User Preferences Research Articles

Lights, Headset, Tablet, Action: Exploring the Use of Hybrid User Interfaces for Immersive Situated Analytics

While augmented reality (AR) headsets provide entirely new ways of seeing and interacting with data, traditional computing devices can play a symbiotic role when used in conjunction with AR as a hybrid user interface. A promising use case for this setup is situated analytics. AR can provide embedded views that are integrated with their physical referents, and a separate device such as a tablet can provide a familiar situated overview of the entire dataset being examined. While prior work has explored similar setups, we sought to understand how people perceive and make use of visualizations presented on both embedded visualizations (in AR) and situated visualizations (on a tablet) to achieve their own goals. To this end, we conducted an exploratory study using a scenario and task familiar to most: adjusting light levels in a smart home based on personal preference and energy usage. In a prototype that simulates AR in virtual reality, embedded visualizations are positioned next to lights distributed across an apartment, and situated visualizations are provided on a handheld tablet. We observed and interviewed 19 participants using the prototype. Participants were easily able to perform the task, though the extent the visualizations were used during the task varied, with some making decisions based on the data and others only on their own preferences. Our findings also suggest the two distinct roles that situated and embedded visualizations can have, and how this clear separation might improve user satisfaction and minimize attention-switching overheads in this hybrid user interface setup. We conclude by discussing the importance of considering the user's needs, goals, and the physical environment for designing and evaluating effective situated analytics applications.

Comparison of Unencumbered Interaction Technique for Head-Mounted Displays

Head Mounted Displays (HMDs) are gaining more public attention. With the advancement of tracking technologies, they are incorporating unencumbered interaction techniques to address the need for user-friendly and efficient interaction techniques for day-to-day activities. While there is a good understanding of the different interaction techniques individually, very little research has been done to compare them directly. This would be vital to understanding their strengths and weaknesses in different contexts and building better synergies among them. This paper uses a target selection task to compare the performance and user preferences for four interaction techniques: gaze-pinch, ray pointer, hand-proximate user interface, and direct mid-air interactions. Results indicate that the gaze-pinch interaction technique required significantly more time to complete the task than the others, whose time to complete was similar. However, in terms of preferences and errors, the interaction techniques mostly performed similar.

An Approach for Combining Clinical Judgment with Machine Learning to Inform Medical Decision Making: Analysis of Nonemergency Surgery Strategies for Acute Appendicitis in Patients with Multiple Long-Term Conditions.

Machine learning (ML) methods can identify complex patterns of treatment effect heterogeneity. However, before ML can help to personalize decision making, transparent approaches must be developed that draw on clinical judgment. We develop an approach that combines clinical judgment with ML to generate appropriate comparative effectiveness evidence for informing decision making. We motivate this approach in evaluating the effectiveness of nonemergency surgery (NES) strategies, such as antibiotic therapy, for people with acute appendicitis who have multiple long-term conditions (MLTCs) compared with emergency surgery (ES). Our 4-stage approach 1) draws on clinical judgment about which patient characteristics and morbidities modify the relative effectiveness of NES; 2) selects additional covariates from a high-dimensional covariate space (P > 500) by applying an ML approach, least absolute shrinkage and selection operator (LASSO), to large-scale administrative data (N = 24,312); 3) generates estimates of comparative effectiveness for relevant subgroups; and 4) presents evidence in a suitable form for decision making. This approach provides useful evidence for clinically relevant subgroups. We found that overall NES strategies led to increases in the mean number of days alive and out-of-hospital compared with ES, but estimates differed across subgroups, ranging from 21.2 (95% confidence interval: 1.8 to 40.5) for patients with chronic heart failure and chronic kidney disease to -10.4 (-29.8 to 9.1) for patients with cancer and hypertension. Our interactive tool for visualizing ML output allows for findings to be customized according to the specific needs of the clinical decision maker. This principled approach of combining clinical judgment with an ML approach can improve trust, relevance, and usefulness of the evidence generated for clinical decision making. Machine learning (ML) methods have many potential applications in medical decision making, but the lack of model interpretability and usability constitutes an important barrier for the wider adoption of ML evidence in practice.We develop a 4-stage approach for integrating clinical judgment into the way an ML approach is used to estimate and report comparative effectiveness.We illustrate the approach in undertaking an evaluation of nonemergency surgery (NES) strategies for acute appendicitis in patients with multiple long-term conditions and find that NES strategies lead to better outcomes compared with emergency surgery and that the effects differ across subgroups.We develop an interactive tool for visualizing the results of this study that allows findings to be customized according to the user's preferences.

Desain Taman Atap pada Gedung SMP Pesat Bogor Berdasarkan Preferensi Pengguna

The increasing rate of urbanization on limited urban land has resulted in reduced Green Open Space (RTH) in urban areas. Therefore, the design of a roof garden on a school building can be a solution to increase the area of ​​green open space and a place for outdoor learning activities. This study aims to analyze the potential and constraints on the site so that a roof garden design can be developed according to user preferences. The stages of work refer to Booth (1983) which consist of project acceptance, research/analysis, concepts, and construction drawings. The design concept applied is inspired by the organically formed Falco peregrinus. The results of this study are in the form of a roof garden site plan as well as detailed pictures of the facilities used in the roof garden of building 3 SMP-SMA-SMK Informatika Pesat. The results of the study are expected to create a roof garden on a school building that can function as green open space and a refreshing area as well as a teaching and learning area.

DMHANT: DropMessage Hypergraph Attention Network for Information Propagation Prediction.

Predicting propagation cascades is crucial for understanding information propagation in social networks. Existing methods always focus on structure or order of infected users in a single cascade sequence, ignoring the global dependencies of cascades and users, which is insufficient to characterize their dynamic interaction preferences. Moreover, existing methods are poor at addressing the problem of model robustness. To address these issues, we propose a predication model named DropMessage Hypergraph Attention Networks, which constructs a hypergraph based on the cascade sequence. Specifically, to dynamically obtain user preferences, we divide the diffusion hypergraph into multiple subgraphs according to the time stamps, develop hypergraph attention networks to explicitly learn complete interactions, and adopt a gated fusion strategy to connect them for user cascade prediction. In addition, a new drop immediately method DropMessage is added to increase the robustness of the model. Experimental results on three real-world datasets indicate that proposed model significantly outperforms the most advanced information propagation prediction model in both MAP@k and Hits@K metrics, and the experiment also proves that the model achieves more significant prediction performance than the existing model under data perturbation.

Transforming Libraries: The Impact of Artificial Intelligence

Artificial intelligence (AI) is revolutionising library services and enhancing user experience, creating a new era of efficiency, accessibility, and innovation. This editorial explores how AI reshapes the library landscape, ushering in a new generation of efficiency, accessibility, and innovation. The AI’s most notable contribution to libraries is the automation of routine tasks, cataloguing and organising; librarians can now rely on AI algorithms to streamline. It saves librarians valuable time engaging in intellectually stimulating activities and ensures a more accurate and organised library system. AI-driven systems can efficiently analyse vast amounts of data, leading to improved search functionalities and more seamless information retrieval for library patrons. Moreover, AI is instrumental in the personalisation of library services. Through machine learning algorithms, libraries can analyse user behaviour, preferences, and historical data to provide customised recommendations. This enhances the user experience by offering tailored suggestions for reading materials, resources, and services, making libraries more relevant and engaging for diverse user groups. Another essential role of AI in libraries is the development of virtual assistants. These digital assistants, powered by natural language processing and machine learning, can help library patrons navigate the catalogue system, answer queries, and even provide Realtime language translation service. Virtual assistants help libraries become more inclusive and accessible, reaching more audiences with diverse language backgrounds and information needs.

Multimodal Feedback to Improve Performance of Order Picker Truck Drivers Using a Virtual Reality Simulator

VR technology presents exciting prospects for immersive forklift training environments. VR facilitates hands-on learning without the risks of real world errors. Real-time multimodal feedback (such as visual and haptic) is an effective way to enhance learning outcomes and skill acquisition. However, the efficacy and usability of real-time multimodal feedback provided for VR-based forklift driving needs to be investigated, as its impact on training outcomes remains unexplored. We aim to understand how various feedback modalities influence task performance, perceived workload, and user preferences. Fifteen (3 female, 12 male) individuals participated and completed VR-based forklift driving tasks with four feedback conditions (No feedback, visual, haptic, combined visual and haptic). A significant main effect of Feedback was found for completion time. Mental demand and frustration were affected by the Sex and Feedback interaction. These differences in the perception of feedback modalities underscore the importance of considering diverse user demographics when designing feedback systems.

Predicting Consumer Behavior in E-Commerce Using Recommendation Systems

As e-commerce platforms continue to expand, understanding consumer behavior has become crucial for enhancing customer satisfaction and driving business success. Recommendation systems play a pivotal role in predicting consumer preferences and delivering personalized product suggestions. This paper presents an extensive literature review on recommendation techniques, including collaborative filtering, content-based approaches, and hybrid models. Notable advancements, such as the use of deep learning, trust-based filtering, and context-aware models, are highlighted. Building on these foundations, we propose a novel model that integrates advanced machine learning algorithms with consumer behavior analysis to predict preferences more accurately. The expected results suggest that this model will improve the precision of recommendations, effectively addressing challenges like data sparsity and evolving user preferences and enhancing overall customer engagement in e- commerce environments.

Leveraging user’s preference and social circle for personalized recommendation via matrix factorization with sub-linear convergence rate

Recommender systems aim to filter information effectively and recommend useful sources to match users’ requirements. However, the exponential growth of information in recent social networks may cause low prediction accuracy for recommendation systems. This article proposes a unified personalized recommendation architecture referred to as PSRec, which incorporates user preference and social relationship into matrix factorization framework. Specifically, PSRec generates two collections for textual reviews and contextual information respectively, and performs preference learning for each user via the Latent Dirichlet Allocation topic model. Moreover, PSRec exploits the inner relations within the social circle for recommendation, including direct trust relationship and indirect trust relationship. Additionally, it’s certificated that PSRec can converge at a sub-linear rate via theoretical analysis. Experimental results over DoubanMovie, CiaoDVDs and Yelp demonstrate the superiority of the proposed PSRec, which can achieve significant improvements and provide much better user experience while compared with other benchmark models.

The complete mitochondrial genome of Castanopsis carlesii and Castanea henryi reveals the rearrangement and size differences of mitochondrial DNA molecules

BackgroundCastanopsis carlesii is a dominant tree species in subtropical evergreen broad-leaved forests and holds significant ecological value. It serves as an excellent timber tree species and raw material for cultivating edible fungi. Henry Chinquapin (Castanea henryi) wood is known for its hardness and resistance to water and moisture, making it an exceptional timber species. Additionally, its fruit has a sweet and fruity taste, making it a valuable food source. However, the mitogenomes of these species have not been previously reported. To gain a better understanding of them, this study successfully assembled high-quality mitogenomes of C. carlesii and Ca. henryi for the first time.ResultsOur research reveals that the mitochondrial DNA (mtDNA) of C. carlesii exhibits a unique multi-branched conformation, while Ca. henryi primarily exists in the form of two independent molecules that can be further divided into three independent molecules through one pair of long repetitive sequences. The size of the mitogenomes of C. carlesii and Ca. henryi are 592,702 bp and 379,929 bp respectively, which are currently the largest and smallest Fagaceae mitogenomes recorded thus far. The primary factor influencing mitogenome size is dispersed repeats. Comparison with published mitogenomes from closely related species highlights differences in size, gene loss patterns, codon usage preferences, repetitive sequences, as well as mitochondrial plastid DNA segments (MTPTs).ConclusionsOur study enhances the understanding of mitogenome structure and evolution in Fagaceae, laying a crucial foundation for future research on cell respiration, disease resistance, and other traits in this family.

A Comparative Study of Bazaar Cultural Spaces in Central Asia and China

With the advancement of modernization, traditional bazaars have encountered challenges, such as diminished vitality. Concurrently, the trend of integrating cultural spaces into bazaars has become increasingly evident. Understanding the relationship between bazaars and cultural spaces, as well as the preferences of users of these spaces, is crucial for enhancing bazaar vitality. Employing field research, questionnaire surveys, cross-analysis, and the narrative preference method, this paper compares the bazaar cultural spaces of Central Asia and Chinese from four perspectives: the current state of the bazaar, development overview, user preferences, and cultural space type preferences. This aims to deepen the understanding of the commonalities and differences between the two regions, and to explore the development trends of bazaars and their cultural spaces. The study reveals that (1) Spaces with diversified functions, high accessibility, and openness can enhance the vitality of the bazaar; (2) There exists a synergistic, mutually beneficial relationship between the bazaar and the cultural spaces; (3) Central Asian residents place greater emphasis on the environmental quality of the bazaar and the engaging content of its cultural spaces. In contrast, Chinese residents are more focused on the accessibility of the bazaar and the openness of the cultural spaces; (4) The function of art and culture is the preferred type of cultural space in the bazaar among residents of both regions. This study significantly contributes to the planning, design, and optimization of bazaars and their cultural spaces.

User characteristics and preferences for micromobility use in first- and last-mile journeys in Dublin, Ireland

Micromobility and public transport integration is an area of urban mobility that has been increasingly gaining attention and importance. The necessity to provide improvements to public transport services and their spatial reach in order to reduce the number and volume of car trips in cities is irrefutable. The integration of micromobility and public transport is often presented as a valuable strategy to improve door-to-door connectivity and coverage of existing public transport services, via provision of key first- and last-mile or access-egress connections. The aim of this study was to understand and model the propensity of commuters in County Dublin to use micromobility (private and shared) in the first- and last-miles of their public transport journeys. A stated preference experiment was conducted with a focus on these specific segments of the journey and a mixed logit model was estimated to identify user characteristics and preferences based on socio-economic factors, mobility patterns and attitudes towards and previous experience of shared mobility. The results show that, in this particular case study, respondents with a strong walking preference were less likely to be interested in private micromobility and sharing services for the first- and last-mile. A common assumption that walking is a last resort, and only chosen when there are no other options available was not confirmed by the findings of this study. Moreover, competition between the modes showed that private bicycles are the preferred mode after walking, followed by private e-scooters, while shared modes were less likely to be chosen over walking, and shared e-scooters less so than shared bicycles. Overall, the findings suggest that a small percentage of the sample – mainly young (<35 years old) and male respondents with interest in and experience of e-scooters – were interested in using private and shared e-scooters for the first- and last-mile, but that the majority of the respondents were likely to choose walking, albeit with longer travel times overall.

Comparing ‘fair’ machine learning models for detecting at-risk online gamblers

ABSTRACT Researchers have worked to develop machine learning models that detect at-risk online gamblers, enabling personalized harm prevention tools. However, existing research has not evaluated these models’ potential to reinforce or amplify sociodemographic biases leading to treatment disparity, a recognized issue in the machine learning field. We sought to develop and compare three examples of potentially fair models using online gambling data. In two large samples of transaction data from a provincially owned Canadian gambling website (N1 = 9,145, N2 = 10,716), we developed three machine learning models based on competing concepts of fairness: fairness via unawareness, classification parity, and outcome calibration. We hypothesized that significant relationships existed between reporting a high risk of past-year gambling problems (the dependent variable) and participants’ age and sex. Further, we hypothesized that the three ‘fair’ models would show differing levels of classification performance both in aggregate and within sociodemographic groups. Significant age and sex effects were found, refuting the fairness via unawareness modeling strategy. Superiority across all performance metrics was not present for either of the remaining models. For the fairest practices in any jurisdiction, classification parity and outcome calibration models should be tested in situ, and incorporate the perspectives and preferences of end users who will be affected.

Overcoming barriers to proactive plastic recycling toward a sustainable future

The plastics sector, accounting for a significant portion of global emissions, presents a challenge and an opportunity in achieving carbon neutrality. Despite Japan's commendable polyethylene terephthalate (PET) bottle recycling rates, most plastics are thermally recycled, creating environmental issues. This study proposes an evaluation framework to enhance recycling, aligned with end-user preferences and fostering a circular plastics economy. Employing a mixed-methods approach, this study conducts fieldwork including interviews with plastic recyclers and analysis of industry data. A weighted sum multicriteria analysis integrating end-user preferences, recycling effectiveness, and market dynamics is utilized. Systemic, process, and policy challenges were shown to hinder sustainable recycling practices, while varying willingness to pay, emission and cost reduction potentials, among acceptability and sectoral diversity informed priority plastic types for recycling. Multicriteria analysis showed that although PET is favored by end users, Polyoxymethylene (POM) emerges as a potential priority target for manufacturers and recyclers. Sensitivity analysis underscores the potential impact of establishing or enhancing willingness to pay (WTP) toward certain plastic types. Moreover, manufacturer and recycler evaluations suggest a broader willingness to recycle plastics than previously assumed. The proposed evaluation framework offers insights toward plastic recycling strategies. Policy interventions such as sustained subsidies for recyclers, market incentives leveraging WTP preferences, and technological advances, including chemical recycling and the broadening of plastic type recycling in line with user and manufacturer preferences, could all contribute to promoting sustainable plastic recycling practices.

User preference and social relationship-aware recommendations base on a novel light graph convolutional network

User preference and social relationship-aware recommendations base on a novel light graph convolutional network

Our Model Achieves Excellent Performance on MovieLens: What Does It Mean?

A typical benchmark dataset for recommender system (RecSys) evaluation consists of user-item interactions generated on a platform within a time period. The interaction generation mechanism partially explains why a user interacts with (e.g., like, purchase, rate) an item, and the context of when a particular interaction happened. In this study, we conduct a meticulous analysis of the MovieLens dataset and explain the potential impact of using the dataset for evaluating recommendation algorithms. We make a few main findings from our analysis. First, there are significant differences in user interactions at the different stages when a user interacts with the MovieLens platform. The early interactions largely define the user portrait which affect the subsequent interactions. Second, user interactions are highly affected by the candidate movies that are recommended by the platform's internal recommendation algorithm(s). Third, changing the order of user interactions makes it more difficult for sequential algorithms to capture the progressive interaction process. We further discuss the discrepancy between the interaction generation mechanism that is employed by the MovieLens system and that of typical real-world recommendation scenarios. That is, the MovieLens dataset records \(\langle user-MovieLens\rangle\) interactions, but not \(\langle user-movie\rangle\) interactions. All research articles using the MovieLens dataset model the \(\langle user-MovieLens\rangle\) rather than the \(\langle user-movie\rangle\) interactions, making their results less generalizable to many practical recommendation scenarios in real-world settings. In summary, the MovieLens platform demonstrates an efficient and effective way of collecting user preferences to address cold-starts. However, models that achieve excellent recommendation accuracy on the MovieLens dataset may not demonstrate superior performance in practice , for at least two kinds of differences: (1) the differences in the contexts of user-item interaction generation, and (2) the differences in user knowledge about the item collections. While results on MovieLens can be useful as a reference, they should not be solely relied upon as the primary justification for the effectiveness of a recommendation system model.

DRL-based Content Caching Strategy With Efficient User Preference Predictions in UAV-assisted VEC

DRL-based Content Caching Strategy With Efficient User Preference Predictions in UAV-assisted VEC

Knowledge-Enhanced Conversational Recommendation via Transformer-Based Sequential Modeling

In conversational recommender systems (CRSs), conversations usually involve a set of items and item-related entities or attributes, e.g., director is a related entity of a movie. These items and item-related entities are often mentioned along the development of a dialog, leading to potential sequential dependencies among them. However, most of existing CRSs neglect these potential sequential dependencies. In this article, we first propose a Transformer-based sequential conversational recommendation method, named TSCR, to model the sequential dependencies in the conversations to improve CRS. In TSCR, we represent conversations by items and the item-related entities, and construct user sequences to discover user preferences by considering both the mentioned items and item-related entities. Based on the constructed sequences, we deploy a Cloze task to predict the recommended items along a sequence. Meanwhile, in certain domains, knowledge graphs formed by the items and their related entities are readily available, which provide various different kinds of associations among them. Given that TSCR does not benefit from such knowledge graphs, we then propose a knowledge graph enhanced version of TSCR, called TSCRKG. In specific, we leverage the knowledge graph to offline initialize our model TSCRKG, and augment the user sequence of conversations (i.e., sequence of the mentioned items and item-related entities in the conversation) with multi-hop paths in the knowledge graph. Experimental results demonstrate that our TSCR model significantly outperforms state-of-the-art baselines, and the enhanced version TSCRKG further improves recommendation performance on top of TSCR.

Tools and Techniques for the Effective and Responsible Management of Print Journal Back-Runs in an Academic Library: Lessons from a Case Study

With shifting use patterns and user preferences, competing demands on finite library spaces, and reliable electronic journal backfile platforms, the withdrawal of print journal back-runs from academic library shelves is now commonplace. Yet the related procedures covered in the literature are manual and time-consuming. In a recent print journal management project at an academic library, using current tools and techniques enabled the efficient application of evidence-informed criteria, automated overlap and collection comparison, and responsive implementation. Participation in a shared print archive as part of the project prompted reflections about the associated costs and benefits.

SABTR: semantic analysis-based tourism recommendation

Online tourism spot recommendations, as a key component of tourism services, aim to present travel options that align with users’ personal preferences. However, current recommendation systems often underperform due to the sparsity of tourism data and the wide variance in user preferences. To address this challenge, we propose a Semantic Analysis-Based Tourism Recommendation framework, abbreviated as SABTR (Semantic Analysis-Based Tourism Recommendation). The framework comprises two stages: Firstly, Latent Dirichlet Allocation (LDA) models are utilized to deeply mine data between users and attractions, constructing two core matrices: the user similarity matrix and the attraction similarity matrix. Secondly, based on the user similarity matrix, similarity calculation methods are applied to predict ratings for tourism spots that users have not yet evaluated. Simultaneously, within the attraction similarity matrix, probability distributions for each attraction across various thematic interests are calculated. When the system identifies a user’s interest in specific types of attractions, SABTR can select a series of related attractions from associated interest tags. Then, these candidate attractions are ranked according to both known and predicted user ratings, ultimately forming personalized attraction packages recommended to users. Extensive experiments have demonstrated that compared to existing tourism recommendation solutions, our method significantly improves the quality of attraction recommendations and enhances user satisfaction.