Authorship analysis is an important subject in the field of natural language processing. It allows the detection of the most likely writer of articles, news, books, or messages. This technique has multiple uses in tasks related to authorship attribution, detection of plagiarism, style analysis, sources of misinformation, etc. The focus of this paper is to explore the limitations and sensitiveness of established approaches to adversarial manipulations of inputs. To this end, and using those established techniques, we first developed an experimental frame-work for author detection and input perturbations. Next, we experimentally evaluated the performance of the authorship detection model to a collection of semantic-preserving adversarial perturbations of input narratives. Finally, we compare and analyze the effects of different perturbation strategies, input and model configurations, and the effects of these on the author detection model.

Corruption continues to be one of the biggest societal challenges of our time. New hope is placed in Artificial Intelligence (AI) to serve as an unbiased anti-corruption agent. Ever more available (open) government data paired with unprecedented performance of such algorithms render AI the next frontier in anti-corruption. Summarizing existing efforts to use AI-based anti-corruption tools (AI-ACT), we introduce a conceptual framework to advance research and policy. It outlines why AI presents a unique tool for top-down and bottom-up anti-corruption approaches. For both approaches, we outline in detail how AI-ACT present different potentials and pitfalls for (a) input data, (b) algorithmic design, and (c) institutional implementation. Finally, we venture a look into the future and flesh out key questions that need to be addressed to develop AI-ACT while considering citizens' views, hence putting "society in the loop".

In this paper, we ask whether vocal source features (pitch, shimmer, jitter, etc) can improve the performance of automatic sung speech recognition, arguing that conclusions previously drawn from spoken speech studies may not be valid in the sung speech domain. We first use a parallel singing/speaking corpus (NUS-48E) to illustrate differences in sung vs spoken voicing characteristics including pitch range, syllables duration, vibrato, jitter and shimmer. We then use this analysis to inform speech recognition experiments on the sung speech DSing corpus, using a state of the art acoustic model and augmenting conventional features with various voice source parameters. Experiments are run with three standard (increasingly large) training sets, DSing1 (15.1 hours), DSing3 (44.7 hours) and DSing30 (149.1 hours). Pitch combined with degree of voicing produces a significant decrease in WER from 38.1% to 36.7% when training with DSing1 however smaller decreases in WER observed when training with the larger more varied DSing3 and DSing30 sets were not seen to be statistically significant. Voicing quality characteristics did not improve recognition performance although analysis suggests that they do contribute to an improved discrimination between voiced/unvoiced phoneme pairs.

On January 20th, while the world's attention was focussed on the Inauguration, David Lynch quietly turned seventy-five. He spent the day the way he's spent almost every day since the pandemic began: sheltered in his Los Angeles home, engaged with self-prescribed daily routines. "If you have a habit pattern," Lynch told me, over Zoom, "the more conscious part of your mind can concentrate on your work, and you can get ideas and do those things, and the rest sort of takes care of itself in the background." It sounded practical and wholesome, until Lynch related an example: a "famous criminal case" that he'd heard about, involving a man who hacked up his parents with an axe. The mother was killed in the act, but, Lynch said, "the father didn't die right away. He was wounded terribly, in the head, but, in the morning, when it was his time normally to wake up, covered in blood he got out of bed--he didn't even notice that his wife was dead right next to him--he just woke up and made his way down to do his habitual program. . . . Fixed breakfast, but he spilled his cereal all over the place. He made coffee, he made a mess of everything, but he knew the habits, he knew the routine. He went to get his paper, like he does every morning, and he came in with the paper and just bled out, right there in the foyer, and that was the end of him."

With increasing usage of clickbaits in Indonesian Online News, newsworthy articles sometimes get buried among clickbaity news. A reliable and lightweight tool is needed to detect such clickbaits on-the-go. Leveraging state-of-the-art natural language processing model BERT, a RESTful API based application is developed. This study offloaded the computing resources needed to train the model on the cloud server, while the client-side application only needs to send a request to the API and the cloud server will handle the rest. This study proposed the design and developed a web-based application to detect clickbait in Indonesian using IndoBERT as a language model. The application usage is discussed and available for public use with a performance of mean ROC-AUC of 89%.

We present CheckSoft, a scalable event-driven software architecture for keeping track of people-object interactions in people-centric applications such as airport checkpoint security areas, automated retail stores, smart libraries, and so on. The architecture works off the video data generated in real time by a network of surveillance cameras. Although there are many different aspects to automating these applications, the most difficult part of the overall problem is keeping track of the interactions between the people and the objects. CheckSoft uses finite-state-machine (FSM) based logic for keeping track of such interactions which allows the system to quickly reject any false detections of the interactions by the video cameras. CheckSoft is easily scalable since the architecture is based on multi-processing in which a separate process is assigned to each human and to each "storage container" for the objects. A storage container may be a shelf on which the objects are displayed or a bin in which the objects are stored, depending on the specific application in which CheckSoft is deployed.

Margaret Mitchell was the co-leader of a group investigating ethics in AI, alongside Timnit Gebru, who said she was fired in December.

Margaret Mitchell, known as Meg, who was one of the leaders of Google's Ethical A.I. team, sent a tweet on Friday afternoon saying merely: "I'm fired.".

Conclusion. In light of these priorities, it is critical that companies managing big data or developing and deploying artificial intelligence (AI) and machine …

Social networks are rich source of data to analyze user habits in all aspects of life. User's behavior is decisive component of a health system in various countries. Promoting good behavior can improve the public health significantly. In this work, we develop a new model for social network analysis by using text analysis approach. We define each user reaction to global pandemic with analyzing his online behavior. Clustering a group of online users with similar habits, help to find how virus spread in different societies. Promoting the healthy life style in the high risk online users of social media have significant effect on public health and reducing the effect of global pandemic. In this work, we introduce a new approach to clustering habits based on user activities on social media in the time of pandemic and recommend a machine learning model to promote health in the online platforms.