Search for: All records

Narrative data spans all disciplines and provides a coherent model of the world to the reader or viewer. Recent advancement in machine learning and Large Language Models (LLMs) have enable great strides in analyzing natural language. However, Large language models (LLMs) still struggle with complex narrative arcs as well as narratives containing conflicting information. Recent work indicates LLMs augmented with external knowledge bases can improve the accuracy and interpretability of the resulting models. In this work, we analyze the effectiveness of applying knowledge graphs (KGs) in understanding true-crime podcast data from both classical Natural Language Processing (NLP) and LLM approaches. We directly compare KG-augmented LLMs (KGLLMs) with classical methods for KG construction, topic modeling, and sentiment analysis. Additionally, the KGLLM allows us to query the knowledge base in natural language and test its ability to factually answer questions. We examine the robustness of the model to adversarial prompting in order to test the model's ability to deal with conflicting information. Finally, we apply classical methods to understand more subtle aspects of the text such as the use of hearsay and sentiment in narrative construction and propose future directions. Our results indicate that KGLLMs outperform LLMs on a variety of metrics, are more robust to adversarial prompts, and are more capable of summarizing the text into topics. 

We introduce a policy model coupled with the susceptible–infected- recovered (SIR) epidemic model to study interactions between policy-making and the dynamics of epidemics. We considered both single-region policies as well as game-theoretic models involving interactions among several regions and hierarchical interactions among policy-makers modeled as multi-layer games. We assumed that the policy functions are piece-wise constant with a minimum time interval for each policy stage, considering that policies cannot change frequently in time or be easily followed. The optimal policy was obtained by minimizing a cost function that consists of an implementation cost, an impact cost, and, in the case of multi-layer games, a non-compliance cost. We show, in a case study of COVID-19 in France, that when the cost function is reduced to the impact cost and parameterized as the final epidemic size, the solution approximates that of the optimal control in Bliman et al, (2021) for a sufficiently small minimum policy time interval. For a larger time interval, however, the optimal policy is a step down function, quite different from the step up structure typically deployed during the COVID-19 pandemic. In addition, we present a counterfactual study of how the pandemic would have evolved if herd immunity was reached during the second wave in the county of Los Angeles, California. Finally, we study a case of three interacting counties with and without a governing state. 

There is growing interest in U.S. cities to shift resources towards community-led solutions to crime and disorder. However, there is a simultaneous need to provide community organizations with access to real-time data to facilitate decision making, to which only the police normally have access. In this work we present a low-cost gunshot detection system with localization that has been developed for community-based violence interruption. The distributed real-time gunshot detection sensor network is linked to a mobile phone-based alert and tasking system for exclusive use by civilian gang interventionists. Here we present details on the system architecture and gunshot detection model, which consists of an Audio Spectrogram Transformer (AST) neural network. We then combine gradient maps of the input to the AST for time of arrival identification with a Bayesian maximum a posteriori estimation procedure to identify the location of gunshots. We conduct several experiments using simulated data, open data from the commercial ShotSpotter detection system in Pittsburgh, and data collected using our devices during live-fire experiments at the Indianapolis Metropolitan Police Department (IMPD) gun firing range. We then discuss potential applications of the system and directions for future research. 

Abstract The murder of George Floyd triggered a broad social response and noticeable shift in public opinion of policing. Since policing is dependent upon public cooperation, a question is whether the shift in opinion had an effect on police calls-for-service. Data from Los Angeles and New York City are evaluated using a regression discontinuity design. Violent crime, property crime, and quality-of-life disorder calls are analyzed to address differences in reporting norms. The role of racial–ethnic composition of local areas is assessed by examining census tracts where the majority of the residential population is Asian, Black, Hispanic, or White. Following the murder of George Floyd, in New York City violent crime, property crime, and quality-of-life calls all increased significantly. In Los Angeles, quality-of-life calls for service decreased significantly. The increase in violent crime calls observed in New York was greatest in areas where the majority of residents are Black, whereas the increase in property crime calls was the greatest in areas where a majority of residents are White. The decrease in quality-of-life calls observed in Los Angeles was in areas where the majority of residents are White. In both cases, the effect was relatively short-lived.