With the incredible growth of the scale and complexity of datasets, creating proper visualizations for users becomes more and more challenging in large datasets. Though several visualization ...recommendation systems have been proposed, so far, the lack of practical engineering inputs is still a major concern regarding the usage of visualization recommendations in the industry. In this paper, we proposed AVA, an open-sourced web-based framework for Automated Visual Analytics. AVA contains both empiric-driven and insight-driven visualization recommendation methods to meet the demands of creating aesthetic visualizations and understanding expressible insights respectively. The code is available at https://github.com/antvis/AVA.
Clinical Practice Guideline on Acupuncture and Moxibustion: Migraine (WFAS 007.9-2023) is a clinical practice guideline officially released by the World Federation of Acupuncture-Moxibustion ...Societies (WFAS) on October 9, 2023, and is the first international guideline on the treatment of migraine with acupuncture. This international standard was developed under the guidance of rigorous evidence-based methodology, and it contains guideline purpose, scope, applicable population, applicable settings, overview of acupuncture for migraine, guideline development process and recommendations. For promoting the understanding and application of this guideline, this article summarizes a total of 18 recommendations in order to assist clinical decisions for migraine with acupuncture.
Curriculum Learning (CL) is an effective technique to train machine learning models where the training samples are supplied to the model in an easy-to-hard manner. Similar to human learning, the ...model can benefit if the data is given in a relevant order. Based on this notion, we propose to apply the concept of CL to the task of session-based recommender systems. Recurrent Neural Networks and transformer-based models have been successfully utilized for this task and shown to be very effective. In these approaches, all training examples are supplied to the model in every iteration and treated equally. However, the difficulty of a training example can vary greatly and the recommendation model can learn better if the data is given according to an easy-to-difficult curriculum. We design various curriculum strategies and show that applying the proposed CL techniques to a given recommendation model helps to improve performance.
•We explore Curriculum Learning (CL) for session-based recommendation systems.•Our curriculum strategies are based on domain knowledge.•We show that CL improves the performance of a recommendation model.
Next point-of-interest (POI) recommendation, also known as a natural extension of general POI recommendation, is recently proposed to predict user's next destination and has attracted considerable ...research interest. It focuses on learning users' sequential patterns of check-in behavior and on training personalized recommendation models using different types of contextual information. Unfortunately, most of the previous studies failed to incorporate the spatiotemporal contextual information, which plays a critical role in analyzing user check-in behavior, into recommending the next POI. In recent years, embedding learning and recurrent neural network (RNN) based approaches show promising performance for modeling sequential patterns of check-in behavior in next POI recommendation. However, not all of the historical check-in records contribute equally to the next-step check-in behavior. To provide better next POI recommendation performance, we first proposed a spatiotemporal long and short-term memory (ST-LSTM) network. By feeding the spatiotemporal contextual information into the LSTM network in each step, ST-LSTM can model the spatial and temporal information better. Also, we developed an attention-based spatiotemporal LSTM (ATST-LSTM) network for next POI recommendation. By using the attention mechanism, ATST-LSTM can focus on the relevant historical check-in records in a check-in sequence selectively using the spatiotemporal contextual information. Besides, we conducted a comprehensive performance evaluation using large-scale real-world datasets collected from two popular location-based social networks, namely Gowalla and Brightkite. Experimental results indicated that the proposed ATST-LSTM network outperformed two state-of-the-art next POI recommendation approaches regarding three commonly-used evaluation metrics.
Although algorithms have been widely used to deliver useful applications and services, it is unclear how users actually experience and interact with algorithm-driven services. This ambiguity is even ...more troubling in news recommendation algorithms, where thorny issues are complicated. This study investigates the user experience and usability of algorithms by focusing on users' cognitive process to understand how qualities/features are received and transformed into experiences and interaction. This work examines how users perceive and feel about issues in news recommendations and how they interact and engage with algorithm-recommended news. It proposes an algorithm experience model of news recommendation integrating the heuristic process of cognitive, affective, and behavioral factors. The underlying algorithm can affect in different ways the user's perception and trust of the system. The heuristic affect occurs when users' subjective feelings about transparency and accuracy act as a mental shortcut: users considered transparent and accurate systems convenient and useful. The mediating role of trust suggests that establishing algorithmic trust between users and NRS could enhance algorithm performance. The model illustrates the users' cognitive processes of perceptual judgment as well as the motivation behind user behaviors. The results highlight a link between news recommendation systems and user interaction, providing a clearer conceptualization of user-centered development and the evaluation of algorithm-based services.
•The usability of algorithms by focusing on users' cognitive process.•How qualities/features are received and transformed into experiences.•An algorithm experience model of news recommendation.
The proliferation of fake and paid online reviews means that building and maintaining consumer trust is a challenging task for websites hosting consumer-generated content. This study tests a model of ...antecedents and consequences of trust for consumer-generated media (CGM). Five factors are proposed for building consumer trust towards CGM: source credibility, information quality, website quality, customer satisfaction, user experience with CGM. Trust is expected to predict recommendation adoption and word of mouth. Data from 366 users of CGM were analyzed through structural equation modeling and the findings show that all the aforementioned factors with the exception of source credibility and user experience influence consumer trust towards CGM. Trust towards a CGM website influences travel consumers' intentions to follow other users' recommendations and fosters positive word of mouth. Findings also show that information quality predicts source credibility, customer satisfaction, and website quality.
Display omitted
•The study tests a model of antecedents and consequences of trust towards consumer-generated media (CGM).•Information quality, website quality, and customer satisfaction influence trust towards CGM.•Information quality predicts source credibility, customer satisfaction, and website quality.•Trust influences consumers' intention to follow other users' advice and to foster positive word of mouth.
With the prevalence of multimedia content on the Web, developing recommender solutions that can effectively leverage the rich signal in multimedia data is in urgent need. Owing to the success of deep ...neural networks in representation learning, recent advances on multimedia recommendation has largely focused on exploring deep learning methods to improve the recommendation accuracy. To date, however, there has been little effort to investigate the robustness of multimedia representation and its impact on the performance of multimedia recommendation. In this paper, we shed light on the robustness of multimedia recommender system. Using the state-of-the-art recommendation framework and deep image features, we demonstrate that the overall system is not robust, such that a small (but purposeful) perturbation on the input image will severely decrease the recommendation accuracy. This implies the possible weakness of multimedia recommender system in predicting user preference, and more importantly, the potential of improvement by enhancing its robustness. To this end, we propose a novel solution named Adversarial Multimedia Recommendation (AMR), which can lead to a more robust multimedia recommender model by using adversarial learning. The idea is to train the model to defend an adversary, which adds perturbations to the target image with the purpose of decreasing the model's accuracy. We conduct experiments on two representative multimedia recommendation tasks, namely, image recommendation and visually-aware product recommendation. Extensive results verify the positive effect of adversarial learning and demonstrate the effectiveness of our AMR method. Source codes are available in https://github.com/duxy-me/AMR .
Process recommendation is an important technique in business process management (BPM), which can be introduced to support modelling biomedical processes. However, most existing process recommendation ...algorithms in terms of behaviour (what tasks need to be executed in what order) suffer from the problem of state-space explosion when unfolding a process with many parallel patterns. To address this issue, the authors propose an independent path-based process recommendation algorithm to speed up the biomedical process recommendation while guaranteeing the accuracy. The experimental results of the proposed algorithm showed higher accuracy and better efficiency than the state-of-the-art algorithms.