UMUAI Journal

Latest Results for User Modeling and User-Adapted Interaction

28 March 2023

• Recommending on graphs: a comprehensive review from a data perspective

  Abstract

  Recent advances in graph-based learning approaches have demonstrated their effectiveness in modelling users’ preferences and items’ characteristics for Recommender Systems (RSs). Most of the data in RSs can be organized into graphs where various objects (e.g. users, items, and attributes) are explicitly or implicitly connected and influence each other via various relations. Such a graph-based organization brings benefits to exploiting potential properties in graph learning (e.g. random walk and network embedding) techniques to enrich the representations of the user and item nodes, which is an essential factor for successful recommendations. In this paper, we provide a comprehensive survey of Graph Learning-based Recommender Systems (GLRSs). Specifically, we start from a data-driven perspective to systematically categorize various graphs in GLRSs and analyse their characteristics. Then, we discuss the state-of-the-art frameworks with a focus on the graph learning module and how they address practical recommendation challenges such as scalability, fairness, diversity, explainability, and so on. Finally, we share some potential research directions in this rapidly growing area.

• Design, development, and evaluation of an interactive personalized social robot to monitor and coach post-stroke rehabilitation exercises

  Abstract

  Socially assistive robots are increasingly being explored to improve the engagement of older adults and people with disability in health and well-being-related exercises. However, even if people have various physical conditions, most prior work on social robot exercise coaching systems has utilized generic, predefined feedback. The deployment of these systems still remains a challenge. In this paper, we present our work of iteratively engaging therapists and post-stroke survivors to design, develop, and evaluate a social robot exercise coaching system for personalized rehabilitation. Through interviews with therapists, we designed how this system interacts with the user and then developed an interactive social robot exercise coaching system. This system integrates a neural network model with a rule-based model to automatically monitor and assess patients’ rehabilitation exercises and can be tuned with individual patient’s data to generate real-time, personalized corrective feedback for improvement. With the dataset of rehabilitation exercises from 15 post-stroke survivors, we demonstrated our system significantly improves its performance to assess patients’ exercises while tuning with held-out patient’s data. In addition, our real-world evaluation study showed that our system can adapt to new participants and achieved 0.81 average performance to assess their exercises, which is comparable to the experts’ agreement level. We further discuss the potential benefits and limitations of our system in practice.

• Clustering of conversational bandits with posterior sampling for user preference learning and elicitation

  Abstract

  Conversational recommender systems elicit user preference via conversational interactions. By introducing conversational key-terms, existing conversational recommenders can effectively reduce the need for extensive exploration required by a traditional interactive recommender. However, there are still limitations of existing conversational recommender approaches eliciting user preference via key-terms. First, the key-term data of the items needs to be carefully labeled, which requires a lot of human efforts. Second, the number of the human labeled key-terms is limited and the granularity of the key-terms is fixed, while the elicited user preference is usually from coarse-grained to fine-grained during the conversations. In this paper, we propose a clustering of conversational bandits algorithm. To avoid the human labeling efforts and automatically learn the key-terms with the proper granularity, we online cluster the items and generate meaningful key-terms for the items during the conversational interactions. Our algorithm is general and can also be used in the user clustering when the feedback from multiple users is available, which further leads to more accurate learning and generations of conversational key-terms. Moreover, to learn the user clustering structure more efficiently in more complex user clustering structure, we further propose a simple yet effective soft user clustering module to perform exploration on user clustering via sampling the posterior user representations. We analyze the regret bound of our learning algorithm. In the empirical evaluations, without using any human labeled key-terms, our algorithm effectively generates meaningful coarse-to-fine grained key-terms and performs as well as or better than the state-of-the-art baseline.

• Eye-tracking-based personality prediction with recommendation interfaces

  Abstract

  Recent research in behavioral decision making demonstrates the advantages of using eye-tracking to surface insights into users’ underlying cognitive processes. Personality, according to psychology definition, accounts for individual differences in our enduring emotional, interpersonal, experiential, attitudinal, and motivational styles. In recommender systems (RS), it has been found that user personality is related to their preferences and behavior, which attracted an increasing attention to the ways to leverage personality into the recommendation process. However, accurate acquisition of a user’s personality is still a challenging issue. In this work, we investigate the possibility of automatically detecting personality from users’ eye movements when interacting with a recommendation interface. Specifically, we report an experiment that harnesses two recommendation interfaces to collect eye-movement data in several product domains and then utilize the data to predict the users’ Big-Five personality traits through various machine learning methods. The results show that AdaBoost combined with Gini index score-based feature selector predicts the traits most accurately, and interface- and domain-specific data allow to improve the accuracy of personality trait predictions. Our findings could inform personality-based RS by improving the process of indirect user personality acquisition.

• A bias detection tree approach for detecting disparities in a recommendation model’s errors

  Abstract

  Many of the current recommendation systems are considered to be blackboxes that are tuned to optimize some global objective function. However, their error distribution may differ dramatically among different combinations of attributes, and such algorithms may lead to propagating hidden data biases. Identifying potential disparities in an algorithm’s functioning is essential for building recommendation systems in a fair and responsible way. In this work, we propose a model-agnostic technique to automatically detect the combinations of user and item attributes correlated with unequal treatment by the recommendation model. We refer to this technique as the Bias Detection Tree. In contrast to the existing works in this field, our method automatically detects disparities related to combinations of attributes without any a priori knowledge about protected attributes, assuming that relevant metadata is available. Our results on five public recommendation datasets show that the proposed technique can identify hidden biases in terms of four kinds of metrics for multiple collaborative filtering models. Moreover, we adapt a minimax model selection technique to control the trade-off between the global and the worst-case optimizations and improve the recommendation model’s performance for biased attributes.