Evaluating Visualization Sets

The design of effective glyphs for visualisation involves a number of different visual encodings. Since spatial position is usually already specified in advance, we must rely on other visual channels to convey additional relationships for multivariate analysis. One such relationship is the apparent order present in the data. This paper presents two crowdsourcing empirical studies that focus on the perceptual evaluation of orderability for visual channels, namely Bertin's retinal variables. The first study investigates the perception of order in a sequence of elements encoded with different visual channels. We found evidence that certain visual channels are perceived as more ordered (for example, value) while others are perceived as less ordered (for example, hue) than the measured order present in the data. As a result, certain visual channels are more/less sensitive to disorder. The second study evaluates how visual orderability affects min and max judgements of elements in the sequence. We found that visual channels that tend to be perceived as ordered, improve the accuracy of identifying these values.

Research on graphical perception of time series visualisations has focused on visual representation, and not on interaction. Even for visual representation, there has been limited study of the impact on users of visual encodings and the strengths and weaknesses of Cartesian and Polar coordinate systems. In order to address this research gap, we performed a comprehensive graphical perception study that measured the effectiveness of time series visualisations with different interactions, visual encodings and coordinate systems for several tasks. Our results show that, while positional and colour visual encodings were better for most tasks, area visual encoding performed better for data comparison. Most importantly, we identified that introducing interactivity within time series visualisations considerably enhances the user experience, without any loss of efficiency or accuracy. We believe that our findings can greatly improve the development of visual analytics tools using time series visualisations in a variety of domains.

Design of a dynamic and robust recommender system based on item context, trust, rating matrix and rating time using social networks analysis

The authors' interest is focused on advanced recommending functionalities proposed by more and more Internet websites w.r.t. the selection of movies, e-business sites, or any e-purchases. These functionalities often rely on the Internet users' opinions and evaluations. A « movie-recommender » application is presented. Recommender websites generally propose an aggregation of the user's evaluations critics according to different relevant criteria w.r.t. the application.The authors propose an Information Processing System (IPS) to collect, process and manage as automatically as possible these opinions or critics to support this multi criteria evaluation for recommendation. The RS (Recommender System) firstly proposes information extraction techniques in order to classify the available users' critics w.r.t. the criteria implied in the evaluation process and to automatically associate numerical scores to these critics. Then multicriteria techniques are introduced to numerically evaluate, compare and rank the competing movies the critics are reported to. Finally the RS is presented as an interactive Decision-Making Support System (DMSS) relying on a sensibility analysis of the movies ranking. A particular attention is paid to the automation of the information phase in the decision-making process: movie comments cartography according to users' evaluation criteria and attribution of a partial score to each critic considered as the expression of a value judgment in natural language.

Recently, several approaches to recommendation systems have been studied. A recommender system aims to provide personalized recommendations to users for specific items. Most of these systems always provide the most relevant items of users or items. Traditionally, the evaluation of recommender system quality has focused on the various predictive accuracy metrics of these. However, recommender system must be not only accurate but also useful to users. User satisfaction with recommender systems as an evaluation criterion of recommender system is related not only to how accurately the system recommends but also to how much it supports the user’s decision making. In particular, highly serendipitous recommendation would help a user to find a surprising and interesting item. Serendipity in this study is defined as a measure of the extent to which the recommended items are both attractive and surprising to the users. Therefore, this paper proposes an application of serendipity measure to recommender systems to improve the performance of recommender systems. In this study we define relevant or attractive unexpectedness as serendipity measure for assessing recommendation systems. That is, serendipity measure is evaluated as the measure indicating how the recommender system can find unexpected and useful items for users. Our experimental results show that highly serendipitous recommendation has better performance than the other recommendations in terms of recommendation accuracy.

We present findings from interdisciplinary research at the intersection between literary studies, information visualization, and interface design. Despite a growing interest in text visualization among literary scholars, so far, narrative visualizations are not designed to support the particular tasks involved in narratological analysis and often fail to reveal nuanced narratological features. One major outcome of our iterative research and design process is Narrelations, a novel visualization technique specifically suited for analyzing and interpreting narrative levels of a story and temporal aspects of its narrative representation. The visualization provides an overview of the nesting and distribution of narrative levels, integrates the representation of temporal phenomena, and facilitates the examination of correlations between these aspects. With this research we explore how collaboratively designed visual encodings and interaction techniques may allow for an insightful analysis at a high level coupled with a close inspection of text passages. We discuss prior work relevant to our research objectives and explain the specific characteristics of narrative levels and temporal aspects of narrative representation. After describing the research process and design principles, we apply the visualization on a test corpus of eight annotated German short stories and demonstrate its heuristic value for literary analyses and interpretations. In particular, we explore the intricate connections between the literary content of the novellas and their narrative form.

Food recommendation system has become a recent topic of research due to increase use of web services. A balanced food intake is significant to maintain individual’s physical health. Due to unhealthy eating patterns, it results in various diseases like diabetes, thyroid disorder, and even cancer. The choice of food items with proper nutritional values depends on individual’s health conditions and food preferences. Therefore, personalized food recommendations are provided based on personal requirements. People can easily access a huge amount of food details from online sources like healthcare forums, dietitian blogs, and social media websites. Personal food preferences, health conditions, and reviews or ratings of food items are required to recommend diet for thyroid patients. We propose a unified food recommendation framework to identify food items by incorporating various content-based features. The framework uses the domain knowledge to build the private model to analyze unique food characteristics. The proposed recommender model generates diet recommendation list for thyroid patients using food items rating patterns and similarity scores. The experimental setup validated the proposed food recommender system with various evaluation criteria, and the proposed framework provides better results than conventional food recommender systems.KeywordsContent-basedK-Nearest neighborTerm frequencyInverse document frequencyFood preference matrix

This paper aims to design a news recommendation model based on user preferences to address the issues in recommendation systems under large datasets. Initially, four datasetsclick_history, news, news_embedding, and user_predictwere integrated into a single table, followed by data cleaning and feature engineering. Due to the large volume of data, this paper proposes necessary data filtering for the training and testing sets, utilizing temporal data to construct user feature vectors and news feature vectors. One challenge is how to effectively integrate user preferences and news features into the model to avoid overfitting or underfitting. In the model design and building phase, different methods were attempted to merge the information of users and news. Ultimately, the user preference features were processed using a fully connected layer, and the news embedding vectors were handled using an LSTM model. These two data parts were then combined into another fully connected layer, using ReLU as the activation function and CELoss as the loss function. Subsequently, the model's hyperparameters were adjusted and evaluated, achieving favorable model performance. The prediction accuracy for recommending news to users in user_predict was calculated as an evaluation criterion. Finally, this paper proposes directions for generalization and optimization in three aspects: data processing, model design, and experimental design. This includes data processing methods, potential improvements or mechanisms that could be incorporated into the model, and hyperparameter tuning. The paper primarily proposes data filtering to solve the problem of excessive data scale, which may aid in addressing recommendation system issues under large-scale datasets.

While much recommender system research has been driven by the rating prediction task, there is an emphasis in recent research on exploring new methods to evaluate the effectiveness of a recommendation. The Recommender Systems Challenge 2014 takes up this theme by challenging researchers to explore engagement as an evaluation criterion. In this paper we discuss how predicting engagement differs from the traditional rating prediction task and motivate the rationale behind our approach to the challenge. We show that standard matrix factorization recommender algorithms do not perform well on the task. Our solution depends on clustering items according to their time-dependent profile to distinguish topical movies from other movies. Our prediction engine also exploits the observation that extreme ratings are more likely to attract engagement.

Most visualization recommendation systems predominantly rely on graphical previews to describe alternative visual encodings. However, since InfoVis novices are not familiar with visual representations (e.g., interpretation barriers [GTS10]), novices might have difficulty understanding and choosing recommended visual encodings. As an initial step toward understanding effective representation methods for visualization recommendations, we investigate the effectiveness of three representation methods (i.e., previews, animated transitions, and textual descriptions) under scatterplot construction tasks. Our results show how different representations individually and cooperatively help users understand and choose recommended visualizations, for example, by supporting their expect‐and‐confirm process. Based on our study results, we discuss design implications for visualization recommendation interfaces.

The article deals with the new principle of diploma defence (protection) for Ukrainian higher education in the form of start-ups on the example of the masters of educational and professional program «Advertising and Public Relations» Borys Grinchenko Kyiv University, which provides great opportunities for the establishment of innovative environment and every alumnus confirms very high level of qualification which was acquired during years of university study. The possible results of such a step for the development of entrepreneurship in Ukraine are also being evaluated. On the grounds of content analysis, the theme of master’s thesis of professional program «Advertising and Public Relations are analyzed as a result of willingness to solve difficult tasks and problems in professional activity, competence to apply the acquired knowledge in applied scientific research, practical communication projects, in public, commercial, creative and other socially beneficial activities with the help of future specialists in the field of advertising and PR. The structural components of a master’s startup project are described in the details, as well as an evaluation criteria and a range of possible points for their implementation were pointed out. clearly defined criteria for evaluating startup projects: creativity, visual effects, aesthetic impression, originality, style, composition, etc. The conclusions which are relative to the dynamic of development such masters’ startups are formulated in the form of more complicated, integrated interdisciplinary project, in which individual parts can be performed by a master of another structural subdivision(unit) of Borys Grinchenko Kyiv University or even other higher education institution.

Introduction: Recommendation systems (RS) are pivotal in enhancing personalized user experiences, particularly in the educational domain, where tailored book recommendation systems (BRS) support individualized learning. Despite their importance, selecting an optimal recommendation algorithm remains challenging, especially in scenarios involving large and sparse datasets. Objectives: This study aims to evaluate the performance of four recommendation algorithms—Random Baseline, Popular, User-Based Collaborative Filtering (UBCF), and Singular Value Decomposition (SVD)—to identify their strengths and tradeoffs regarding accuracy and computational efficiency. The goal is to provide actionable insights for selecting appropriate algorithms for educational platforms and similar applications. Methods: The evaluation employed a dataset containing over 10,000 books, 53,424 users, and 981,756 ratings. The algorithms were assessed using Root Mean Square Error (RMSE) to measure predictive accuracy and training time to indicate computational efficiency. The analysis addressed challenges such as data sparsity and rating biases. Results: The results demonstrated that SVD achieved the highest accuracy (RMSE: 0.950), effectively uncovering latent relationships in sparse datasets. UBCF, with a slightly lower accuracy (RMSE: 1.020), offered a balance between accuracy and computational efficiency, making it suitable for real-time applications. Conversely, simpler algorithms like Random Baseline and Popular exhibited faster training times but significantly lower predictive accuracy, highlighting the limitations of non-personalized methods. Conclusions: This study underscores the tradeoffs between accuracy and efficiency among recommendation algorithms. While SVD is ideal for accuracy-driven applications, UBCF provides a practical alternative for scenarios requiring computational efficiency. The findings have substantial implications for educational platforms and e-commerce, where personalized recommendations enhance user satisfaction and engagement. Future research should focus on integrating deep learning models and expanding evaluation criteria, including user satisfaction and diversity, to further improve the performance of recommendation systems.

Smoke has a very bad effect on the outdoor vision system. Not only are the videos with poor visual effects obtained, but also the quality and structure of the videos are reduced. In this paper, we propose a video smoke removal method based on low‐rank tensor completion via spatial‐temporal continuity constraint. The proposed method is based on the smoke mixing model and consider the sparseness of smoke and the global and local consistency of clean video. Then, the optimal solution of the smoke removal algorithm model is quickly realized by the Alternating Direction Method of Multiplier. Finally, we evaluate the experiment results of real‐world data and simulated data from the visual effects and objective indicators. And the experiment results show that our proposed algorithm can achieve better smoke removal results.

Shoulder problems are prevalent in industrial work, particularly when tasks require the hands to be used at or above shoulder level. Although extensive research has been conducted on prolonged static exertions, and several guidelines for such efforts exist, there is insufficient information for ergonomic evaluation of tasks that are intermittent and/or dynamic. A laboratory simulation was conducted of overhead assembly work that was both intermittent and dynamic, and which varied the duty cycle (work/rest ratio), arm reach, and hand orientation of a tapping task. Results consisted of endurance times and also the times of fatigue onset as indicated by perceived discomfort and declines in muscle strength. Females exhibited longer (22%) endurance times, delayed reports of discomfort, and slower declines in strength. Significant influences of duty cycle were found on both endurance and fatigue times, yet arm reach and hand orientation did not have consistent effects. Distributions of endurance and fatigue times are presented as criteria for preliminary evaluation of overhead work. Endurance times could be predicted with only moderate accuracy from earlier indicators of fatigue onset. Existing guidelines, albeit developed for static tasks, appeared unsuitable for the simulated overhead assembly efforts examined. Furthermore, such guidelines may fail to capture the substantial interindividual variability observed in this experiment.

This study investigated whether compatibility between responses and their consistent sensorial effects influences performance in manual choice reaction tasks. In Experiment 1 responses to the nonspatial stimulus attribute of color were affected by the correspondence between the location of responses and the location of their visual effects. In Experiment 2, a comparable influence was found with nonspatial responses of varying force and nonspatial response effects of varying auditory intensity. Experiment 3 ruled out the hypothesis that acquired stimulus-effect associations may account for this influence of response-effect compatibility. In sum, the results show that forthcoming response effects influence response selection as if these effects were already sensorially present, suggesting that in line with the classical ideomotor theory, anticipated response effects play a substantial role in response selection.