Discovering causal effects is at the core of scientific investigation but remains challenging when only observational data is available. In practice, causal networks are difficult to learn and interpret, and limited to relatively small datasets. We report a more reliable and scalable causal discovery method (iMIIC), based on a general mutual information supremum principle, which greatly improves the precision of inferred causal relations while distinguishing genuine causes from putative and latent causal effects. We showcase iMIIC on synthetic and real-life healthcare data from 396,179 breast cancer patients from the US Surveillance, Epidemiology, and End Results program. More than 90\% of predicted causal effects appear correct, while the remaining unexpected direct and indirect causal effects can be interpreted in terms of diagnostic procedures, therapeutic timing, patient preference or socio-economic disparity. iMIIC's unique capabilities open up new avenues to discover reliable and interpretable causal networks across a range of research fields.

The spread of online misinformation threatens public health, democracy, and the broader society. While professional fact-checkers form the first line of defense by fact-checking popular false claims, they do not engage directly in conversations with misinformation spreaders. On the other hand, non-expert ordinary users act as eyes-on-the-ground who proactively counter misinformation -- recent research has shown that 96% counter-misinformation responses are made by ordinary users. However, research also found that 2/3 times, these responses are rude and lack evidence. This work seeks to create a counter-misinformation response generation model to empower users to effectively correct misinformation. This objective is challenging due to the absence of datasets containing ground-truth of ideal counter-misinformation responses, and the lack of models that can generate responses backed by communication theories. In this work, we create two novel datasets of misinformation and counter-misinformation response pairs from in-the-wild social media and crowdsourcing from college-educated students. We annotate the collected data to distinguish poor from ideal responses that are factual, polite, and refute misinformation. We propose MisinfoCorrect, a reinforcement learning-based framework that learns to generate counter-misinformation responses for an input misinformation post. The model rewards the generator to increase the politeness, factuality, and refutation attitude while retaining text fluency and relevancy. Quantitative and qualitative evaluation shows that our model outperforms several baselines by generating high-quality counter-responses. This work illustrates the promise of generative text models for social good -- here, to help create a safe and reliable information ecosystem. The code and data is accessible on https://github.com/claws-lab/MisinfoCorrect.

The aggravating effects of climate change and the growing population in hurricane-prone areas escalate the challenges in large-scale hurricane evacuations. While hurricane preparedness and response strategies vastly rely on the accuracy and timeliness of the predicted households' evacuation decisions, current studies featuring psychological-driven linear models leave some significant limitations in practice. Hence, the present study proposes a new methodology for predicting households' evacuation decisions constructed by easily accessible demographic and resource-related predictors compared to current models with a high reliance on psychological factors. Meanwhile, an enhanced logistic regression (ELR) model that could automatically account for nonlinearities (i.e., univariate and bivariate threshold effects) by an interpretable machine learning approach is developed to secure the accuracy of the results. Specifically, low-depth decision trees are selected for nonlinearity detection to identify the critical thresholds, build a transparent model structure, and solidify the robustness. Then, an empirical dataset collected after Hurricanes Katrina and Rita is hired to examine the practicability of the new methodology. The results indicate that the enhanced logistic regression (ELR) model has the most convincing performance in explaining the variation of the households' evacuation decision in model fit and prediction capability compared to previous linear models. It suggests that the proposed methodology could provide a new tool and framework for the emergency management authorities to improve the estimation of evacuation traffic demands in a timely and accurate manner.

While combining imitation learning (IL) and reinforcement learning (RL) is a promising way to address poor sample efficiency in autonomous behavior acquisition, methods that do so typically assume that the requisite behavior demonstrations are provided by an expert that behaves optimally with respect to a task reward. If, however, suboptimal demonstrations are provided, a fundamental challenge appears in that the demonstration-matching objective of IL conflicts with the return-maximization objective of RL. This paper introduces D-Shape, a new method for combining IL and RL that uses ideas from reward shaping and goal-conditioned RL to resolve the above conflict. D-Shape allows learning from suboptimal demonstrations while retaining the ability to find the optimal policy with respect to the task reward. We experimentally validate D-Shape in sparse-reward gridworld domains, showing that it both improves over RL in terms of sample efficiency and converges consistently to the optimal policy in the presence of suboptimal demonstrations.

In recent years, hate speech has gained great relevance in social networks and other virtual media because of its intensity and its relationship with violent acts against members of protected groups. Due to the great amount of content generated by users, great effort has been made in the research and development of automatic tools to aid the analysis and moderation of this speech, at least in its most threatening forms. One of the limitations of current approaches to automatic hate speech detection is the lack of context. Most studies and resources are performed on data without context; that is, isolated messages without any type of conversational context or the topic being discussed. This restricts the available information to define if a post on a social network is hateful or not. In this work, we provide a novel corpus for contextualized hate speech detection based on user responses to news posts from media outlets on Twitter. This corpus was collected in the Rioplatense dialectal variety of Spanish and focuses on hate speech associated with the COVID-19 pandemic. Classification experiments using state-of-the-art techniques show evidence that adding contextual information improves hate speech detection performance for two proposed tasks (binary and multi-label prediction). We make our code, models, and corpus available for further research.

Researchers at the University of New Orleans want to use artificial intelligence to evaluate and detect potential deficiencies in the United States' floodwater control structures. The proposal includes the creation of an automated program using unmanned aerial system imagery and other sensory data to assess the integrity and stability of the nation's flood control systems. The Joseph Canizaro and James Livingston Gulf States Center for Environmental Informatics (GulfSCEI, pronounced Gulfsea) at the University of New Orleans has secured a one-year contract worth $1.25 million from the U.S. Army Corps of Engineers (USACE) for the research. The research will be performed jointly with USACE's domain experts. As part of its national flood risk management plan, the USACE has planned, designed and constructed over 700 dam and reservoir projects and more than 13,500 miles of federally authorized levees and floodwalls.

Artificial intelligence and machine learning have grown in popularity in recent decades as a result of advances in high-performance computing and open-source software. At the core, machine learning provides a statistical inference based on the inputs provided by the user, in which algorithms learn relationships between input data and output results. The complexity of these algorithms allows for the discovery of patterns and trends invisible to the human analyst, making it important to create analysis-appropriate input for these models to ensure that they answer the questions we are asking. This training will provide attendees an overview of machine learning in regards to Earth Science, and how to apply these algorithms and techniques to remote sensing data in a meaningful way. Attendees will also be provided with end-to-end case study examples for generating a simple random forest model for land cover classification from optical remote sensing.

New York attorney and writer Alexander Zubatov weighs in on how A.I. is rapidly changing society and says he's concerned about A.I. being used as a weapon against descent on'The Ingraham Angle.' Virginia Gov. Glenn Youngkin said Thursday that more school districts should ban the ChatGPT artificial intelligence tool. The Republican said during a CNN evening town hall that the U.S. should be clear about its goal as a nation "which is to make sure that our kids can think and, therefore, if a machine is thinking for them, then we're not accomplishing our goal." "I do think that it's something to be very careful of, and I do think more districts, more school districts should ban it," the governor said. Earlier in the year, public schools in northern Virginia blocked the chatbot from county-issued devices. ARE YOU READY FOR AI VOICE CLONING ON YOUR PHONE?

An artificial intelligence could soon allow players to transform their video game character to look like anything or anyone they want, simply by typing a description. "If you want to be a movie star, or you want to be an animal, or you want to be anything, you just type on your keyboard and, boom, you will have a character that looks like what you described," says Zhengxia Zou at Beihang University in Beijing, China.

Are ChatGPT and generative AI a blessing or a curse for security teams? While artificial intelligence (AI)'s ability to generate malicious code and phishing emails presents new challenges for organizations, it's also opened the door to a range of defensive use cases, from threat detection and remediation guidance, to securing Kubernetes and cloud environments. Recently, VentureBeat reached out to some of PWC's top analysts, who shared their thoughts on how generative AI and tools like ChatGPT will impact the threat landscape and what use cases will emerge for defenders. Follow VentureBeat's ongoing generative AI coverage Overall, the analysts were optimistic that defensive use cases will rise to combat malicious uses of AI over the long term. Below is an edited transcript of their responses.