The truth behind dating app scams has now been exposed in new research revealing the tell-tale signs of a Tinder swindler. Scientists have pinpointed the key personality traits exhibited by romance scammers in a bid to crackdown on cybercrime. Flattery, pets names and personal questions are among the numerous ways that criminals may try to reel you in before asking for help with money. Many fraudulent accounts pose as military servicemen too - emotionally manipulating partners before demanding emergency funds. The Abertay University research comes at a time when romance tricks are surging, with many across the world being scammed out of money.

Deep learning-based recommender systems (DRSs) are increasingly and widely deployed in the industry, which brings significant convenience to people's daily life in different ways. However, recommender systems are also shown to suffer from multiple issues,e.g., the echo chamber and the Matthew effect, of which the notation of "fairness" plays a core role.While many fairness notations and corresponding fairness testing approaches have been developed for traditional deep classification models, they are essentially hardly applicable to DRSs. One major difficulty is that there still lacks a systematic understanding and mapping between the existing fairness notations and the diverse testing requirements for deep recommender systems, not to mention further testing or debugging activities. To address the gap, we propose FairRec, a unified framework that supports fairness testing of DRSs from multiple customized perspectives, e.g., model utility, item diversity, item popularity, etc. We also propose a novel, efficient search-based testing approach to tackle the new challenge, i.e., double-ended discrete particle swarm optimization (DPSO) algorithm, to effectively search for hidden fairness issues in the form of certain disadvantaged groups from a vast number of candidate groups. Given the testing report, by adopting a simple re-ranking mitigation strategy on these identified disadvantaged groups, we show that the fairness of DRSs can be significantly improved. We conducted extensive experiments on multiple industry-level DRSs adopted by leading companies. The results confirm that FairRec is effective and efficient in identifying the deeply hidden fairness issues, e.g., achieving 95% testing accuracy with half to 1/8 time.

Apple is copying Amazon's Alexa with a major change to Siri, a respected leaker claims. According to Apple tipster Mark Gurman, Siri users will soon only need to say'Siri' instead of'Hey Siri' when activating the personal assistant. The change would match Alexa, the virtual assistant from rival Amazon, which requires to users to simply say'Alexa' without the word'hey' first. It could be implemented across multiple Apple operating systems, including iOS for iPhones, as well as iPadOS, watchOS, macOS and more. Gurman has already revealed Apple is planning to unveil its mixed reality headset in less than two months.

Those who've been in the market for a video doorbell to add to their array of smart home devices may want to check out a sale on some options from Google Nest. A sale has dropped the prices of Nest video doorbells by 28 percent. That means the second-gen Nest Doorbell Wired has dropped to $130, which is a record low for that model. Nest's latest wired doorbell works with both Google Assistant- and Amazon Alexa-enabled devices. The latest iteration of the device can continuously record footage for up to 10 days at a time if you have a Nest Aware Plus subscription. A Nest Aware subscription includes 30 days of event video history and a familiar face detection function.

Smart assistants like Amazon's Alexa and Apple's Siri recognize patterns in speech using Natural Language Processing, comprehend meaning and provide a meaningful response. Search engines surface relevant results based on the similar search behaviors. For instance, when you start typing, Google not only predicts what searches may apply to your query, but looks at the whole picture rather than the exact search words. All thanks to NLP as it associates the ambiguous query to a relative entity and provides useful results. These are not the only use cases where Natural Language Processing emerges as a game changer; there are other applications as well.

The Era 300 is the second in Sonos's next-generation line of wifi hi-fis, packing six speakers into one curvaceous box capable of immersing listeners in quality sound. The speaker costs £449 ($449/A$749) and sits above the new £249 Era 100, competing directly with Apple's HomePod and other high-end speakers – premium audio at a premium price. But where the Era 100 is a compact bookshelf speaker, the Era 300 is a different animal. It needs to sit out in the open to allow it to project music outwards from its front, sides and top to fill the room with sound. The cinched-in design allows a series of speakers to fire up and out to the sides from the back half of the Era 300, projecting sound all around the listener for full stereo and new spatial audio surround sound.

CyberGuy shows you how to create and customize events in the calendar app. When the pandemic hit and so many aspects of our lives went digital, older adults had to get accustomed to using more technology like Facetime, Zoom and more. Now, older adults have become a lot more tech-savvy and even have their favorite devices that they enjoy using. Here are five tech obsessions that older adults have adopted over the last few years. Perhaps the most popular devices among older adults are ones like Apple Watches, FitBits and other products that help people keep track of their health.

Recommendation systems are a core feature of social media companies with their uses including recommending organic and promoted contents. Many modern recommendation systems are split into multiple stages - candidate generation and heavy ranking - to balance computational cost against recommendation quality. We focus on the candidate generation phase of a large-scale ads recommendation problem in this paper, and present a machine learning first heterogeneous re-architecture of this stage which we term TwERC. We show that a system that combines a real-time light ranker with sourcing strategies capable of capturing additional information provides validated gains. We present two strategies. The first strategy uses a notion of similarity in the interaction graph, while the second strategy caches previous scores from the ranking stage. The graph based strategy achieves a 4.08% revenue gain and the rankscore based strategy achieves a 1.38% gain. These two strategies have biases that complement both the light ranker and one another. Finally, we describe a set of metrics that we believe are valuable as a means of understanding the complex product trade offs inherent in industrial candidate generation systems.

Recommender systems are increasingly successful in recommending personalized content to users. However, these systems often capitalize on popular content. There is also a continuous evolution of user interests that need to be captured, but there is no direct way to systematically explore users' interests. This also tends to affect the overall quality of the recommendation pipeline as training data is generated from the candidates presented to the user. In this paper, we present a framework for exploration in large-scale recommender systems to address these challenges. It consists of three parts, first the user-creator exploration which focuses on identifying the best creators that users are interested in, second the online exploration framework and third a feed composition mechanism that balances explore and exploit to ensure optimal prevalence of exploratory videos. Our methodology can be easily integrated into an existing large-scale recommender system with minimal modifications. We also analyze the value of exploration by defining relevant metrics around user-creator connections and understanding how this helps the overall recommendation pipeline with strong online gains in creator and ecosystem value. In contrast to the regression on user engagement metrics generally seen while exploring, our method is able to achieve significant improvements of 3.50% in strong creator connections and 0.85% increase in novel creator connections. Moreover, our work has been deployed in production on Facebook Watch, a popular video discovery and sharing platform serving billions of users.

Artificial intelligence: Danish startup Be My Eyes is developing an app based on the Open AI model that acts as a virtual assistant for people with blindness. Be My Eyes has a mission: to help blind people explore the world around them using smartphone technology. Created in 2015, the app developed by the Danish startup of the same name connects blind users with a network of sighted volunteers who, through a video call, 'lend' their eyes to observe and describe what they see through the device's camera. In the not-too-distant future, however, volunteers may no longer be needed. Be My Eyes is developing a beta version of the application that relies on a virtual assistant based on GPT-4, the latest version of Open AI's artificial intelligence model.