Search Results (26)

Generative artificial intelligence (GAI) is emerging as a disruptive force, both economically and socially, with its use spanning from the provision of goods and services to everyday activities such as healthcare and household management. This study analyzes the enabling and inhibiting factors of GAI use in Spain based on a large-scale survey conducted by the Spanish Center for Sociological Research on the use and perception of artificial intelligence. The proposed model is based on the Theory of Planned Behavior and is fitted using machine learning techniques, specifically decision trees, Random Forest extensions, and extreme gradient boosting. While decision trees allow for detailed visualization of how variables interact to explain usage, Random Forest provides an excellent model fit (R² close to 95%) and predictive performance. The use of Shapley Additive Explanations reveals that knowledge about artificial intelligence, followed by innovation orientation, is the main explanatory variable of GAI use. Among sociodemographic variables, Generation X and Z stood out as the most relevant. It is also noteworthy that the perceived privacy risk does not show a clear inhibitory influence on usage. Factors representing the positive consequences of GAI, such as performance expectancy and social utility, exert a stronger influence than the negative impact of hindering factors such as perceived privacy or social risks. Full article

China’s population is aging rapidly, with a large proportion of elderly individuals “aging in place”. In central areas of large cities, the amount of community and home-based elderly care services provided by the government and for-profit organizations are insufficient to meet the demands of these “aging in place” elderly. Taking the core area of Beijing as the spatial scope, this empirical study collects the demand on services of the main types of elderly residents in community and home-based dwelling through questionnaires (n = 242) and employs a mixed-methods approach for analysis. Descriptive statistics and exploratory factor analysis are used to determine the categories and levels of those demands, and machine learning methods (random forest regression model) are used to calculate the importance of various influencing factors (features of the elderly and subdistricts’ built environment) on them. It is shown that elderly residents have a higher demand for psychological and physical condition maintenance services (mean = 3.40), and a lower demand for reconciliation and rights defense services (mean = 3.08). The results also show that the built environment factors are very important for the elderly on choosing demands, especially mean distance of CECSs (community elderly care stations) to downtown landmarks and main roads in subdistricts, and characteristics of CECS. The elderly’s own features also have a relatively important impact, especially their living arrangements, caregivers, and occupations before retirement. This study applies machine learning techniques to sociological survey analysis, helping to understand the intensity of elderly people’s demand for various community and home-based elderly care services. It provides a reference for the allocation of such service resources. Full article

Lithuania has initiated the development of voluntary ecosystem protection measures within private forests, establishing protection agreements between the state and private forest owners. This article examines the priorities and motivations of private forest owners in the voluntary protection of ecosystems, based on the analysis of expert opinions. The Delphi sociological method was employed to assess expert opinions on the priorities and motivations of private forest owners regarding the voluntary protection of ecosystems. Twenty-nine experts responded to the survey, providing insights into the attitudes of Lithuanian private forest owners towards voluntary forest protection models and contract types, potential environmental protection instruments, the necessity of compensation for losses incurred due to forest management restrictions in protected areas, the proportion of protected forests, factors influencing the intention to engage in forest protection, motivations for voluntary forest protection, the “crowd-out” effect, sources of compensation for losses, the effectiveness of ecosystem protection mechanisms in Lithuanian forests, and the factors that diminish their effectiveness. Summarizing the experts’ findings, it can be concluded that the forest protection priorities of Lithuanian private forest owners, concerning the expansion of protected areas in private forests, protection models, and incentives for protection, are likely to align with the priorities and motivations identified in other European countries. A heterogeneity of priorities and motives was identified. Almost three-quarters of experts thought the current amount of protected forest in Lithuania is sufficient or is already more than necessary, and only about one in ten thought that is necessary for owners to protect more forest. Lithuanian private forest owners are mostly motivated by full financial compensation for losses. According to experts, the majority of private forest owners do not support forest protection models that lack financial compensation. It would be appropriate to implement both permanent and fixed-term protection agreements (contracts) with compensation, alongside the option of selling forests to the state. The level of compensation is identified as the most-significant factor influencing private forest owners’ willingness to engage in ecosystem protection. Experts highlight that the primary reasons for the ineffectiveness of private forest protection measures in Lithuania include inadequate and unjustified compensation, compensation amounts that are too low relative to forest owners’ income, insufficient information, and complex bureaucratic procedures. Full article

The increasing complexity of social science data and phenomena necessitates using advanced analytical techniques to capture nonlinear relationships that traditional linear models often overlook. This chapter explores the application of machine learning (ML) models in social science research, focusing on their ability to manage nonlinear interactions in multidimensional datasets. Nonlinear relationships are central to understanding social behaviors, socioeconomic factors, and psychological processes. Machine learning models, including decision trees, neural networks, random forests, and support vector machines, provide a flexible framework for capturing these intricate patterns. The chapter begins by examining the limitations of linear models and introduces essential machine learning techniques suited for nonlinear modeling. A discussion follows on how these models automatically detect interactions and threshold effects, offering superior predictive power and robustness against noise compared to traditional methods. The chapter also covers the practical challenges of model evaluation, validation, and handling imbalanced data, emphasizing cross-validation and performance metrics tailored to the nuances of social science datasets. Practical recommendations are offered to researchers, highlighting the balance between predictive accuracy and model interpretability, ethical considerations, and best practices for communicating results to diverse stakeholders. This chapter demonstrates that while machine learning models provide robust solutions for modeling nonlinear relationships, their successful application in social sciences requires careful attention to data quality, model selection, validation, and ethical considerations. Machine learning holds transformative potential for understanding complex social phenomena and informing data-driven psychology, sociology, and political science policy-making. Full article

The frequent turnover of college graduates is a key factor leading to the frictional unemployment and structural unemployment of youth, which are important research fields concerned with pedagogy, sociology, and management; however, there is little research on the prediction of college graduates’ turnover. Therefore, this study investigated the turnover status of 17,268 college graduates from 52 universities in China, constructed and optimized a random forest model for predicting the turnover of college graduates, and analyzed the influencing mechanism of college graduates’ turnover and the importance of influencing factors. The enhanced random forest model could deal with the unbalanced data and has a higher prediction accuracy as well as stronger generalization ability in predicting the turnover of college graduates. Individual background variables, job characteristic variables, and work environment variables are all important factors influencing whether college graduates resign or not. The top five factors that affect the turnover of college graduates by more than 10% are income level, job satisfaction degree, job opportunities, and job matching degree. The conclusion of this study is conducive to improving the accuracy of turnover prediction, systematically exploring the influencing factors of college graduates’ turnover, and effectively guaranteeing the overall stability of youth employment. Full article

Ticks are acarids that can transmit diseases, such as Lyme borreliosis, to human beings. They have often been considered from an ecological perspective (the environments in which they live) or from a medical one (diagnosis and treatment), while relational approaches to human–tick encounters that integrate the social sciences have remained less common. This article opts for a socio-territorial approach and a cross-analysis of different groups of actors faced with tick risk in a rural environment during their professional or leisure activities: foresters, farmers, hunters, environmentalists and hikers. The paper is based on observations and about thirty sociological interviews conducted in 2021–2022 in the rural Argonne region (France). The survey reveals the interconnection and tension between three types of approach to tick-related issues, i.e., a localized approach (based on a knowledge of place as well as everyday uses), a health-centered approach (medical knowledge as transformed and shaped by the respondents’ own experiences of tick-borne disease) and an emphasis on taking personal responsibility instead of collective preventive health initiatives or awareness campaigns (as to the location of “tick areas” or of protective measures). Full article

Circular data are extremely important in many different contexts of natural and social science, from forestry to sociology, among many others. Since the usual inference procedures based on the maximum likelihood principle are known to be extremely non-robust in the presence of possible data contamination, in this paper, we develop robust estimators for the general class of multinomial circular logistic regression models involving multiple circular covariates. Particularly, we extend the popular density-power-divergence-based estimation approach for this particular set-up and study the asymptotic properties of the resulting estimators. The robustness of the proposed estimators is illustrated through extensive simulation studies and few important real data examples from forest science and meteorology. Full article

Up till now, the research on game theory has concentrated on the game issues between agents, which are homogeneous and at the same level in the complex hierarchical system. There have already been many fruitful results that have been successfully used in many fields, such as economics, public management, sociology, and so on. However, in real life, the more frequently faced game problems are cross-level games, which are among agents from different levels. For example, in a supply chain, single factory and whole chain; in the public management, the single family and the whole community; in a tropical rain forest, single species and whole eco-system; in biology, an animal and the bacterial group in its body; and so on. Up till now, similar topics had not been discussed in detail. This situation seriously limited the research and applications for game theory. In this paper, the author introduces their own ideas for the difficulties and possible approaches on this issue. Some suggestions have been provided at the end. The main suggestion of this paper is to learn from the results of the complexity study, to focus on the payoff function, and to find an approach for the cross-level game model. Full article

Deer hunting has a long history in the US. It is supported by hunting cultures, described as necessary for protecting forest/plant biodiversity and ecosystems, but opposed by animal welfare and rights advocates as cruel. Using multiple literature sources, we examine the trade-off between protecting deer and ecosystems from harm in the context of contemporary America. We examine various approaches for exploring harms affecting nonhuman animal populations found in the green criminological, environmental sociology, wildlife conservation and management, and ecological literature. We argue that making sense of these opposing positions requires examining the extent of deer hunting to quantify those harms in some way. Here, we examine reported deer kills for US states for the period 1999–2020. These data indicate that nearly 7 million deer are taken annually in the US. We also examined some hypothesized correlates of deer harvesting across states. While these data tell us something about the number of deer killed, these data alone are insufficient. We argue no clear conclusion about the acceptability of deer hunting can be reached given the difficulty rectifying opposing moral/philosophical positions on deer hunting, opposing deer management objectives, and scientific evidence on the ecological impacts of deer populations in the US under contemporary conditions that include shrinking forest ecosystems and impaired ecosystem stability. Full article

The study of the biodiversity of vegetation cover in the context of its genesis and development is an important task. The results of these studies are the basis for the development of ecological, biogeographical, evolutionary, and sociological research, such as modelling the dynamic processes of natural ecosystems, understanding the consequences of natural and anthropogenic changes for biodiversity, solving problems of biodiversity conservation, etc. Of particular interest from this point of view is the biodiversity of ecotones, which can serve as a model for studying the factors of the genesis of the plant cover structure in a dynamic environment. In this paper, we analyze the taxonomic structure of the flora of vascular plants and the spatial structure of the plant cover in the East Asian boreal–nemoral ecotone (of the Lower Amur region). The botanical research was conducted through the application of traditional techniques for floristic and geobotanical studies. The material for this article was drawn from over 15,000 herbarium samples and 1400 floristic and geobotanical descriptions made between 1993 and 2021 in the Lower Amur region. The analyzed flora includes 2240 species from 760 genera and 158 families, which constitute 80% of the species composition of the Russian part of the Amur River basin. The native flora comprises 1801 species from 602 genera and 152 families. The species diversity and quantitative characteristics of the natural and adventive flora of vascular plants in the Lower Amur region are comparable to those of the southern limit of the distribution of taiga ecosystems in the Holarctic. The spectrum of the leading families and genera in terms of the number of species corresponds to the geographical position of the territory (the family spectrum is led by Asteraceae, Cyperaceae, Poaceae, Ranunculaceae, Rosaceae and Polygonaceae and in the generic spectrum, Carex, Artemisia, Salix, Viola, Saxifraga, Poa and Saussurea). The specificity of the flora is determined by a combination of elements in the boreal and sub-boreal flora of East Asia. Seven floristic complexes are defined for the Lower Amur region flora: forest (41.4% of the native flora), meadow (19.2%), mire (4.1%), mountain tundra (12.5%), rocky scree (8.9%), aquatic–semiaquatic (7.8%) and floodplain–estuarine shallow (6.2%). The regularity of some floristic complexes is defined by the landscape’s ecological conditions, and the variety in the edaphic, orographic and climatic parameters within the region. The spatial structure of the plant cover of the boreal–nemoral ecotone is described. Full article

The paper deals with predicting grade point average (GPA) with supervised machine learning models. Based on the literature review, we divide the factors into three groups—psychological, sociological and study factors. Data from the questionnaire are evaluated using statistical analysis. We use confirmatory data analysis, where we compare the answers of men and women, university students coming from grammar schools versus students coming from secondary vocational schools and students divided according to the average grade. The differences between groups are tested with the Shapiro–Wilk and Mann–Whitney U-test. We identify the factors influencing the GPA through correlation analysis, where we use the Pearson test and the ANOVA. Based on the performed analysis, factors that show a statistically significant dependence with the GPA are identified. Subsequently, we implement supervised machine learning models. We create 10 prediction models using linear regression, decision trees and random forest. The models predict the GPA based on independent variables. Based on the MAPE metric on the five validation sets in cross-validation, the best generalization accuracy is achieved by a random forest model—its average MAPE is 11.13%. Therefore, we recommend the use of a random forest as a starting model for modeling student results. Full article

Artificial intelligence (AI) seeks to simulate the human ability to reason, make decisions, and solve problems. Several AI methodologies have been introduced in forestry to reduce costs and increase accuracy in estimates. We evaluate the performance of Artificial Neural Networks (ANN) in estimating the heights of Araucaria angustifolia (Bertol.) Kuntze (Brazilian pine) trees. The trees are growing in Uneven-aged Mixed Forests (UMF) in southern Brazil and are under different levels of competition. The dataset was divided into training and validation sets. Multi-layer Perceptron (MLP) networks were trained under different Data Normalization (DN) procedures, Neurons in the Hidden Layer (NHL), and Activation Functions (AF). The continuous input variables were diameter at breast height (DBH) and height at the base of the crown (HCB). As a categorical input variable, we consider the sociological position of the trees (dominant–SP1 = 1; codominant–SP2 = 2; and dominated–SP3 = 3), and the continuous output variable was the height (h). In the hidden layer, the number of neurons varied from 3 to 9. Results show that there is no influence of DN in the ANN accuracy. However, the increase in NHL above a certain level caused the model’s over-fitting. In this regard, around 6 neurons stood out, combined with logistic sigmoid AF in the intermediate layer and identity AF in the output layer. Considering the best selected network, the following values of statistical criteria were obtained for the training dataset (R² = 0.84; RMSE = 1.36 m, and MAPE = 6.29) and for the validation dataset (R² = 0.80; RMSE = 1.49 m, and MAPE = 6.53). The possibility of using categorical and numerical variables in the same modeling has been motivating the use of AI techniques in different forestry applications. The ANN presented generalization and consistency regarding biological realism. Therefore, we recommend caution when determining DN, amount of NHL, and using AF during modeling. We argue that such techniques show great potential for forest management procedures and are suggested in other similar environments. Full article

The main goal of this study is to analyse and interpret interspecific differences in foliage biomass/area and woody parts biomass as well as the ratio between quantities of foliage and woody components (i.e., branches, stem and roots). The study was principally aimed at determining basic biomass allocation patterns and growth efficiency (GE) of four broadleaved species, specifically common aspen (Populus tremula L.), European hornbeam (Carpinus betulus L.), silver birch (Betula pendula Roth.) and sycamore (Acer pseudoplatanus L.) in young growth stages. We performed whole-tree sampling at 32 sites located in central and northern parts of Slovakia. We sampled over 700 trees and nearly 4900 leaves to quantify biomass of woody parts and foliage traits at leaf and tree levels. Moreover, we estimated specific leaf area in three parts of the crown, i.e., the upper, middle and lower thirds. We found that hornbeam had the largest foliage biomass and the lowest foliage area of all investigated species, while its biomass of woody parts did not differ from aspen and sycamore. Birch had the lowest biomass of woody parts, although its foliage properties were similar to those of aspen. Intraspecific differences of foliage were related to tree size and to leaf position along the vertical crown profile. Growth efficiency (GE), expressed as woody biomass production per foliage area unit, was evidently larger in hornbeam than in the other three broadleaves. We suggest that future GE modelling should utilize real values of stem diameter increment measured in a current year, bio–sociological position of trees and competition indicators as inputs. Such an approach would elucidate the role of stand structure and tree species mixture for ecological and production properties of forest stands. Full article

Establishing shelterbelts for field protection is one of the rediscovered agroforestry practices in Europe and Hungary. Several studies have focused on the effects of these plantations on agricultural production. Prior scholarship reveals that shelterbelts enhance the diversity of bird and insect communities but generally fail to consider herbaceous cover. Our study aimed to describe the herbaceous vegetation in shelterbelts of different origins, tree species composition, and land management. We investigated surveys in four agricultural landscapes of North West Hungary, where the intensity of the landscape transformation is different. The diversity and species composition of the herbaceous vegetation were analyzed, including plant sociology and forest affinity. Our results highlight the importance of landscape history in herbaceous flora. Shelterbelts planted on cultivated without an immediate connection to former woody vegetation soil are not appropriate for the appearance of forest-related herbaceous species, regardless of tree species composition or the extent of the shelterbelt. On the contrary, the remnants of former woody vegetation are refuges for those herbaceous species that are very slow at colonizing new plantations. These findings expose that protecting existing woody areas is an essential task of agricultural land management. Full article

Forest operations are well known in exposing their workers to many risk factors, and they often require ergonomic interventions for improvement. In this regard, evaluation of biomechanical exposure has gained a lot of interest due to the concerning scientific results repeatedly showing the association between poor working postures and the development of work-related musculoskeletal disorders. Due to its simplicity, easy understanding, cost affordability, and the capability to evaluate the whole body, the OWAS method has been commonly used in postural evaluation of forestry work, being able to map the experimental observations in a final action category, in the form of a postural risk index (PRI), which helps designing or taking actions for ergonomic improvement. However, postural comparability is both relevant and important when, for instance, one tries to improve a work method or to introduce a new technology. Unfortunately, the PRI metric holds a rather low capability to characterize the changes brought by such factors in terms of postural dissimilarity or similarity, making it difficult to accurately follow the changes. For this reason, we introduce in the postural analysis, test and discuss herein two commonly used similarity metrics as specific to plant sociology and other ecology-related sciences, namely the Sørensen’s quotient of similarity (hereafter QS) and the Canberra metric (hereafter CM); their selection was based on their mathematical capabilities of dealing with data at two resolutions, namely species and individuals. Three case studies were setup to show the differences between QS, CM, and PRI and their usefulness for postural analysis while, for a better understanding, the results were described and discussed by analogy to the living world. As the technology of automating data collection and processing for postural analysis is in progress, the utility of similarity metrics in postural assessment and comparison could be further expanded so as to map a given work sequence in the time domain against best-fit postural profiles. The main conclusion of this study is that the PRI is useful for action-taking while the similarity metrics are useful for pairwise postural change evaluations and comparison. Full article