Bundle recommender systems recommend sets of items (e.g., pants, shirt, and shoes) to users, but they often suffer from two issues: significant interaction sparsity and a large output space. In this work, we extend multi-round conversational recommendation (MCR) to alleviate these issues. MCR, which uses a conversational paradigm to elicit user interests by asking user preferences on tags (e.g., categories or attributes) and handling user feedback across multiple rounds, is an emerging recommendation setting to acquire user feedback and narrow down the output space, but has not been explored in the context of bundle recommendation. In this work, we propose a novel recommendation task named Bundle MCR. We first propose a new framework to formulate Bundle MCR as Markov Decision Processes (MDPs) with multiple agents, for user modeling, consultation and feedback handling in bundle contexts. Under this framework, we propose a model architecture, called Bundle Bert (Bunt) to (1) recommend items, (2) post questions and (3) manage conversations based on bundle-aware conversation states. Moreover, to train Bunt effectively, we propose a two-stage training strategy. In an offline pre-training stage, Bunt is trained using multiple cloze tasks to mimic bundle interactions in conversations. Then in an online fine-tuning stage, Bunt agents are enhanced by user interactions. Our experiments on multiple offline datasets as well as the human evaluation show the value of extending MCR frameworks to bundle settings and the effectiveness of our Bunt design.

Social media marketing plays a vital role in promoting brand and product values to wide audiences. In order to boost their advertising revenues, global media buying platforms such as Facebook Ads constantly reduce the reach of branded organic posts, pushing brands to spend more on paid media ads. In order to run organic and paid social media marketing efficiently, it is necessary to understand the audience, tailoring the content to fit their interests and online behaviours, which is impossible to do manually at a large scale. At the same time, various personality type categorization schemes such as the Myers-Briggs Personality Type indicator make it possible to reveal the dependencies between personality traits and user content preferences on a wider scale by categorizing audience behaviours in a unified and structured manner. This problem is yet to be studied in depth by the research community, while the level of impact of different personality traits on content recommendation accuracy has not been widely utilised and comprehensively evaluated so far. Specifically, in this work we investigate the impact of human personality traits on the content recommendation model by applying a novel personality-driven multi-view content recommender system called Personality Content Marketing Recommender Engine, or PersiC. Our experimental results and real-world case study demonstrate not just PersiC's ability to perform efficient human personality-driven multi-view content recommendation, but also allow for actionable digital ad strategy recommendations, which when deployed are able to improve digital advertising efficiency by over 420% as compared to the original human-guided approach.

There are many fears out there when it comes to artificial intelligence – some rational, some irrational. By now, most people have integrated some form of artificial intelligence (AI) into their daily lives. For example, if you use Alexa to check the weather or ask Siri to tell you jokes, that's AI. However, despite the widespread use of such technology around the world, people are still concerned about AI. While many fears are valid – such as AI taking over certain jobs, or making humans lazier – others are unfounded.

Have you ever given any thought to how digital assistants like Siri can accurately understand our speech and return highly specific answers? Or have you ever tried to delve into the Alexa schematics just to empathize better with this virtual assistant? I bet not, and that is exactly why you need to get even more familiar with a term called NLP or Natural Language processing. NLP is one of the major AI technologies aimed at making machines capable enough to interpret speech and text-based human language. And if you are still unsure about the utilities involved, NLP forms the backbone of several common tools like chatbots, grammar checkers, translation software modules, spam filters, and even scaled search engines.

Various efficient and robust product recommender systems using machine learning algorithms are helpful in filtering and exploring unseen data by users for better prediction and extrapolation of decisions. These are providing a wider range of solutions to such challenges as imbalanced data set problems, cold-start problems, and long tail problems. This book also looks at fundamental ontological positions that form the foundations of recommender systems and explain why certain recommendations are predicted over others.

Traditional recommendation systems are faced with two long-standing obstacles, namely, data sparsity and cold-start problems, which promote the emergence and development of Cross-Domain Recommendation (CDR). The core idea of CDR is to leverage information collected from other domains to alleviate the two problems in one domain. Over the last decade, many efforts have been engaged for cross-domain recommendation. Recently, with the development of deep learning and neural networks, a large number of methods have emerged. However, there is a limited number of systematic surveys on CDR, especially regarding the latest proposed methods as well as the recommendation scenarios and recommendation tasks they address. In this survey paper, we first proposed a two-level taxonomy of cross-domain recommendation which classifies different recommendation scenarios and recommendation tasks. We then introduce and summarize existing cross-domain recommendation approaches under different recommendation scenarios in a structured manner. We also organize datasets commonly used. We conclude this survey by providing several potential research directions about this field.

In this paper, we propose an end-to-end sentiment-aware conversational agent based on two models: a reply sentiment prediction model, which leverages the context of the dialogue to predict an appropriate sentiment for the agent to express in its reply; and a text generation model, which is conditioned on the predicted sentiment and the context of the dialogue, to produce a reply that is both context and sentiment appropriate. Additionally, we propose to use a sentiment classification model to evaluate the sentiment expressed by the agent during the development of the model. This allows us to evaluate the agent in an automatic way. Both automatic and human evaluation results show that explicitly guiding the text generation model with a pre-defined set of sentences leads to clear improvements, both regarding the expressed sentiment and the quality of the generated text.

Fox News Flash top entertainment and celebrity headlines are here. Check out what clicked this week in entertainment. Kristin Cavallari is going for the online dating route following her split from Jay Cutler. "People have set me up. Mutual friends," she said on the "Not Skinny, But Not Fat" podcast episode on Tuesday.

Amazon took up a lot of oxygen in the deals room last week with Prime Day. However, there are a few gadgets and gizmos that are even cheaper this week than they were then. If you're in the market for a new robot vacuum, keyboard, or even a large TV, we've got some goodies for you. Special offer for Gear readers: Get a one-year subscription to WIRED for $5 ($25 off). This includes unlimited access to WIRED.com and our print magazine (if you'd like). Subscriptions help fund the work we do every day.

A version of this post was originally published in Entrepreneur on February 1, 2022. I've been in the education business for decades as a senior lecturer, trainer and CEO. When people ask me about the biggest challenge that learners face, the first thing that comes to mind is that learners see training as something they "have to do." Now, let's think for a moment about this. How did we get here? Why aren't we talking about "want to do" or "happy to have the opportunity to do?"