AI plays a huge role in how Spotify delivers personalized playlists to users, so it's somewhat fitting that the company's new partnership with Microsoft is focused on messages about how AI can impact all aspects of life -- including education, healthcare and philanthropy. Those messages are going to be showing up in the Discover Weekly playlist for free users, the first time that Spotify has lets brands have full customization and control over advertising in that feed. We talked with Spotify's Danielle Lee, VP and Global Head of Partner Solutions, about how the company uses AI to power its personalized content, how it can apply that in the future to things like video and podcasts and how the company can offer branding options for Discover Weekly while keeping things relevant to listeners. Follow all the latest news from CES 2019 here!

Dataset pruning is the process of removing sub-optimal tuples from a dataset to improve the learning of a machine learning model. In this paper, we compared the performance of different algorithms, first on an unpruned dataset and then on an iteratively pruned dataset. The goal was to understand whether an algorithm (say A) on an unpruned dataset performs better than another algorithm (say B), will algorithm B perform better on the pruned data or vice-versa. The dataset chosen for our analysis is a subset of the largest movie ratings database publicly available on the internet, IMDb [1]. The learning objective of the model was to predict the categorical rating of a movie among 5 bins: poor, average, good, very good, excellent. The results indicated that an algorithm that performed better on an unpruned dataset also performed better on a pruned dataset.

Humor is an essential human trait. Efforts to understand humor have called out links between humor and the foundations of cognition, as well as the importance of humor in social engagement. As such, it is a promising and important subject of study, with relevance for artificial intelligence and human-computer interaction. Previous computational work on humor has mostly operated at a coarse level of granularity, e.g., predicting whether an entire sentence, paragraph, document, etc., is humorous. As a step toward deep understanding of humor, we seek fine-grained models of attributes that make a given text humorous. Starting from the observation that satirical news headlines tend to resemble serious news headlines, we build and analyze a corpus of satirical headlines paired with nearly identical but serious headlines. The corpus is constructed via Unfun.me, an online game that incentivizes players to make minimal edits to satirical headlines with the goal of making other players believe the results are serious headlines. The edit operations used to successfully remove humor pinpoint the words and concepts that play a key role in making the original, satirical headline funny. Our analysis reveals that the humor tends to reside toward the end of headlines, and primarily in noun phrases, and that most satirical headlines follow a certain logical pattern, which we term false analogy. Overall, this paper deepens our understanding of the syntactic and semantic structure of satirical news headlines and provides insights for building humor-producing systems.

Natural human-computer interaction and audio-visual human behaviour sensing systems, which would achieve robust performance in-the-wild are more needed than ever as digital devices are becoming indispensable part of our life more and more. Accurately annotated real-world data are the crux in devising such systems. However, existing databases usually consider controlled settings, low demographic variability, and a single task. In this paper, we introduce the SEWA database of more than 2000 minutes of audio-visual data of 398 people coming from six cultures, 50% female, and uniformly spanning the age range of 18 to 65 years old. Subjects were recorded in two different contexts: while watching adverts and while discussing adverts in a video chat. The database includes rich annotations of the recordings in terms of facial landmarks, facial action units (FAU), various vocalisations, mirroring, and continuously valued valence, arousal, liking, agreement, and prototypic examples of (dis)liking. This database aims to be an extremely valuable resource for researchers in affective computing and automatic human sensing and is expected to push forward the research in human behaviour analysis, including cultural studies. Along with the database, we provide extensive baseline experiments for automatic FAU detection and automatic valence, arousal and (dis)liking intensity estimation.

That's most of what I remember from Sony's press event at CES last night. TVs, headphones with Alexa and a wireless turntable, its 45-minute media briefing rarely touched on any new products. When Sony CEO Kenichiro Yoshida stepped on stage, he laid out that he planned to "shift our gears" and showcase the company's involvement in more creative endeavors. That meant fewer product flourishes and plenty of moments where Sony simply sang its own praises. At a show famed for hardware announcements, the company sidelined its own news.

The rise of the machines is coming.

A link has been posted to your Facebook feed. LAS VEGAS – You enter the backseat of a tricked out BMW SUV X5, imagine it's a self-driving car of the future and look to be entertained. A movie screen pops up and offers you 270 degrees worth of choices – how about a visual Batman comic book, a movie trailer or a complete film? Sit in this BMW and listen to the sounds of multiple speakers pumping out stereo, and hi-def resolution on the screen, and let's face it – how could you argue that this wasn't really cool? The Batman Immersive Experience, from computer chip maker Intel and Batman owner Warner Media, is just one of five cool things we saw on the second day of CES previews. The trade floor of the CES officially opens to the public Tuesday.

A new episode of Charlie Brooker's Black Mirror debuted on Netflix just before the new year. Unlike most previous examples, Bandersnatch is not a cautionary tale of how current technologies might evolve to further ruin our hearts, minds and communities. It is, rather, a period piece set in early-1980s Britain, when young video-game programmers were becoming millionaires selling their games in WH Smith. Unlike all previous Black Mirror episodes, Bandersnatch is a nonlinear film that allows the viewer to steer the plot using simple A/B choices at key moments in the drama. Like the Choose Your Own Adventure books of the period, these choices range from the mundane ("which cereal would you like for breakfast?") to the life-imperilling, and each path winds to one of a number of possible endings.

LG has unveiled the world's first consumer-ready rollable television at the CES 2019 trade show in Las Vegas. The South Korean electronics giant said the "revolutionary form factor" of its Signature OLED TV R will define the next generation of television. A concept for the roll-up screen was first demonstrated at the world's biggest technology showcase in 2016 but it has taken three years to develop a commercially viable version of the television. The Signature OLED forms part of a new trend that has seen manufacturers attempt to diminish the presence of large televisions in the living room when they are not in use. Samsung's answer is Ambient Mode, a setting that blends the screen with the wall behind it when it is on standby.