More Like this

1. Recommendations as Treatments

   https://doi.org/10.1609/aimag.v42i3.18141  

   Joachims, Thorsten; London, Ben; Su, Yi; Swaminathan, Adith; Wang, Lequn (January 2022, AI Magazine)

   In recent years, a new line of research has taken an interventional view of recommender systems, where recommendations are viewed as actions that the system takes to have a desired effect. This interventional view has led to the development of counterfactual inference techniques for evaluating and optimizing recommendation policies. This article explains how these techniques enable unbiased offline evaluation and learning despite biased data, and how they can inform considerations of fairness and equity in recommender systems. 

   more » « less
2. 3D-Model-Based Augmented Reality for Enhancing Physical Architectural Models

   https://doi.org/10.52842/conf.ecaade.2022.2.495  

   Tuzun Canadinc, Seda; Yan, Wei (January 2022, Proceedings of the 40th Conference on Education and Research in Computer Aided Architectural Design in Europe (eCAADe 2022))

   Pak, B (Ed.)

   In the presentation of architectural projects, physical models are still commonly used as a powerful and effective representation for building design and construction. On the other hand, Augmented Reality (AR) promises a wide range of possibilities in visualizing and interacting with 3D physical models, enhancing the modeling process. To benefit both, we present a novel medium for architectural representation: a marker-less AR powered physical architectural model that employs dynamic digital features. With AR enhancement, physical capabilities of a model could be extended without sacrificing its tangibility. We developed a framework to investigate the potential uses of 3D-model- based AR registration method and its augmentation on physical architectural models. To explore and demonstrate integration of physical and virtual models in AR, we designed this framework providing physical and virtual model interaction: a user can manipulate the physical model parts or control the visibility and dynamics of the virtual parts in AR. The framework consists of a LEGO model and an AR application on a hand-held device which was developed for this framework. The AR application utilizes a marker-less AR registration method and employs a 3D-model-based AR registration. A LEGO model was proposed as the physical 3D model in this registration process and machine learning training using Vuforia was utilized for the AR application to recognize the LEGO model from any point of view to register the virtual models in AR. The AR application also employs a user interface that allows user interaction with the virtual parts augmented on the physical ones. The working application was tested over its registration, physical and virtual interactions. Overall, the adoption of AR and its combination with physical models, and 3D-model-based AR registration allow for many advantages, which are discussed in the paper. 

   more » « less
3. LuckyFind: Leveraging Surprise to Improve User Satisfaction and Inspire Curiosity in a Recommender System

   https://doi.org/10.1145/3406522.3446017  

   Niu, Xi; Al-Doulat, Ahmad (March 2021, CHIIR '21: Proceedings of the 2021 ACM SIGIR Conference on Human Information Interaction and Retrieval)

   null (Ed.)

   The growing amount of online information today has increased opportunity to discover interesting and useful information. Various recommender systems have been designed to help people discover such information. No matter how accurately the recommender algorithms perform, users’ engagement with recommended results has been complained being less than ideal. In this study, we touched on two human-centered objectives for recommender systems: user satisfaction and curiosity, both of which are believed to play roles in maintaining user engagement and sustain such engagement in the long run. Specifically, we leveraged the concept of surprise and used an existing computational model of surprise to identify relevantly surprising health articles aiming at improving user satisfaction and inspiring their curiosity. We designed a user study to first test the validity of the surprise model in a health news recommender system, called LuckyFind. Then user satisfaction and curiosity were evaluated. We find that the computational surprise model helped identify surprising recommendations at little cost of user satisfaction. Users gave higher ratings on interestingness than usefulness for those surprising recommendations. Curiosity was inspired more for those individuals who have a larger capacity to experience curiosity. Over half of the users have changed their preferences after using LuckyFind, either discovering new areas, reinforcing their existing interests, or stopping following those they did not want anymore. The insights of the research will make researchers and practitioners rethink the objectives of today’s recommender systems as being more human-centered beyond algorithmic accuracy. 

   more » « less
4. Estimating Error and Bias in Offline Evaluation Results

   https://doi.org/10.1145/3343413.3378004  

   Tian, Mucun; Ekstrand, Michael D. (March 2020, Proceedings of the 2020 Conference on Computer-Human Interaction and Information Retrieval)

   Offline evaluation protocols for recommender systems are intended to estimate users' satisfaction with recommendations using static data from prior user interactions. These evaluations allow researchers and production developers to carry out first-pass estimates of the likely performance of a new system and weed out bad ideas before presenting them to users. However, offline evaluations cannot accurately assess novel, relevant recommendations, because the most novel recommendations items that were previously unknown to the user; such items are missing from the historical data, so they cannot be judged as relevant. A breakthrough that reliably produces novel, relevant recommendations would score poorly with current offline evaluation techniques. While the existence of this problem is noted in the literature, its extent is not well-understood. We present a simulation study to estimate the error that such missing data causes in commonly-used evaluation metrics in order to assess its prevalence and impact. We find that missing data in the rating or observation process causes the evaluation protocol to systematically mis-estimate metric values, and in some cases erroneously determine that a popularity-based recommender outperforms even a perfect personalized recommender. Substantial breakthroughs in recommendation quality, therefore, will be difficult to assess with existing offline techniques. 

   more » « less
5. A Deep Reinforcement Learning Based Recommender System for Occupant-Driven Energy Optimization in Commercial Buildings

   https://doi.org/10.1109/JIOT.2020.2974848  

   Wei, Peter; Xia, Stephen; Chen, Runfeng; Qian, Jingyi; Li, Chong; Jiang, Xiaofan (February 2020, IEEE Internet of Things Journal)

   In this work, we present recEnergy, a recommender system for reducing energy consumption in commercial buildings with human-in-the-loop. We formulate the building energy optimization problem as a Markov Decision Process, show how deep reinforcement learning can be used to learn energy saving recommendations, and effectively engage occupants in energy-saving actions. is a recommender system that learns actions with high energy saving potential, actively distribute recommendations to occupants in a commercial building, and utilize feedback from the occupants to learn better energy saving recommendations. Over a four week user study, four different types of energy saving recommendations were trained and learned. improves building energy reduction from a baseline saving (passive-only strategy) of 19% to 26%. 

   more » « less