Points of interest (POI) recommendation has been drawn much attention recently due to the increasing popularity of location-based networks, e.g., Foursquare and Yelp. Among the existing approaches to POI recommendation, Matrix Factorization (MF) based techniques have proven to be effective. However, existing MF approaches suffer from two major problems: (1) Expensive computations and storages due to the centralized model training mechanism: the centralized learners have to maintain the whole user-item rating matrix, and potentially huge low rank matrices. (2) Privacy issues: the users' preferences are at risk of leaking to malicious attackers via the centralized learner. To solve these, we present a Decentralized MF (DMF) framework for POI recommendation. Specifically, instead of maintaining all the low rank matrices and sensitive rating data for training, we propose a random walk based decentralized training technique to train MF models on each user's end, e.g., cell phone and Pad. By doing so, the ratings of each user are still kept on one's own hand, and moreover, decentralized learning can be taken as distributed learning with multi-learners (users), and thus alleviates the computation and storage issue. Experimental results on two real-world datasets demonstrate that, comparing with the classic and state-of-the-art latent factor models, DMF significantly improvements the recommendation performance in terms of precision and recall.

The popularity of live streaming has led to the explosive growth in new video contents and social communities on emerging platforms such as Facebook Live and Twitch. Viewers on these platforms are able to follow multiple streams of live events simultaneously, while engaging discussions with friends. However, existing approaches for selecting live streaming channels still focus on satisfying individual preferences of users, without considering the need to accommodate real-time social interactions among viewers and to diversify the content of streams. In this paper, therefore, we formulate a new Social-aware Diverse and Preferred Live Streaming Channel Query (SDSQ) that jointly selects a set of diverse and preferred live streaming channels and a group of socially tight viewers. We prove that SDSQ is NP-hard and inapproximable within any factor, and design SDSSel, a 2-approximation algorithm with a guaranteed error bound. We perform a user study on Twitch with 432 participants to validate the need of SDSQ and the usefulness of SDSSel. We also conduct large-scale experiments on real datasets to demonstrate the superiority of the proposed algorithm over several baselines in terms of solution quality and efficiency.

The Google Home ($99 at Walmart) is a worthy alternative to the Amazon Echo; it can answer questions you'd usually type into Google, set a timer for the kitchen, serve as a centralized smart home controller, and of course, play music. It also works with lots of great smart devices, but that's not the only trick up the Home's sleeve. Did you know you can program it to do nearly anything you can think of? With the help of free services like IFTTT (If This Then That), the smart speaker can perform common tasks like sending messages, posting to social media, or even adding ingredients to a shared shopping list in a cloud service like Google Drive. IFTTT is a free service that lets you automate tasks between Internet-connected devices and cloud or social media accounts. All the recipes are for both Android and iOS unless otherwise specified.

In all their infinite wisdom, the Romans decided to celebrate Valentine's Day in the dead of winter. Even if that wasn't their original intention, the holiday is a good excuse to stave off the cold, gray doldrums with a new gaming computer. Or maybe a smart home assistant to help you check the forecast? With the help of our friends at TechBargains, we've pulled together a few deals to indulge yourself or someone you love. Dell is currently still offering 10% with the code TENOFF.

Microsoft updated its Cortana app and it now features native iPad support. The interface makes use of the bigger iPad screen, but otherwise it's largely similar to the iPhone version. The update, spotted by MacRumors, also notes that the app now opens 20 percent faster. Enjoy an exclusive layout and interface for your iPad," says the update release. "Cortana now launches 20 percent faster!

The 2018 Winter Olympics games, taking place in PyeongChang, South Korea, kicks off in February. A record amount of condoms -- nearly 40 per person -- were distributed to athletes participating in the 2018 Winter Olympics this month, a handout officials say will allow tense competitors to let out steam during the high-pressure games in South Korea. But the move is raising questions about allowing the Olympic Village to turn into a freewheeling sex romp at a time when the #MeToo movement has taken the world by storm and sensitivity about sexual misconduct is at an all-time high. "The Olympics is a very sexually charged time," Julie Spira, an online and mobile dating expert, told CBS News. "Young athletes and attendees have been using dating apps heavily in prior Olympics, but now the popularity of an app like Tinder continues to grow and grow." Some 1.2 million people, including athletes, were expected to gather in PyeongChang, South Korea for the 2018 Winter Olympics.

"Siri, where's the best place to grab dinner nearby?" "What's the weather today, Siri?" "Hey, Siri. Who won the game last night?" It has become second nature for me to ask my iPhone questions and expect a chipper, informative response. From grabbing a bite to booking a flight, Siri has become an ...

Magazines are constantly looking at ways to bridge the gap between their paper-based and digital audiences, especially with an ecommerce slant, which has demonstrated its potential in a number of innovative areas, including augmented reality. Now, Condé Nast fashion bibles Vogue and GQ are experimenting with content on the exclusive Amazon Echo Look, which is basically Alexa with a camera (and is only available to purchase by invitation at this stage). From February 19, readers can take a selfie with the Look, send it to the app and get a host of celebrity and fashion content in return, some of which they can buy through the app, with Condé Nast getting a cut of the sale. The content will be updated once a week by Condé Nast and Amazon employees, and while it's not clear how many customers the glossy titles hope to reach through the project, Vogue's digital director Anna-Lisa Yabsley revealed that the experiment was prompted largely because more and more readers are asking for help in choosing products. Plus, Condé Nast has previously identified ecommerce as a key growth area for 2018.

The rise of artificial intelligence (AI), as with a lot of recent technologies, seems to be exponential. Recently, the news was of the NHS looking to introduce AI to assist in more rapid diagnosis of heart conditions. So perhaps the time is right to start thinking how AI could be utilised within UK housing organisations? At the beginning of 2017 I began an open conversation with the housing sector around emerging technologies, including chatbots, sensor-based Internet of Things devices and headless user interfaces (UIs) like Amazon's Alexa or Google at Home. Since then I've been visiting and meeting with a diverse range of organisations who have all started to explore the potential benefits that these sorts of technologies could offer them.

"Alexa, can you order me a pizza from Dominos?" "Alexa, do you know Siri?" These are just some of the questions you might enjoy asking Alexa on your smartphone now that Amazon has brought the voice control feature to the Android version of the app. But before you start geeking out, here's the rundown of the most recent update: Until recently, the Amazon Alexa app could only be used to control settings for the Echo, Dot, and other supported devices. Considering what the AI-powered assistant is actually capable of, this is nothing to get excited about. But now all that has changed as Amazon brings voice control to the Android version of the app, making Alexa a full-fledge digital assistant on Android handsets.