Classical Item Research Articles

Multi-dimensional Graph Neural Network for Sequential Recommendation

Graph neural networks (GNNs) technology has been widely used in recommendation systems because most information in recommendation systems has a graph structure in nature, and GNNs have advantages in graph representation learning. In sequential recommendation, the relationships between interacting items can be constructed as an isomorphic graph, and (GNNs) can capture high-order information between graph nodes. Many models have used graph-based methods for sequential recommendation, and achieved great success. However, the existing research only considers the number of interactions between items when constructing the item graph. As such, revisions are needed to capture the multi-dimensional transformation relationships between items. Hence, we emphasize the importance of multi-dimensional information, and we propose a Category and Time information integrated Graph Neural Network (CTGNN), which combines the item category and interaction time information with a multi-layer graph convolution network to form multi-dimensional fine-grained item representations. In addition, we design a temporal self-attention network to model the dynamic user preference and make the next-item recommendation. Finally, we conduct extensive experiments on three real-world datasets, and the results demonstrate the excellent performance of the proposed model.

Body Shape-Aware Object-Level Outfit Completion for Full-Body Portrait Images

Modeling fashion compatibility between different categories of items and forming personalized outfits have become important topics in recommender systems recently. However, item compatibility and outfit recommendation have been explored in perfect settings in the past, where high-quality images of items from the front view or user profiles are available. In this paper, we propose a new task called Complete The full-body Portrait (CTP) for real-world fashion images (e.g., street photos and selfies), which is able to recommend the most compatible item for a masked scene where the outfit is incomplete. Visual compatibility and personalization are the key points for accurate scene-based recommendations. In our approach, the former is accomplished by calculating the visual distance of the query scene and target item in latent space, while the latter is achieved by taking the body-shape information of the human subject into consideration. To obtain side information to train our model, ResNet-50, YOLOv3 and SMPLify-X models are adopted to extract visual features, detect item objects, and reconstruct a 3D body mesh, respectively. Our approach first predicts the missing item category from the masked scene, and then finds the most compatible items from the predicted category through computing visual distances at image level, region level and object level, together with measuring human body-shape compatibility. We conduct extensive experiments on two real-world datasets, Street2Shop and STL-Fashion. Both quantitative and qualitative results show that our model outperforms all baseline models.

Generalized theme dictionary models for association pattern discovery

Discovering association patterns of items from a collection of baskets composed of different items is an important problem in various fields. Assuming that each basket is composed of themes of items randomly sampled from a theme dictionary, the theme dictionary model provides a general framework to achieve efficient association pattern discovery with statistical inference. This paper extends the original theme dictionary model by allowing more than one category of items in a basket and only presence/absence of items is observed for each basket with all quantitative information missing. The extended models can solve a larger range of practical problems that cannot be handled by the original theme dictionary model. Both simulation studies and real data applications confirm the superiority of the proposed methods over the existing ones.

Transfer Learning applied to a Classification Task: a Case Study in the Footwear Industry

Convolutional Neural Networks are a widely used method for image classification. They are part of the Deep Learning area, whose main advantage is the fact that they do not require an human support to extract features from the images. In the context of the footwear industry, they represent a useful computational resource, being applied for style classification problems, machine vision, among others. This article aims to evaluate the performance of transfer learning methods for the purpose of hierarchical classification of new items of footwear products. For this purpose, a dataset composed by 5,177 images of womens shoes was built. A pretrained architecture was selected to be refined, in order to produce a classification model. As a main result of this study, we confirm that the use of transfer learning speeds up deep neural nets training, allowing outstanding results through a VGG16 architecture. In terms of accuracy, the results achieved 99.97% and 98.42% for classifying respectively footwear categories and subcategories.

The Importance of an Organization’s Reputation: Application of the Rasch Model to the Organizational Reputation Questionnaire for Sports Fans

Crises are unavoidable in the sport world, and their relationship with reputation is inextricable. Protecting its reputation is a top priority for a sport organization in a crisis; thus, developing a valid and reliable instrument should be a precedent. In this study, Rasch analysis was applied to evaluate a 10-item Organizational Reputation Scale (ORP), extensively used in general and sport communication research, but whose development was made under classical test theory. This traditional method has several limitations (i.e., item and sample dependencies, nonaddictive features of ordinal data, and item category functioning). The main purposes of the study were to calibrate ORP items and evaluate their category functions. A total of 373 sport fans responded to the ORP on a 5-point Likert scale. Several analytic steps were applied to provide psychometric properties of each item in the ORP. The findings provided evidence that supports the unidimensional structure of the ORP with eight items. All items and a person’s ability exhibited satisfactory levels of variability along the continuum. The 5-category rating scale in Likert format functioned properly. As a better alternative to classical test theory, Rasch analysis provided information about the practicality of each ORP item in measuring individuals’ perceptual level of an organization’s reputation within a sport setting. Our study proposed some insights for enhancing each item’s quality and encouraging future scholars to make informed decisions when using the ORP.

Classical Item Analysis from a Signal Detection Perspective

AbstractA conceptualization of multiple‐choice exams in terms of signal detection theory (SDT) leads to simple measures of item difficulty and item discrimination that are closely related to, but also distinct from, those used in classical item analysis (CIA). The theory defines a “true split,” depending on whether or not examinees know an item, and so it provides a basis for using total scores to split item tables, as done in CIA, while also clarifying benefits and limitations of the approach. The SDT item difficulty and discrimination measures differ from those used in CIA in that they explicitly consider the role of distractors and avoid limitations due to range restrictions. A new screening measure is also introduced. The measures are theoretically well‐grounded and are simple to compute by hand calculations or with standard software for choice models; simulations show that they offer advantages over traditional measures.

Discussion of “Multivariate dynamic modeling for Bayesian forecasting of business revenue”

Discussion of “Multivariate dynamic modeling for Bayesian forecasting of business revenue”

An experimental study on the categorization ability of children with moderate intellectual disabilities in China

Background Little is known about the categorization ability of children with intellectual disabilities (ID) in China, which is critical in guiding teaching practice and learning support strategies for those students. The study has aimed to explore the characteristics of categorization ability of children with ID. Method This study used an experimental method to compare the classification ability of children with moderate ID (n = 40, average age of 10.6, average IQ = 47.03), typically developing children of the same age (n = 40, average age of 10.5), and kindergarten middle-class children (n = 20, average age of 6.2) to find differences in categorization abilities, including selecting items in the same category, excluding items from a different category, and direct classification. Findings We found that the classification capacity of 10-year-old children with moderate ID was significantly lower than that of typically developing children of the same age. There was no significant difference in the total classification score between 10-year-old children with moderate ID and 6-year-old typically developing children, while there were differences in the task of direct classification. Besides, there was a significant positive correlation between IQ and classification capability in children with moderate ID. Conclusion Educators should develop corresponding educational programs based on the cognitive level and categorization ability characteristics of children with moderate ID.

Correcting for Extreme Response Style: Model Choice Matters.

Extreme response style (ERS), the tendency of participants to select extreme item categories regardless of the item content, has frequently been found to decrease the validity of Likert-type questionnaire results. For this reason, various item response theory (IRT) models have been proposed to model ERS and correct for it. Comparisons of these models are however rare in the literature, especially in the context of cross-cultural comparisons, where ERS is even more relevant due to cultural differences between groups. To remedy this issue, the current article examines two frequently used IRT models that can be estimated using standard software: a multidimensional nominal response model (MNRM) and a IRTree model. Studying conceptual differences between these models reveals that they differ substantially in their conceptualization of ERS. These differences result in different category probabilities between the models. To evaluate the impact of these differences in a multigroup context, a simulation study is conducted. Our results show that when the groups differ in their average ERS, the IRTree model and MNRM can drastically differ in their conclusions about the size and presence of differences in the substantive trait between these groups. An empirical example is given and implications for the future use of both models and the conceptualization of ERS are discussed.

Exploring the Use of Price Indices to Adjust Angler Expenditure Profiles over Time

AbstractThis research evaluated a price‐adjusting methodology to update trip expenditure information annually for economic impact analysis. Historic expenditure profiles for nonlocal Texas anglers and nonresident (out‐of‐state) anglers were generated from 1995 angler survey data collected at Lake Fork Reservoir; these data were then adjusted over a 20‐year period using price indices produced by the U.S. Bureau of Labor Statistics. To determine whether the price adjustment methodology was appropriate for angler expenditures, a replication of the 1995 angler survey was conducted in 2015 to compare adjusted expenditures to actual expenditures. Preliminary results concluded that expenditure profiles for nonlocal and nonresident anglers were different between the two periods but also suggested that significant differences within angler groups existed between the two angler surveys, so anglers were regrouped based on trip length rather than origin of trip. Adjusted average daily expenditure total for 1‐d trips during the 1995 study (US$69.38) was similar to the average daily expenditure total of the 2015 study ($77.18), and the same conclusion was found for all item categories. For multiple‐day trips, adjusted average daily expenditure ($130.48) was similar to the average daily expenditure ($128.04) in 2015. Expenditure profiles were then combined with effort data in the IMPLAN (Impact Analysis for Planning) software model to generate estimates of economic impacts. Total economic impacts of 1‐d fishing trips to Lake Fork Reservoir were estimated to be $1.28 million and $1.43 million when using the adjusted and actual expenditure profiles, respectively. For multiple‐day trips, economic impacts were estimated to be $10.82 million and $10.80 million for the adjusted and actual expenditure profiles, respectively. Although economic impact analysis must continue to identify where trip expenditures originate, results suggest that adjusting trip expenditures over time can be done using price indices and should be conducted based on trip length regardless of origin.

Forgetting dynamics for items of different categories.

How the dynamic evolution of forgetting changes for different material types is unexplored. By using a common experimental paradigm with stimuli of different types, we were able to directly cross-examine the emerging dynamics and found that even though the presentation sets differ minimally by design, the obtained curves appear to fall on a discrete spectrum. We also show that the resulting curves do not depend on physical time but rather on the number of items shown. All measured curves were compatible with our previously developed mathematical model, hinting to a potential common underlying mechanism of forgetting.

조경학 연구에서 자연성 개념의 다의적 체계 연구†

In landscape studies, the concept of naturalness was vast in its categories from physical space to cognitive systems, making it difficult to define terms at once. Therefore, this study summarized the concept and evaluation attributes of ‘naturalness’ used in the literature through systematic review (SR), and identified the scope of individual attributes that constitute the meaning of naturalness. In addition, the individual attributes classified in previous studies were identified as the meaning chain, one of the cognitive linguistic research methods, and applied to papers targeting naturalness among domestic landscape studies to organize a polysemous meaning system. Meaning chain is a suitable method for grasping words whose meaning expands in a chain due to family resemblance around prototypical meaning, and the dimension is classified according to the classification of naturalness evaluation items and a multi-semantic chain system of naturalness concepts discussed in domestic academia. The results of the study are as follows. First, the attributes of naturalness extracted through foreign landscape literature were classified into four areas: nature perceived as wilderness, nature as non-artificiality, nature as visual landscape, and nature as experience, and 13 detailed attributes. Second, these detailed attributes are generally consistent with domestic landscape studies, but their specific cases were different, and a Korean context was presented in perception of time accumulation, also they suggested that there may be a mutual conflict between naturalness attributes.

Click-through rate prediction model integrating user interest and multi-head attention mechanism

The purpose of click-through rate (CTR) prediction is to anticipate how likely a person is to click on an advertisement or item. It's required for a lot of internet applications, such online advertising and recommendation systems. The previous click-through rate estimation approach suffered from the following two flaws. On the one hand, input characteristics (such as user id, user age, user age, item id, item category) are usually sparse and multidimensional, making them effective. High-level combination characteristics are used for prediction. Obtaining it manually by domain experts takes a long time and is difficult to finish; also, customer interests are not all the same. The accuracy of the model findings will significantly increase if this immediately recognized component is incorporated in the prediction model. As a consequence, this study creates an IARM (interactive attention rate estimation model) that incorporates user interest as well as a multi-head self-attention mechanism. The deep learning network is used in the model to determine the user's interest expression based on user attributes. The multi-head self-attention mechanism with residual network is then employed to get feature interaction, which enhances the degree of effect of significant characteristics on the estimation result as well as its accuracy. The IARM model outperforms other recent prediction models in the assessment metrics AUC and LOSS, and it has superior accuracy, according to the results from the public experimental data set.

Childrens and young adults’ generalized attitudes toward foods in unbranded mobile games

PurposeThe purpose of this study is to examine how children and young adults form attitudes toward food products in unbranded gaming mobile applications and the degree to which product category attitudes can generate responses to brands in the category through the generalization process.Design/methodology/approachTwo experiments exposed children and young adults to mobile games featuring food products in a between-subjects treatment versus control design to examine both affective responses and belief formation toward food brands within the category.FindingsIt was found that both children and young adults favored branded food items in the product category after playing with an unbranded mobile game assembling food products. Young adults also developed specific beliefs about nonrepresented brands in the category, which were found to be stronger under high involvement. Parents and public policymakers must be vigilant in controlling access to food-related games, even when they are not commercial in nature because of the attitudes and beliefs formed in unbranded games.Originality/valueThis research demonstrates that attitudes and beliefs around food brands can be formed through unbranded game play when children and young adults generalize attitudes. Because of the emphasis on “advergames,” no studies have examined the impact of unbranded games on children and young adults through the generalization process.

ANALISIS BUTIR SOAL PEMELIHARAAN SASIS DAN PEMINDAH TENAGA KENDARAAN RINGAN KELAS XI SMK NEGERI 1 SEYEGAN

This study aims to determine the quality of the multiple choice items for the Final Assessment of Odd Semester Subjects for Chassis Maintenance and Light Vehicle Power Transfer for Class XI SMK Negeri 1 Seyegan for the 2020/2021 Academic Year. This research is a type of descriptive research with a quantitative approach. The data collection technique used is documentation to obtain data in the form of test question sheets, answer keys, and student responses. The data obtained were then analyzed using the program Anates Version 4.0.9 where the program will analyze the items in terms of validity, reliability, level of difficulty, discriminatory power, and effectiveness of distractors. The subjects in this study were all students of class XI Automotive Light Vehicle Engineering at SMK Negeri 1 Seyegan for the 2020/2021 Academic Year. The results showed that the quality of the multiple choice items for the Odd Semester Final Assessment of a total of 25 questions, there were 11 items (44%) in the very good category, 10 items (40%) in the good category, 2 items (8%) ) is in the sufficient category, 1 item (4%) is in the poor category, and 1 item (4%) is in the bad category. Overall, these items are of good quality and deserve to be tested on students.

Sample size requirements for riverbank macrolitter characterization

Anthropogenic litter is omnipresent in terrestrial and freshwater systems, and can have major economic and ecological impacts. Monitoring and modeling of anthropogenic litter comes with large uncertainties due to the wide variety of litter characteristics, including size, mass, and item type. It is unclear as to what the effect of sample set size is on the reliability and representativeness of litter item statistics. Reliable item statistics are needed to (1) improve monitoring strategies, (2) parameterize litter in transport models, and (3) convert litter counts to mass for stock and flux calculations. In this paper, we quantify sample set size requirement for riverbank litter characterization, using a database of more than 14,000 macrolitter items (>0.5 cm), sampled for 1 year at eight riverbank locations along the Dutch Rhine, IJssel, and Meuse rivers. We use this database to perform a Monte Carlo based bootstrap analysis on the item statistics, to determine the relation between sample size and variability in the mean and median values. Based on this, we present sample set size requirements, corresponding to selected uncertainty and confidence levels. Optima between sampling effort and information gain is suggested (depending on the acceptable uncertainty level), which is a function of litter type heterogeneity. We found that the heterogeneity of the characteristics of litter items varies between different litter categories, and demonstrate that the minimum required sample set size depends on the heterogeneity of the litter category. This implies that more items of heterogeneous litter categories need to be sampled than of heterogeneous item categories to reach the same uncertainty level in item statistics. For example, to describe the mean mass the heterogeneous category soft fragments (>2.5 cm) with 90% confidence, 990 items were needed, while only 39 items were needed for the uniform category metal bottle caps. Finally, we use the heterogeneity within litter categories to assess the sample size requirements for each river system. All data collected for this study are freely available, and may form the basis of an open access global database which can be used by scientists, practitioners, and policymakers to improve future monitoring strategies and modeling efforts.

How causal machine learning can leverage marketing strategies: Assessing and improving the performance of a coupon campaign.

We apply causal machine learning algorithms to assess the causal effect of a marketing intervention, namely a coupon campaign, on the sales of a retailer. Besides assessing the average impacts of different types of coupons, we also investigate the heterogeneity of causal effects across different subgroups of customers, e.g., between clients with relatively high vs. low prior purchases. Finally, we use optimal policy learning to determine (in a data-driven way) which customer groups should be targeted by the coupon campaign in order to maximize the marketing intervention's effectiveness in terms of sales. We find that only two out of the five coupon categories examined, namely coupons applicable to the product categories of drugstore items and other food, have a statistically significant positive effect on retailer sales. The assessment of group average treatment effects reveals substantial differences in the impact of coupon provision across customer groups, particularly across customer groups as defined by prior purchases at the store, with drugstore coupons being particularly effective among customers with high prior purchases and other food coupons among customers with low prior purchases. Our study provides a use case for the application of causal machine learning in business analytics to evaluate the causal impact of specific firm policies (like marketing campaigns) for decision support.

Hybrid Movie Recommendation System Using Machine Learning

This research suggests a hybrid movie recommendation system and optimization approach based on weighted classification and user collaborative filtering algorithm to address the issue that the single model of the standard recommendation system cannot adequately reflect user preferences. The top-N personalized movie recommendations are made by fusing the weighted classification model with the local recommendation model, which is trained based on user clustering, and the sparse linear model, which serves as the fundamental recommendation model. The scoring matrix is transformed into a low-dimensional, dense item category preference matrix based on item category preference, multiple cluster centers are obtained, the distance between each cluster center and the target user is calculated, and the target user is categorized into the closest cluster. Finally, a suggestion list is created using the collaborative filtering algorithm to forecast the scores for the target user's unrated items. The highdimensional rating matrix is transformed into a lowdimensional item category preference matrix, which further reduces the sparsity of the data. The items are then grouped based on item category preference. The recommendation algorithm suggested in this article addresses some of the limitations of a single algorithm model and enhances the suggestion effect, according to experiments using the MovieLens movie dataset.

Construct validity and fairness of an operational listening test with World Englishes

In this study, I investigate the construct validity and fairness pertaining to the use of a variety of Englishes in listening test input. I obtained data from a post-entry English language placement test administered at a public university in the United States. In addition to expectedly familiar American English, the test features Hawai’i, Filipino, and Indian English, which are expectedly less familiar to our test takers, but justified by the context. I used confirmatory factor analysis to test whether the category of unfamiliar English items formed a latent factor distinct from the other category of more familiar American English items. I used Rasch-based differential item functioning analysis to examine item biases as a function of examinees’ place of origin. The results from the confirmatory factor analysis suggested that the unfamiliar English items tapped into the same underlying construct as the familiar English items. The Rasch-based differential item functioning analysis revealed many instances of item bias among unfamiliar English items with higher proportions of item biases for items targeting narrow comprehension than broad comprehension. However, at the test level, the unfamiliar English items did not substantially influence raw total scores. These findings offer support for using a variety of Englishes in listening tests.

A Tool for Assessing the Quality of Life of Adolescents in Youth Care: Psychometric Properties of the QOLYSS.

Quality of life (QOL) has gained increased interest as a critical pathway to better understanding the lives and circumstances of children and adolescents in both the general population and among specific populations. Yet, QOL assessment among youngsters in youth care services remains a highly under-researched topic. This study examines the suitability and psychometric properties of a new QOL self-report scale for adolescents between 12 and 18 years old in youth care: the Quality of Life in Youth Services Scale (QOLYSS). The provisional version of the QOLYSS was pre-tested in a sample of 28 adolescents in youth care to examine its applicability and feasibility. Next, a comprehensive evaluation of the psychometric properties of the field-test version was conducted in a sample of 271 adolescents in youth care in Flanders, Belgium (M = 15.43, SD = 1.73). Classical item and factor analyses were carried out per subscale, (test-retest) reliability and item-discriminant validity of the subscales were examined, convergent validity was explored, and confirmatory factor analysis was used to examine the goodness-of-fit of different measurement models. Reliability measures of the scale are satisfactory, results are indicative of convergent validity, and confirmatory factor analysis provides evidence for the eight correlated factors model. Future lines of research concerning the ongoing development and application of the QOLYSS are discussed.