveness of our framework using data with official development aid earmarked to end HIV/AIDS in 105 countries, amounting to more than USD 5.2 billion. For this, we first show that our framework successfully computes heterogeneous treatment-response curves using semi-synthetic data. Then, we demonstrate our framework using real-world HIV data. Our framework points to large opportunities for a more effective aid allocation, suggesting that the total number of new HIV infections could be reduced by up to 3.3% (~50,000 cases) compared to the current allocation practice.

Fake news undermines individuals’ ability to make informed decisions. However, the theoretical understanding of how users assess online news as real or fake has thus far remained incomplete. In particular, previous research cannot explain why users fall for fake news inadvertently and despite careful thinking. In this work, we study the role of affect when users assess online news as real or fake. We employ NeuroIS measurements as a complementary approach beyond self-reports, which allows us to capture affective responses in situ, i.e., directly in the moment they occur. We draw upon cognitive dissonance theory, which suggests that users experiencing affective responses avoid unpleasant information to reduce psychological discomfort. In our NeuroIS experiment, we measured affective responses based on electrocardiography and eye tracking. We find that lower heart rate variability and shorter mean fixation duration are associated with greater perceived fakeness and a higher probability of incorrect assessments, thus providing evidence of affective information processing. These findings imply that users may fall for fake news automatically and without even noticing. This has direct implications for information systems (IS) research and practice as effective countermeasures against fake news must account for affective information processing.

Machine learning can provide predictions with disparate outcomes, in which subgroups of the population (e.g., defined by age, gender, or other sensitive attributes) are systematically disadvantaged. In order to comply with upcoming legislation, practitioners need to locate such disparate outcomes. However, previous literature typically detects disparities through statistical procedures for when the sensitive attribute is specified a priori. This limits applicability in real-world settings where datasets are high dimensional and, on top of that, sensitive attributes may be unknown. As a remedy, we propose a data-driven framework called Automatic Location of Disparities (ALD) which aims at locating disparities in machine learning. ALD meets several demands from industry: ALD (1) is applicable to arbitrary machine learning classifiers; (2) operates on different definitions of disparities (e.g., statistical parity or equalized odds); (3) deals with both categorical and continuous predictors even if disparities arise from complex and multi-way interactions known as intersectionality (e.g., age above 60 and female). ALD produces interpretable audit reports as output. We demonstrate the effectiveness of ALD based on both synthetic and real-world datasets. As a result, we empower practitioners to effectively locate and mitigate disparities in machine learning algorithms, conduct algorithmic audits, and protect individuals from discrimination.

Information in industry, research, and the public sector is widely stored as rendered documents (e.g., PDF files, scans). Hence, to enable downstream tasks, systems are needed that map rendered documents onto a structured hierarchical format. However, existing systems for this task are limited by heuristics and are not end-to-end trainable. In this work, we introduce the Document Structure Generator (DSG), a novel system for document parsing that is fully end-to-end trainable. DSG combines a deep neural network for parsing (i) entities in documents (e.g., figures, text blocks, headers, etc.) and (ii) relations that capture the sequence and nested structure between entities. Unlike existing systems that rely on heuristics, our DSG is trained end-to-end, making it effective and flexible for real-world applications. We further contribute a new, large-scale dataset called E-Periodica comprising real-world magazines with complex document structures for evaluation. Our results demonstrate that our DSG outperforms commercial OCR tools and, on top of that, achieves state-of-the-art performance. To the best of our knowledge, our DSG system is the first end-to-end trainable system for hierarchical document parsing.

The social media platform "Parler'' has emerged into a prominent fringe community where a significant part of the user base are self-reported supporters of QAnon, a far-right conspiracy theory alleging that a cabal of elites controls global politics. QAnon is considered to have had an influential role in the public discourse during the 2020 U.S. presidential election. However, little is known about QAnon supporters on Parler and what sets them aside from other users. Building up on social identity theory, we aim to profile the characteristics of QAnon supporters on Parler. We analyze a large-scale dataset with more than 600,000 profiles of English-speaking users on Parler. Based on users' profiles, posts, and comments, we then extract a comprehensive set of user features, linguistic features, network features, and content features. This allows us to perform user profiling and understand to what extent these features discriminate between QAnon and non-QAnon supporters on Parler. Our analysis is three-fold: (1) We quantify the number of QAnon supporters on Parler, finding that 34,913 users (5.5% of all users) openly report supporting the conspiracy. (2) We examine differences between QAnon vs. non-QAnon supporters. We find that QAnon supporters differ statistically significantly from non-QAnon supporters across multiple dimensions. For example, they have, on average, a larger number of followers, followees, and posts, and thus have a large impact on the Parler network. (3) We use machine learning to identify which user characteristics discriminate QAnon from non-QAnon supporters. We find that user features, linguistic features, network features, and content features, can - to a large extent - discriminate QAnon vs. non-QAnon supporters on Parler. In particular, we find that user features are highly discriminatory, followed by content features and linguistic features.

The storming of the U.S. Capitol on January 6, 2021 has led to the killing of 5 people and is widely regarded as an attack on democracy. The storming was largely coordinated through social media networks such as Twitter and "Parler". Yet little is known regarding how users interacted on Parler during the storming of the Capitol. In this work, we examine the emotion dynamics on Parler during the storming with regard to heterogeneity across time and users. For this, we segment the user base into different groups (e.g., Trump supporters and QAnon supporters). We use affective computing to infer the emotions in content, thereby allowing us to provide a comprehensive assessment of online emotions. Our evaluation is based on a large-scale dataset from Parler, comprising of 717,300 posts from 144,003 users. We find that the user base responded to the storming of the Capitol with an overall negative sentiment. Akin to this, Trump supporters also expressed a negative sentiment and high levels of unbelief. In contrast to that, QAnon supporters did not express a more negative sentiment during the storming. We further provide a cross-platform analysis and compare the emotion dynamics on Parler and Twitter. Our findings point at a comparatively less negative response to the incidents on Parler compared to Twitter accompanied by higher levels of disapproval and outrage. Our contribution to research is three-fold: (1) We identify online emotions that were characteristic of the storming; (2) we assess emotion dynamics across different user groups on Parler; (3) we compare the emotion dynamics on Parler and Twitter. Thereby, our work offers important implications for actively managing online emotions to prevent similar incidents in the future.

False rumors are known to have detrimental effects on society. To prevent the spread of false rumors, social media platforms such as Twitter must detect them early. In this work, we develop a novel probabilistic mixture model that classifies true vs. false rumors based on the underlying spreading process. Specifically, our model is the first to formalize the self-exciting nature of true vs. false retweeting processes. This results in a novel mixture marked Hawkes model (MMHM). Owing to this, our model obviates the need for feature engineering; instead, it directly models the spreading process in order to make inferences of whether online rumors are incorrect. Our evaluation is based on 13,650 retweet cascades of both true. vs. false rumors from Twitter. Our model recognizes false rumors with a balanced accuracy of 64.97 % and an AUC of 69.46 %. It outperforms state-of-the-art baselines (both neural and feature engineering) by a considerable margin but while being fully interpretable. Our work has direct implications for practitioners: it leverages the spreading process as an implicit quality signal and, based on it, detects false content.

Machine learning is widely used in e-commerce to analyze clickstream sessions and then to allocate marketing resources. Traditional neural learning can model long-term dependencies in clickstream data, yet it ignores the different shopping phases (i. e., goal-directed search vs. browsing) in user behavior as theorized by marketing research. In this paper, we develop a novel, theory-informed machine learning model to account for different shopping phases as defined in marketing theory. Specifically, we formalize a tailored attentive deep Markov model called ClickstreamDMM for predicting the risk of user exits without purchase in e-commerce web sessions. Our ClickstreamDMM combines (1) an attention network to learn long-term dependencies in clickstream data and (2) a latent variable model to capture different shopping phases (i. e., goal-directed search vs. browsing). Due to the interpretable structure, our ClickstreamDMM allows marketers to generate new insights on how shopping phases relate to actual purchase behavior. We evaluate our model using real-world clickstream data from a leading e-commerce platform consisting of 26,279 sessions with 250,287 page clicks. Thereby, we demonstrate that our model is effective in predicting user exits without purchase: compared to existing baselines, it achieves an improvement by 11.5 % in AUROC and 12.7 % in AUPRC. Overall, our model enables e-commerce platforms to detect users at the risk of exiting without purchase. Based on it, e-commerce platforms can then intervene with marketing resources to steer users toward purchasing.

Location-based services, such as Foursquare, Google Places, and Yelp, offer rich data on places that users visit, i. e., check-ins from points-of-interest (POIs). By mining check-in data, one can make predictions regarding the expected number of check-ins that new POIs will generate. Such predictions are highly relevant for location planning at both companies and public bodies (i. e., to estimate the expected customer visits of retail sites or public facilities). In this work, we propose a new machine learning approach for modeling check-in counts with the distinctive property of being highly interpretable. Specifically, our objective is to model the latent customer flow between retail site locations. To this end, we model the expected check-in count such that it is lowered due to competition among nearby POIs, while additional check-ins can be attracted when customers transition among complementary POIs. Our latent customer flow model is then extended by additional sources of spatial heterogeneity. The model is demonstrated based on data from 2.7 million user check-ins from retail stores across three different cities. As a result, our model yields accurate predictions of check-in counts while simultaneously achieving a high degree of interpretability. The latter is achieved by deriving a tailored multi-variate fixed-point iteration.

Decision-making often requires accurate estimation of treatment effects from observational data. This is challenging as outcomes of alternative decisions are not observed and have to be estimated. Previous methods estimate outcomes based on unconfoundedness but neglect any constraints that unconfoundedness imposes on the outcomes. In this paper, we propose a novel regularization framework for estimating average treatment effects that exploits unconfoundedness. To this end, we formalize unconfoundedness as an orthogonality constraint, which ensures that the outcomes are orthogonal to the treatment assignment. This orthogonality constraint is then included in the loss function via a regularization. Based on our regularization framework, we develop deep orthogonal networks for unconfounded treatments (DONUT), which learn outcomes that are orthogonal to the treatment assignment. Using a variety of benchmark datasets for estimating average treatment effects, we demonstrate that DONUT outperforms the state-of-the-art substantially.

Clinical practice in intensive care units (ICUs) requires early warnings when a patient's condition is about to deteriorate so that preventive measures can be undertaken. To this end, prediction algorithms have been developed that estimate the risk of mortality in ICUs. In this work, we propose a novel generative deep probabilistic model for real-time risk scoring in ICUs. Specifically, we develop an attentive deep Markov model called AttDMM. To the best of our knowledge, AttDMM is the first ICU prediction model that jointly learns both long-term disease dynamics (via attention) and different disease states in health trajectory (via a latent variable model). Our evaluations were based on an established baseline dataset (MIMIC-III) with 53,423 ICU stays. The results confirm that compared to state-of-the-art baselines, our AttDMM was superior: AttDMM achieved an area under the receiver operating characteristic curve (AUROC) of 0.876, which yielded an improvement over the state-of-the-art method by 2.2%. In addition, the risk score from the AttDMM provided warnings several hours earlier. Thereby, our model shows a path towards identifying patients at risk so that health practitioners can intervene early and save patient lives.

To manage the COVID-19 epidemic effectively, decision-makers in public health need accurate forecasts of case numbers. A potential near real-time predictor of future case numbers is human mobility; however, research on the predictive power of mobility is lacking. To fill this gap, we introduce a novel model for epidemic forecasting based on mobility data, called mobility marked Hawkes model. The proposed model consists of three components: (1) A Hawkes process captures the transmission dynamics of infectious diseases. (2) A mark modulates the rate of infections, thus accounting for how the reproduction number R varies across space and time. The mark is modeled using a regularized Poisson regression based on mobility covariates. (3) A correction procedure incorporates new cases seeded by people traveling between regions. Our model was evaluated on the COVID-19 epidemic in Switzerland. Specifically, we used mobility data from February through April 2020, amounting to approximately 1.5 billion trips. Trip counts were derived from large-scale telecommunication data, i.e., cell phone pings from the Swisscom network, the largest telecommunication provider in Switzerland. We compared our model against various state-of-the-art baselines in terms of out-of-sample root mean squared error. We found that our model outperformed the baselines by 15.52%. The improvement was consistently achieved across different forecast horizons between 5 and 21 days. In addition, we assessed the predictive power of conventional point of interest data, confirming that telecommunication data is superior. To the best of our knowledge, our work is the first to predict the spread of COVID-19 from telecommunication data. Altogether, our work contributes to previous research by developing a scalable early warning system for decision-makers in public health tasked with controlling the spread of infectious diseases.

The quality of healthcare provided by hospitals is subject to considerable variability. Consequently, accurate measurements of hospital performance are essential for various decision-makers, including patients, hospital managers and health insurers. Hospital performance is assessed via the health outcomes of their patients. However, as the risk profiles of patients between hospitals vary, measuring hospital performance requires adjustment for patient risk. This task is formalized in the state-of-the-art procedure through a hierarchical generalized linear model, that isolates hospital fixed-effects from the effect of patient risk on health outcomes. Due to the linear nature of this approach, any non-linear relations or interaction terms between risk variables are neglected.In this work, we propose a novel method for measuring hospital performance adjusted for patient risk. This method captures non-linear relationships as well as interactions among patient risk variables, specifically the effect of co-occurring health conditions on health outcomes. For this purpose, we develop a tailored neural network architecture that is partially interpretable: a non-linear part is used to encode risk factors, while a linear structure models hospital fixed-effects, such that the risk-adjusted hospital performance can be estimated. We base our evaluation on more than 13 million patient admissions across almost 1,900 US hospitals as provided by the Nationwide Readmissions Database. Our model improves the ROC-AUC over the state-of-the-art by 4.1 percent. These findings demonstrate that a large portion of the variance in health outcomes can be attributed to non-linear relationships between patient risk variables and implicate that the current approach of measuring hospital performance should be expanded.

Misinformation in social media - such as fake news, rumors, or other forms of deceptive content - poses a significant threat to society and, hence, scalable strategies for an early detection of online cascades with misinformation are in dire need. The prominent approach in detecting online cascades with misinformation builds upon neural networks based on sequences of simple structural features of the propagation dynamics (e.g., cascade size, average retweeting time). However, these structural features neglect large parts of the information in the cascade. As a remedy, we propose a novel tree-structured neural network named Cascade-LSTM.

Most users leave e-commerce websites with no purchase. Hence, it is important for website owners to detect users at risk of exiting and intervene early (e. g., adapting website content or offering price promotions). Prior approaches make widespread use of clickstream data; however, state-of-the-art algorithms only model the sequence of web pages visited and not the time spent on them.

In e-commerce, product presentations, and particularly images, are known to provide important information for user decision-making, and yet the relationship between images and prices has not been studied. To close this research gap, we suggest a tailored web mining framework, since one must quantify the relative contribution of image content in describing prices ceteris paribus. That is, one must account for the fact that such images inherently depict heterogeneous products. In order to isolate the pricing power of image content, we suggest a three-stage framework involving deep learning and statistical inference.

Points-of-interest (POIs; i.e., restaurants, bars, landmarks, and other entities) are common in web-mined data: they greatly explain the spatial distributions of urban phenomena. The conventional modeling approach relies upon feature engineering, yet it ignores the spatial structure among POIs. In order to overcome this shortcoming, the present paper proposes a novel spatial model for explaining spatial distributions based on web-mined POIs. Our key contributions are: (1) We present a rigorous yet highly interpretable formalization in order to model the influence of POIs on a given outcome variable. Specifically, we accommodate the spatial distributions of both the outcome and POIs. In our case, this modeled by the sum of latent Gaussian processes. (2) In contrast to previous literature, our model infers the influence of POIs without feature engineering, instead we model the influence of POIs via distance-weighted kernel functions with fully learnable parameterizations. (3) We propose a scalable learning algorithm based on sparse variational approximation. For this purpose, we derive a tailored evidence lower bound (ELBO) and, for appropriate likelihoods, we even show that an analytical expression can be obtained. This allows fast and accurate computation of the ELBO. Finally, the value of our approach for web mining is demonstrated in two real-world case studies. Our findings provide substantial improvements over state-of-the-art baselines with regard to both predictive and, in particular, explanatory performance. Altogether, this yields a novel spatial model for leveraging web-mined POIs. Within the context of location-based social networks, it promises an extensive range of new insights and use cases.

Personalization in marketing aims at improving the shopping experience of customers by tailoring services to individuals. In order to achieve this, businesses must be able to make personalized predictions regarding the next purchase. That is, one must forecast the exact list of items that will comprise the next purchase, \ie, the so-called market basket. Despite its relevance to firm operations, this problem has received surprisingly little attention in prior research, largely due to its inherent complexity. In fact, state-of-the-art approaches are limited to intuitive decision rules for pattern extraction, so that repeat purchases or co-purchases can be identified. However, the simplicity of the pre-coded rules impedes performance, since decision rules operate in an autoregressive fashion: the rules can only make inferences from past purchases of a single customer without taking into account the knowledge transfer that takes place between customers.

Question answering promises a means of efficiently searching web-based content repositories such as Wikipedia. However, the systems of this type most prevalent today merely conduct their learning once in an offline training phase while, afterwards, all parameters remain static. Thus, the possibility of improvement over time is precluded. As a consequence of this shortcoming, question answering is not currently taking advantage of the wealth of feedback mechanisms that have become prominent on the web (e. g., buttons for liking, voting, or sharing).

In this paper, we analyze possible interferences that occur when developing information systems for cyberphysical systems – hybrids containing legacy technical components and added IT modules. In particular, the enhancement of electricity systems through IT components, resulting in smart grid and smart home solutions, is experiencing increasing adoption rates in advanced and developing countries alike. Due to the substantial interdependence with and reliance on often decades-old legacy infrastructure, these cyberphysical systems present particular opportunities and challenges for the associated information systems. We propose that one channel through which information systems improve cyberphysical systems is by enhancing the components of the legacy system with new features. Introducing the Design–Interference Model, we conceptualize IS design for cyberphysical systems and outline possible obstacles and interferences associated with it. Using a simulation experiment for a smart grid application as a showcase, we derive insights into how to address these challenges. We condense these results into actionable advice that, first, seeks to validate existing guidelines for design-oriented research, second, extends and focuses them on cyberphysical system applications and, third, provides guidance to researchers and practitioners in this increasingly relevant area of information system development.