All types of research, development, and policy work can have unintended, adverse consequences - work in responsible artificial intelligence (RAI), ethical AI, or ethics in AI is no exception.
Graph neural networks (GNNs) are increasingly used in critical human applications for predicting node labels in attributed graphs. Their ability to aggregate features from nodes' neighbors for accurate classification also has the capacity to exacerbate existing biases in data or to introduce new ones towards members from protected demographic groups. Thus, it is imperative to quantify how GNNs may be biased and to what extent their harmful effects may be mitigated. To this end, we propose two new GNN-agnostic interventions namely, (i) PFR-AX which decreases the separability between nodes in protected and non-protected groups, and (ii) PostProcess which updates model predictions based on a blackbox policy to minimize differences between error rates across demographic groups. Through a large set of experiments on four datasets, we frame the efficacies of our approaches (and three variants) in terms of their algorithmic fairness-accuracy tradeoff and benchmark our results against three strong baseline interventions on three state-of-the-art GNN models. Our results show that no single intervention offers a universally optimal tradeoff, but PFR-AX and PostProcess provide granular control and improve model confidence when correctly predicting positive outcomes for nodes in protected groups.
Among the seven key requirements to achieve trustworthy AI proposed by the High-Level Expert Group on Artificial Intelligence (AI-HLEG) established by the European Commission (EC), the fifth requirement ("Diversity, non-discrimination and fairness") declares: "In order to achieve Trustworthy AI, we must enable inclusion and diversity throughout the entire AI system's life cycle. [...] This requirement is closely linked with the principle of fairness". In this paper, we try to shed light on how closely these two distinct concepts, diversity and fairness, may be treated by focusing on information access systems and ranking literature. These concepts should not be used interchangeably because they do represent two different values, but what we argue is that they also cannot be considered totally unrelated or divergent. Having diversity does not imply fairness, but fostering diversity can effectively lead to fair outcomes, an intuition behind several methods proposed to mitigate the disparate impact of information access systems, i.e. recommender systems and search engines.
We present the results of a 12-week longitudinal user study wherein the participants, 110 subjects from Southern Europe, received on a daily basis Electronic Music (EM) diversified recommendations. By analyzing their explicit and implicit feedback, we show that exposure to specific levels of music recommendation diversity may be responsible for long-term impacts on listeners' attitudes. In particular, we highlight the function of diversity in increasing the openness in listening to EM, a music genre not particularly known or liked by the participants previous to their participation in the study. Moreover, we demonstrate that recommendations may help listeners in removing positive and negative attachments towards EM, deconstructing pre-existing implicit associations but also stereotypes associated with this music. In addition, our results show the significant clout that recommendation diversity has in generating curiosity in listeners.
Relevant and timely information collected from social media during crises can be an invaluable resource for emergency management. However, extracting this information remains a challenging task, particularly when dealing with social media postings in multiple languages. This work proposes a cross-lingual method for retrieving and summarizing crisis-relevant information from social media postings. We describe a uniform way of expressing various information needs through structured queries and a way of creating summaries answering those information needs. The method is based on multilingual transformers embeddings. Queries are written in one of the languages supported by the embeddings, and the extracted sentences can be in any of the other languages supported. Abstractive summaries are created by transformers. The evaluation, done by crowdsourcing evaluators and emergency management experts, and carried out on collections extracted from Twitter during five large-scale disasters spanning ten languages, shows the flexibility of our approach. The generated summaries are regarded as more focused, structured, and coherent than existing state-of-the-art methods, and experts compare them favorably against summaries created by existing, state-of-the-art methods.
Artificial Intelligence (AI) is increasingly used to build Decision Support Systems (DSS) across many domains. This paper describes a series of experiments designed to observe human response to different characteristics of a DSS such as accuracy and bias, particularly the extent to which participants rely on the DSS, and the performance they achieve. In our experiments, participants play a simple online game inspired by so-called "wildcat" (i.e., exploratory) drilling for oil. The landscape has two layers: a visible layer describing the costs (terrain), and a hidden layer describing the reward (oil yield). Participants in the control group play the game without receiving any assistance, while in treatment groups they are assisted by a DSS suggesting places to drill. For certain treatments, the DSS does not consider costs, but only rewards, which introduces a bias that is observable by users. Between subjects, we vary the accuracy and bias of the DSS, and observe the participants' total score, time to completion, the extent to which they follow or ignore suggestions. We also measure the acceptability of the DSS in an exit survey. Our results show that participants tend to score better with the DSS, that the score increase is due to users following the DSS advice, and related to the difficulty of the game and the accuracy of the DSS. We observe that this setting elicits mostly rational behavior from participants, who place a moderate amount of trust in the DSS and show neither algorithmic aversion (under-reliance) nor automation bias (over-reliance).However, their stated willingness to accept the DSS in the exit survey seems less sensitive to the accuracy of the DSS than their behavior, suggesting that users are only partially aware of the (lack of) accuracy of the DSS.
Recommender systems typically suggest to users content similar to what they consumed in the past. If a user happens to be exposed to strongly polarized content, she might subsequently receive recommendations which may steer her towards more and more radicalized content, eventually being trapped in what we call a "radicalization pathway". In this paper, we study the problem of mitigating radicalization pathways using a graph-based approach. Specifically, we model the set of recommendations of a "what-to-watch-next" recommender as a d-regular directed graph where nodes correspond to content items, links to recommendations, and paths to possible user sessions. We measure the "segregation" score of a node representing radicalized content as the expected length of a random walk from that node to any node representing non-radicalized content. High segregation scores are associated to larger chances to get users trapped in radicalization pathways. Hence, we define the problem of reducing the prevalence of radicalization pathways by selecting a small number of edges to "rewire", so to minimize the maximum of segregation scores among all radicalized nodes, while maintaining the relevance of the recommendations. We prove that the problem of finding the optimal set of recommendations to rewire is NP-hard and NP-hard to approximate within any factor. Therefore, we turn our attention to heuristics, and propose an efficient yet effective greedy algorithm based on the absorbing random walk theory. Our experiments on real-world datasets in the context of video and news recommendations confirm the effectiveness of our proposal.
Music listening in today's digital spaces is highly characterized by the availability of huge music catalogues, accessible by people all over the world. In this scenario, recommender systems are designed to guide listeners in finding tracks and artists that best fit their requests, having therefore the power to influence the diversity of the music they listen to. Albeit several works have proposed new techniques for developing diversity-aware recommendations, little is known about how people perceive diversity while interacting with music recommendations. In this study, we interview several listeners about the role that diversity plays in their listening experience, trying to get a better understanding of how they interact with music recommendations. We recruit the listeners among the participants of a previous quantitative study, where they were confronted with the notion of diversity when asked to identify, from a series of electronic music lists, the most diverse ones according to their beliefs. As a follow-up, in this qualitative study we carry out semi-structured interviews to understand how listeners may assess the diversity of a music list and to investigate their experiences with music recommendation diversity. We report here our main findings on 1) what can influence the diversity assessment of tracks and artists' music lists, and 2) which factors can characterize listeners' interaction with music recommendation diversity.
This paper describes SciClops, a method to help combat online scientific misinformation. Although automated fact-checking methods have gained significant attention recently, they require pre-existing ground-truth evidence, which, in the scientific context, is sparse and scattered across a constantly-evolving scientific literature. Existing methods do not exploit this literature, which can effectively contextualize and combat science-related fallacies. Furthermore, these methods rarely require human intervention, which is essential for the convoluted and critical domain of scientific misinformation. SciClops involves three main steps to process scientific claims found in online news articles and social media postings: extraction, clustering, and contextualization. First, the extraction of scientific claims takes place using a domain-specific, fine-tuned transformer model. Second, similar claims extracted from heterogeneous sources are clustered together with related scientific literature using a method that exploits their content and the connections among them. Third, check-worthy claims, broadcasted by popular yet unreliable sources, are highlighted together with an enhanced fact-checking context that includes related verified claims, news articles, and scientific papers. Extensive experiments show that SciClops tackles sufficiently these three steps, and effectively assists non-expert fact-checkers in the verification of complex scientific claims, outperforming commercial fact-checking systems.
In this work, the problem of predicting dropout risk in undergraduate studies is addressed from a perspective of algorithmic fairness. We develop a machine learning method to predict the risks of university dropout and underperformance. The objective is to understand if such a system can identify students at risk while avoiding potential discriminatory biases. When modeling both risks, we obtain prediction models with an Area Under the ROC Curve (AUC) of 0.77-0.78 based on the data available at the enrollment time, before the first year of studies starts. This data includes the students' demographics, the high school they attended, and their admission (average) grade. Our models are calibrated: they produce estimated probabilities for each risk, not mere scores. We analyze if this method leads to discriminatory outcomes for some sensitive groups in terms of prediction accuracy (AUC) and error rates (Generalized False Positive Rate, GFPR, or Generalized False Negative Rate, GFNR). The models exhibit some equity in terms of AUC and GFNR along groups. The similar GFNR means a similar probability of failing to detect risk for students who drop out. The disparities in GFPR are addressed through a mitigation process that does not affect the calibration of the model.