Many software systems, such as online social networks enable users to share information about themselves. While the action of sharing is simple, it requires an elaborate thought process on privacy: what to share, with whom to share, and for what purposes. Thinking about these for each piece of content to be shared is tedious. Recent approaches to tackle this problem build personal assistants that can help users by learning what is private over time and recommending privacy labels such as private or public to individual content that a user considers sharing. However, privacy is inherently ambiguous and highly personal. Existing approaches to recommend privacy decisions do not address these aspects of privacy sufficiently. Ideally, a personal assistant should be able to adjust its recommendation based on a given user, considering that user's privacy understanding. Moreover, the personal assistant should be able to assess when its recommendation would be uncertain and let the user make the decision on her own. Accordingly, this paper proposes a personal assistant that uses evidential deep learning to classify content based on its privacy label. An important characteristic of the personal assistant is that it can model its uncertainty in its decisions explicitly, determine that it does not know the answer, and delegate from making a recommendation when its uncertainty is high. By factoring in the user's own understanding of privacy, such as risk factors or own labels, the personal assistant can personalize its recommendations per user. We evaluate our proposed personal assistant using a well-known data set. Our results show that our personal assistant can accurately identify uncertain cases, personalize them to its user's needs, and thus helps users preserve their privacy well.

Advanced music recommendation systems are being introduced along with the development of machine learning. However, it is essential to design a music recommendation system that can increase user satisfaction by understanding users' music tastes, not by the complexity of models. Although several studies related to music recommendation systems exploiting negative preferences have shown performance improvements, there was a lack of explanation on how they led to better recommendations. In this work, we analyze the role of negative preference in users' music tastes by comparing music recommendation models with contrastive learning exploiting preference (CLEP) but with three different training strategies - exploiting preferences of both positive and negative (CLEP-PN), positive only (CLEP-P), and negative only (CLEP-N). We evaluate the effectiveness of the negative preference by validating each system with a small amount of personalized data obtained via survey and further illuminate the possibility of exploiting negative preference in music recommendations. Our experimental results show that CLEP-N outperforms the other two in accuracy and false positive rate. Furthermore, the proposed training strategies produced a consistent tendency regardless of different types of front-end musical feature extractors, proving the stability of the proposed method.

Graph Neural Networks (GNNs) have been shown as promising solutions for collaborative filtering (CF) with the modeling of user-item interaction graphs. The key idea of existing GNN-based recommender systems is to recursively perform the message passing along the user-item interaction edge for refining the encoded embeddings. Despite their effectiveness, however, most of the current recommendation models rely on sufficient and high-quality training data, such that the learned representations can well capture accurate user preference. User behavior data in many practical recommendation scenarios is often noisy and exhibits skewed distribution, which may result in suboptimal representation performance in GNN-based models. In this paper, we propose SHT, a novel Self-Supervised Hypergraph Transformer framework (SHT) which augments user representations by exploring the global collaborative relationships in an explicit way. Specifically, we first empower the graph neural CF paradigm to maintain global collaborative effects among users and items with a hypergraph transformer network. With the distilled global context, a cross-view generative self-supervised learning component is proposed for data augmentation over the user-item interaction graph, so as to enhance the robustness of recommender systems. Extensive experiments demonstrate that SHT can significantly improve the performance over various state-of-the-art baselines. Further ablation studies show the superior representation ability of our SHT recommendation framework in alleviating the data sparsity and noise issues. The source code and evaluation datasets are available at: https://github.com/akaxlh/SHT.

When Amazon first introduced Alexa and the Echo speaker years ago, the idea of talking to a digital assistant wasn't totally novel. Both the iPhone and Android phones had semi-intelligent voice controls -- but with the Echo, Amazon took its first step toward making something like Alexa a constant presence in your home. Since then, Apple and Google have followed suit, and now there's a huge variety of smart speakers available at various price points. As the market exploded, the downsides of having a device that's always listening for a wake word have become increasingly apparent. They can get activated unintentionally, sending private recordings back to monolithic companies to analyze. And even at the best of times, giving more personal information to Amazon, Apple and Google can be a questionable decision.

The march of time is inevitable. Whether the horse and buggy are replaced by the automobile or the slide rule is replaced by the calculator, everything eventually becomes obsolete. And if you listen to the rumors, this time around, it's search engine optimization. Rest in peace, SEO: 1997-2022. SEO is still alive and kicking. It's just as relevant today as it has ever been.

A combinatorial recommender (CR) system feeds a list of items to a user at a time in the result page, in which the user behavior is affected by both contextual information and items. The CR is formulated as a combinatorial optimization problem with the objective of maximizing the recommendation reward of the whole list. Despite its importance, it is still a challenge to build a practical CR system, due to the efficiency, dynamics, personalization requirement in online environment. In particular, we tear the problem into two sub-problems, list generation and list evaluation. Novel and practical model architectures are designed for these sub-problems aiming at jointly optimizing effectiveness and efficiency. In order to adapt to online case, a bootstrap algorithm forming an actor-critic reinforcement framework is given to explore better recommendation mode in long-term user interaction. Offline and online experiment results demonstrate the efficacy of proposed JDRec framework. JDRec has been applied in online JD recommendation, improving click through rate by 2.6% and synthetical value for the platform by 5.03%. We will publish the large-scale dataset used in this study to contribute to the research community.

Recommendation systems will always stay relevant -- users want to see personalized content, the best of the catalog (in the case of our iFunny app -- trending memes and jokes). Our team is testing dozens of hypotheses on how a smart feed can improve user experience. This article will tell you how we implemented the second-ranking level of the model above the collaborative one: what difficulties we encountered, and how they affected the metrics. Usually, a matrix decomposition, such as implicit.ALS, is used to help improve the feed. In this method, for each user and each object, we get the embeddings, and the content, whose embeddings are the closest (in cosine measure) to the user's embeddings, ends up in the top recommendations.

Amazon's smallest smart display is back on sale at one of the best prices we've seen. If you missed the chance to pick up the Echo Show 5 on Prime Day, you can get it now for only $40. That's 53 percent off its normal price and only $5 more than it was during Amazon's two-day shopping event. You're getting the most up-to-date model here, which is the 2021 version with a 2MP camera for video calls. The kids version of the gadget has also been discounted to $50, which is nearly half off its regular rate.

Indeed, commercial task-oriented dialog systems in the form of smart devices like Amazon's Alexa are used by millions of people every day. Within the academic research community, however, task-oriented dialog system models are often benchmarked on relatively few evaluation datasets. This is in spite of the fact that the past few years have seen a substantial growth in the number of available datasets for building and evaluating intent classification and slot-filling models for task-oriented dialog systems. Thus, the goal of this survey is to catalog these intent classification and slot-filling datasets to help facilitate their use in building and evaluating dialog systems and beyond. Other surveys have discussed dialog datasets in depth (Serban et al. 2018), but exclude almost all intent classification and slot-filling datasets, and model-focused surveys on dialog systems mostly focus on models and pay much less attention to datasets.

Late last year, Valerie Peter, a twenty-three-year-old student in Manchester, England, realized that she had an online-shopping problem. It was more about what she was buying than how much. A fashion trend of fuzzy leg warmers had infiltrated Peter's social-media feeds--her TikTok For You tab, her Instagram Explore page, her Pinterest recommendations. She'd always considered leg warmers "ugly, hideous, ridiculous," she told me recently, and yet soon enough she "somehow magically ended up with a pair of them," which she bought online at the push of a button, on an almost subconscious whim. "They're in the back of my closet," she said.)