Recommender systems are becoming increasingly central as mediators of information with the potential to profoundly influence societal opinion. While approaches are being developed to ensure these systems are designed in a responsible way, adolescents in particular, represent a potentially vulnerable user group requiring explicit consideration. This is especially important given the nature of their access and use of recommender systems but also their role as providers of content. This paper proposes core principles for the ethical design of recommender systems and evaluates whether current approaches to ensuring adherence to these principles are sufficiently inclusive of the particular needs and potential vulnerabilities of adolescent users.

Since its inception in 2016, the Alexa Prize program has enabled hundreds of university students to explore and compete to develop conversational agents through the SocialBot Grand Challenge. The goal of the challenge is to build agents capable of conversing coherently and engagingly with humans on popular topics for 20 minutes, while achieving an average rating of at least 4.0/5.0. However, as conversational agents attempt to assist users with increasingly complex tasks, new conversational AI techniques and evaluation platforms are needed. The Alexa Prize TaskBot challenge, established in 2021, builds on the success of the SocialBot challenge by introducing the requirements of interactively assisting humans with real-world Cooking and Do-It-Yourself tasks, while making use of both voice and visual modalities. This challenge requires the TaskBots to identify and understand the user's need, identify and integrate task and domain knowledge into the interaction, and develop new ways of engaging the user without distracting them from the task at hand, among other challenges. This paper provides an overview of the TaskBot challenge, describes the infrastructure support provided to the teams with the CoBot Toolkit, and summarizes the approaches the participating teams took to overcome the research challenges.

Short video has witnessed rapid growth in the past few years in e-commerce platforms like Taobao. To ensure the freshness of the content, platforms need to release a large number of new videos every day, making conventional click-through rate (CTR) prediction methods suffer from the item cold-start problem. In this paper, we propose GIFT, an efficient Graph-guIded Feature Transfer system, to fully take advantages of the rich information of warmed-up videos to compensate for the cold-start ones. Specifically, we establish a heterogeneous graph that contains physical and semantic linkages to guide the feature transfer process from warmed-up video to cold-start videos. The physical linkages represent explicit relationships, while the semantic linkages measure the proximity of multi-modal representations of two videos. We elaborately design the feature transfer function to make aware of different types of transferred features (e.g., id representations and historical statistics) from different metapaths on the graph. We conduct extensive experiments on a large real-world dataset, and the results show that our GIFT system outperforms SOTA methods significantly and brings a 6.82% lift on CTR in the homepage of Taobao App.

New technologies can create new opportunities to engage with customers — but is it always worth it for companies to build out a presence on these platforms? When it comes to launching a voice assistant on Amazon Echo or Google Nest, recent research suggests the investment won’t necessarily pay off. The authors analyzed stock price data for nearly 100 companies before and after they released voice assistant features, and they found that while some firms experienced a positive bump in valuation after launching their voice assistant, others experienced no increase or even a notable decrease in market value. Specifically, firms that launched informational features experienced an average 1% increase in valuation, firms that launched object-control features experienced no change in stock price, and firms that launched transactional features actually experienced an average 1.2% decrease in market value. As such, the authors argue that companies should think carefully before investing in a voice assistant to ensure that the value added will be worth the substantial development costs.

Amazon Alexa is a virtual assistant technology largely based on a Polish speech synthesiser named Ivona, bought by Amazon in 2013. It is integrated into Amazon Echo and Echo Dot smart speakers as well as Echo Show and Echo Spot devices. Alexa's technology allows users to access a wide variety of functionality and information, such as playing music, setting alarms, triggering reminders, streaming podcasts, making to-do lists, playing audiobooks, and updating traffic, weather, sports, and other real-time information, such as local news. Alexa can perform these functions out-of-the-box, usually triggered by a "wake-word" to alert an Alexa-enabled device of a vocal command. Alexa listens for the command and performs the appropriate function, or task, to answer a question or command.

"64% of companies worldwide have experienced at least one form of a cyber-attack." "There were 22 billion breached records in 2021." "Every 39 seconds, there is a new attack somewhere on the web." Today, one of the biggest threats to organizations and businesses is cyber-attacks. Unfortunately, our go-to defense is firewalls.

Reviews contain rich information about product characteristics and user interests and thus are commonly used to boost recommender system performance. Specifically, previous work show that jointly learning to perform review generation improves rating prediction performance. Meanwhile, these model-produced reviews serve as recommendation explanations, providing the user with insights on predicted ratings. However, while existing models could generate fluent, human-like reviews, it is unclear to what degree the reviews fully uncover the rationale behind the jointly predicted rating. In this work, we perform a series of evaluations that probes state-of-the-art models and their review generation component. We show that the generated explanations are brittle and need further evaluation before being taken as literal rationales for the estimated ratings.

To build recommender systems that not only consider user-item interactions represented as ordinal variables, but also exploit the social network describing the relationships between the users, we develop a hierarchical Bayesian model termed ordinal graph factor analysis (OGFA), which jointly models user-item and user-user interactions. OGFA not only achieves good recommendation performance, but also extracts interpretable latent factors corresponding to representative user preferences. We further extend OGFA to ordinal graph gamma belief network, which is a multi-stochastic-layer deep probabilistic model that captures the user preferences and social communities at multiple semantic levels. For efficient inference, we develop a parallel hybrid Gibbs-EM algorithm, which exploits the sparsity of the graphs and is scalable to large datasets. Our experimental results show that the proposed models not only outperform recent baselines on recommendation datasets with explicit or implicit feedback, but also provide interpretable latent representations.

Long-standing data sparsity and cold-start constitute thorny and perplexing problems for the recommendation systems. Cross-domain recommendation as a domain adaptation framework has been utilized to efficiently address these challenging issues, by exploiting information from multiple domains. In this study, an item-level relevance cross-domain recommendation task is explored, where two related domains, that is, the source and the target domain contain common items without sharing sensitive information regarding the users' behavior, and thus avoiding the leak of user privacy. In light of this scenario, two novel coupled autoencoder-based deep learning methods are proposed for cross-domain recommendation. The first method aims to simultaneously learn a pair of autoencoders in order to reveal the intrinsic representations of the items in the source and target domains, along with a coupled mapping function to model the non-linear relationships between these representations, thus transferring beneficial information from the source to the target domain. The second method is derived based on a new joint regularized optimization problem, which employs two autoencoders to generate in a deep and non-linear manner the user and item-latent factors, while at the same time a data-driven function is learnt to map the item-latent factors across domains. Extensive numerical experiments on two publicly available benchmark datasets are conducted illustrating the superior performance of our proposed methods compared to several state-of-the-art cross-domain recommendation frameworks.

In this article, we are going to see what is a recommendation system, the use cases of recommendation systems, why we use recommendation systems, and what are the types of recommendation systems. So without wasting any time let's start this article with a short intro about recommendation systems in Machine Learning. As we know that Netflix uses a recommendation system to recommend movies and web series on the behalf of user interest and Youtube also uses a recommendation system to recommend videos so that users can spend more time on their platforms. The use cases of recommendation systems have been increasing consistently and there could be no better time than now to dive deeper into this excellent machine learning technology so that we can also utilize this technique in the right direction. Recommendation systems are like filtering systems that attempt to predict the rating or preference a user might give an item.