We propose a novel technique to predict a user's movie genre preference from her psycholinguistic attributes obtained from user social media interactions. In particular, we build machine learning based classification models that take user tweets as input to derive her psychological attributes: personality and value scores, and gives her movie genre preference as output. We train these models using user tweets in Twitter, and her reviews and ratings of movies of different genres in Internet movie database (IMDb). We exploit a key concept of psychology, i.e., an individual's personality and values may influence her choice in performing different actions in real life. We have investigated how personality and values independently and collectively influence a user preference on different movie genres. Our proposed model can be used for recommending movies to social media users.

Users of online dating sites compete for attention from potential matches. Member profiles provide an opportunity for candidates to present information about themselves that their counterparts use to assess compatibility and desirability. In this paper, we explore how text-based similarities among users of a dating site impact their success in attracting attention. The principle of homophily predicts that to be successful, a user should be perceived as similar to the person they would prefer to date. Conversely, theories of distinctiveness suggest that standing out from the crowd should be beneficial. Using profiles, we explore how the text similarity between a user, the opposite-sex member they are targeting, and their same-sex competitors impacts the likelihood that a sender of a message receives a response conditional on initiating contact. We find that the probability of receiving a response is maximized when the user has high text similarity to the person they message, but low text similarity to the competitors that are also seeking the same individual's attention. This suggests a balance between homophily and distinctiveness theory.

Product reviews provide insights in to real user experiences which can benefit others when making their purchasing decisions. Text-mining and NLP may be used to extract features and content that could influence a new user. Additionally, recommender systems and filtering interfaces rely on manufacturer reported data in order to support user preferences. In many instances this data may be absent or inaccurate. In this paper we focus on age related features mentioned in user reviews of baby and child related products in order to recommend the appropriate age range of a product. We demonstrate that manufacturer related information is frequently absent and when manufacturer specifications are available, we find they may not reflect real user experiences which could assist a buyer in their decision making process. As a result, we present a simple user interface to allow users assess the age appropriateness of the product.

Dating and romantic relationships not only play a huge role in our personal lives but also collectively influence and shape society. Today, many romantic partnerships originate from the Internet, signifying the importance of technology and the web in modern dating. In this paper, we present a text-based computational approach for estimating the relationship compatibility of two users on social media. Unlike many previous works that propose reciprocal recommender systems for online dating websites, we devise a distant supervision heuristic to obtain real world couples from social platforms such as Twitter. Our approach, the CoupleNet is an end-to-end deep learning basedestimator that analyzes the social profiles of two users and subsequently performs a similarity match between the users. Intuitively, our approach performs both user profiling and match-making within a unified end-to-end framework. CoupleNet utilizes hierarchical recurrent neural models for learning representations of user profiles and subsequently coupled attention mechanisms to fuse information aggregated from two users.To the best of our knowledge, our approach is the first data-driven deep learning approach for our novel relationship recommendation problem.

Welcome to experience a mind-blowing "Artificial Intelligence Expert Course" in 2022. Artificial Intelligence Expert Course: Platinum Edition - The course has now launched. Artificial Intelligence (AI) seems to be a unique technology of making a machine, a robot fully autonomous. AI is an analysis of how the machine is thinking, studying, determining, and functioning when it is trying to solve problems. These kinds of problems are present in all fields, the most emerging ones, and even beyond.

Players of digital games face numerous choices as to what kind of games to play and what kind of game content or in-game activities to opt for. Among these, game content plays an important role in keeping players engaged so as to increase revenues for the gaming industry. However, while nowadays a lot of game content is generated using procedural content generation, automatically determining the kind of content that suits players' skills still poses challenges to game developers. Addressing this challenge, we present matrix- and tensor factorization based game content recommender systems for recommending quests in a single player role-playing game. We discuss the theory behind latent factor models for recommender systems and derive an algorithm for tensor factorizations to decompose collections of bipartite matrices. Extensive online bucket type tests reveal that our novel recommender system retained more players and recommended more engaging quests than handcrafted content-based and previous collaborative filtering approaches.

Tinder says it will no longer charge older users more to use Tinder, following a new report questioning the dating app's practice of charging older users "substantially more." The report, from Mozilla and Consumers International, detailed just how much Tinder pricing can vary based on users' age. The report relied on "mystery shoppers" in six countries -- the United States, the Netherlands, New Zealand, Korea, India and Brazil -- who signed up for Tinder and reported back how much the app charged for the subscription. According to the report, Tinder users between the ages of 30 and 49 were charged an average of 65.3 percent more than their younger counterparts in every country except Brazil. Tinder's age-based pricing for Tinder, which gives users access to premium features like unlimited likes, has long been a source of controversy for the dating app.

Kiosks are a popular self-service option in many fast-food restaurants, they save time for the visitors and save labor for the fast-food chains. In this paper, we propose an effective design of a kiosk shopping cart recommender system that combines a language model as a vectorizer and a neural network-based classifier. The model performs better than other models in offline tests and exhibits performance comparable to the best models in A/B/C tests.

A knowledge graph (KG) consists of a set of interconnected typed entities and their attributes. Recently, KGs are popularly used as the auxiliary information to enable more accurate, explainable, and diverse user preference recommendations. Specifically, existing KG-based recommendation methods target modeling high-order relations/dependencies from long connectivity user-item interactions hidden in KG. However, most of them ignore the cold-start problems (i.e., user cold-start and item cold-start) of recommendation analytics, which restricts their performance in scenarios when involving new users or new items. Inspired by the success of meta-learning on scarce training samples, we propose a novel meta-learning based framework called MetaKG, which encompasses a collaborative-aware meta learner and a knowledge-aware meta learner, to capture meta users' preference and entities' knowledge for cold-start recommendations. The collaborative-aware meta learner aims to locally aggregate user preferences for each user preference learning task. In contrast, the knowledge-aware meta learner is to globally generalize knowledge representation across different user preference learning tasks. Guided by two meta learners, MetaKG can effectively capture the high-order collaborative relations and semantic representations, which could be easily adapted to cold-start scenarios. Besides, we devise a novel adaptive task scheduler which can adaptively select the informative tasks for meta learning in order to prevent the model from being corrupted by noisy tasks. Extensive experiments on various cold-start scenarios using three real data sets demonstrate that our presented MetaKG outperforms all the existing state-of-the-art competitors in terms of effectiveness, efficiency, and scalability.

In my book, Tech Trends in Practice, I talk about a lot of technology trends that are already moving out of the R&D departments and into everyday life, but the following five I think will have the most profound impacts on our society and the human race as a whole. Artificial intelligence, or AI, and machine learning refer to the ability of machines to learn and act intelligently, meaning they can make decisions, carry out tasks, and even predict future outcomes based on what they learn from data. AI and machine learning already play a bigger role in everyday life than you might imagine. Alexa, Siri, Amazon's product recommendations, Netflix's and Spotify's personalized recommendations, every Google search you make, security checks for fraudulent credit card purchases, dating apps, fitness trackers... All are driven by AI.