Statistical topic modeling is widely used in political science to study text. Researchers examine documents of varying lengths, from tweets to speeches. There is ongoing debate on how document length affects the interpretability of topic models. We investigate the effects of aggregating short documents into larger ones based on natural units that partition the corpus. In our study, we analyze one million tweets by U.S. state legislators from April 2016 to September 2020. We find that for documents aggregated at the account level, topics are more associated with individual states than when using individual tweets. This finding is replicated with Wikipedia pages aggregated by birth cities, showing how document definitions can impact topic modeling results.

The goal for classification is to correctly assign labels to unseen samples. However, most methods misclassify samples with unseen labels and assign them to one of the known classes. Open-Set Classification (OSC) algorithms aim to maximize both closed and open-set recognition capabilities. Recent studies showed the utility of such algorithms on small-scale data sets, but limited experimentation makes it difficult to assess their performances in real-world problems. Here, we provide a comprehensive comparison of various OSC algorithms, including training-based (SoftMax, Garbage, EOS) and post-processing methods (Maximum SoftMax Scores, Maximum Logit Scores, OpenMax, EVM, PROSER), the latter are applied on features from the former. We perform our evaluation on three large-scale protocols that mimic real-world challenges, where we train on known and negative open-set samples, and test on known and unknown instances. Our results show that EOS helps to improve performance of almost all post-processing algorithms. Particularly, OpenMax and PROSER are able to exploit better-trained networks, demonstrating the utility of hybrid models. However, while most algorithms work well on negative test samples -- samples of open-set classes seen during training -- they tend to perform poorly when tested on samples of previously unseen unknown classes, especially in challenging conditions.

In a car outside a convenience store in Flint, Michigan, in late 2016, Kemo Parks handed his cousin Dequavion Harris a gun. Things happened quickly after that: Witnesses saw Harris "with his arm up and extended" toward a red truck. The wounded driver sped off but crashed into a tree. EMTs rushed him to the hospital. He was dead on arrival.

Graphic footage: Fox News host Tucker Carlson weighs in on issues facing Americans ahead of the midterm elections on "Tucker Carlson Tonight." A Michigan man pleaded guilty last week to murdering, dismembering and eating the body parts of another man he met on a dating app. Mark David Latunski, 53, of Shiawassee County, Michigan, admitted in court last Thursday that he killed 25-year-old hairdresser Kevin Bacon after luring the University of Michigan-Flint student to his home in December 2019, according to local outlet Mlive.com. Latunski pleaded guilty as charged to mutilation of a body and to open murder, which encompasses murder in the first and second degree. Latunski acknowledged stabbing Bacon in the back and taking parts of his dead body to the kitchen, where he ate them, after meeting the young man on Grindr, which is a hookup app for gay, bisexual and transgender men.

More than six years after residents of Flint, Michigan, suffered widespread lead poisoning from their drinking water, hundreds of millions of dollars have been spent to improve water quality and bolster the city's economy. But residents still report a type of community PTSD, waiting in long grocery store lines to stock up on bottled water and filters. Media reports Wednesday said former governor Rick Snyder has been charged with neglect of duty for his role in the crisis. Snyder maintains his innocence, but he told Congress in 2016, "Local, state and federal officials--we all failed the families of Flint." One tool that emerged from the crisis is a form of artificial intelligence that could prevent similar problems in other cities where lead poisoning is a serious concern.

Internet of Things (IoT) networks consist of sensors, actuators, mobile and wearable devices that can connect to the Internet. With billions of such devices already in the market which have significant vulnerabilities, there is a dangerous threat to the Internet services and also some cyber-physical systems that are also connected to the Internet. Specifically, due to their existing vulnerabilities IoT devices are susceptible to being compromised and being part of a new type of stealthy Distributed Denial of Service (DDoS) attack, called Mongolian DDoS, which is characterized by its widely distributed nature and small attack size from each source. This study proposes a novel anomaly-based Intrusion Detection System (IDS) that is capable of timely detecting and mitigating this emerging type of DDoS attacks. The proposed IDS's capability of detecting and mitigating stealthy DDoS attacks with even very low attack size per source is demonstrated through numerical and testbed experiments.

Existing methods for reducing disparate performance of a classifier across different demographic groups assume that one has access to a large data set, thereby focusing on the algorithmic aspect of optimizing overall performance subject to additional constraints. However, poor data collection and imbalanced data sets can severely affect the quality of these methods. In this work, we consider a setting where data collection and optimization are performed simultaneously. In such a scenario, a natural strategy to mitigate the performance difference of the classifier is to provide additional training data drawn from the demographic groups that are worse off. In this paper, we propose to consistently follow this strategy throughout the whole training process and to guide the resulting classifier towards equal performance on the different groups by adaptively sampling each data point from the group that is currently disadvantaged. We provide a rigorous theoretical analysis of our approach in a simplified one-dimensional setting and an extensive experimental evaluation on numerous real-world data sets, including a case study on the data collected during the Flint water crisis.

More than a thousand days after the water problems in Flint, Michigan, became national news, thousands of homes in the city still have lead pipes, from which the toxic metal can leach into the water supply. To remedy the problem, the lead pipes need to be replaced with safer, copper ones. That sounds straightforward, but it is a challenge to figure out which homes have lead pipes in the first place. The City's records are incomplete and inaccurate. And digging up all the pipes would be costly and time-consuming.

The algorithm is saving about $10 million as part of an effort to replace the city's water infrastructure. To catch you up: In 2014, Flint began getting water from Flint River rather than the Detroit water system. Mistreatment of the new water supply, combined with old lead pipes, created contaminated water for residents. Solving the problem: Records that could be used to figure out which houses might be affected by corroded old pipes were missing or incomplete. So the city turned to AI.

EFFORTS are under way to replace the lead pipes that have been contaminating the water supply in the city of Flint, Michigan. Nobody knows which of the 55,000 properties are directly affected, but an artificially intelligent algorithm can make accurate guesses. The Flint water crisis began in 2014 when city officials began sourcing water from the local river instead of the Detroit water system. The water wasn't treated properly and corroded lead pipes, causing the heavy metal to leach into drinking water.