Search

The interdisciplinary field of knowledge discovery and data mining emerged from a necessity of big data requiring new analytical methods beyond the traditional statistical approaches to discover new knowledge from the data mine. This emergent approach is a dialectic research process that is both deductive and inductive. The data mining approach automatically or semi-automatically considers a larger number of joint, interactive, and independent predictors to address causal heterogeneity and improve prediction. Instead of challenging the conventional model-building approach, it plays an important complementary role in improving model goodness of fit, revealing valid and significant hidden patterns in data, identifying nonlinear and non-additive effects, providing insights into data developments, methods, and theory, and enriching scientific discovery. Machine learning builds models and algorithms by learning and improving from data when the explicit model structure is unclear and algorithms with good performance are difficult to attain. The most recent development is to incorporate this new paradigm of predictive modeling with the classical approach of parameter estimation regressions to produce improved models that combine explanation and prediction.

This paper analyzes the intersection of individual lives and historical context by examining how cohort membership, historical conditions, and individual maturation influence subjective well-being in urban China. We use cross-classified multilevel models and repeated measures of happiness from seven waves of the Chinese General Social Survey (CGSS 2003–2013, N = 43,308). The results indicate that individuals born between 1956 and 1961 experienced setbacks at various pivotal moments throughout their life, including education, employment, economic stability, and social connections, and this cohort reports a lower overall sense of happiness when compared to other cohorts. The effect of aging on happiness comprises a U-shaped pattern; the middle-aged are the least happy. We observe an upward trend in happiness from 2003 to 2013. These results are confirmed by using subjective socioeconomic status (SES) as an alternative measure of well-being from CGSS 2003 and CGSS 2005 (N = 11,992). This paper contributes to studies of market transition by identifying the birth cohort as an important mechanism of inequality. It also augments the life-course paradigm by highlighting the significance of timing when individual lives intersect with historical context.

Studies have shown that happiness level varies significantly across birth cohorts and baby boomers are the unhappiest of all birth cohorts. Yet, we don’t know if this is due to their large cohort size negatively affecting happiness. We question whether people born in high fertility times are unhappy because they suffer more from economic setbacks and/or social strains. Using 9 waves of data from the European Social Survey United Kingdom Subset 2002–2018 (N = 19,364) and hierarchical age-period-cohort cross-classified models, we analyze the effects of cohort size, socioeconomic status, marital status, and sociality on happiness. Cohort size, marital status, and sociality are the top three factors of cohort difference in happiness, but socioeconomic status is not. Cohort size is negatively associated with happiness. Income, education, or employment are not the source of unhappiness among the Boomers. Besides being members of a large cohort, the Boomers have two known factors against their odds: they are the most likely to separate and divorce and the least likely to socialize with friends despite having a large number of peers. Social disintegration and deprivation, not economic impoverishment, appears to be the culprit of unhappiness of the UK Baby Boomers.

Scholars have posed different hypotheses on the impact of global telecommunications on value orientations. We analyze and characterize the global telecommunication network and test a series of hypotheses on the relationship between gender values and three types of telephone connections: ties with the global society, ties with Western nations, and ties within groups of nations sharing similar cultural, religious, political, or geographical traits. We use multilevel models and data on two levels, between-country telecommunications network data from TeleGeography, and individual-level data (N = 70,225) on people living in 47 countries from the World Value Survey, waves III and IV. Countries with high degrees of communication insulation, measured as a high percentage of within-group ties of all global telephone links, hold less egalitarian attitudes toward gender equality. This negative effect of group insulation depresses the egalitarian effects of younger birth cohort, college education, and higher income. Embeddedness in a localized information diffusion network and isolated from global communication is associated with less egalitarian attitude toward gender equality. But neither global ties nor ties with Western countries are linked with gender attitudes.

Hyper-relational knowledge graphs can enhance the intelligence, efficiency, and reliability of industrial production by enabling equipment collaboration and optimizing supply chains. However, the construction of knowledge graphs in industrial fields faces significant challenges due to the complexity of hyper-relational data, the sparsity of industrial datasets, and limitations in existing link prediction methods, which struggle to capture the nuanced relationships and qualifiers often present in industrial scenarios. This paper proposes the HyLinker model, designed to improve the representation of entities and relations through modular components, including an entity neighbor aggregator, a relation qualifier aggregator, MoE-LSTM (Mixture of Experts Long Short-Term Memory), and a convolutional bidirectional interaction module. Experimental results demonstrate that the proposed method performs well on both public datasets and a self-constructed hoisting machine dataset. In the Mine Hoist Super-Relationship Dataset (MHSD-100), HyLinker outperforms the latest models, with improvements of 0.142 in MRR (Mean Reciprocal Rank) and 0.156 in Hit@1 (Hit Rate at Rank 1), effectively addressing the knowledge graph completion problem for hoisting machines and providing more accurate information for equipment maintenance and fault prediction. These results demonstrate the potential of HyLinker in overcoming current challenges and advancing the application of hyper-relational knowledge graphs in industrial contexts. [ABSTRACT FROM AUTHOR]

The rapid development of artificial intelligence technology is driving the intelligentization process across various fields, particularly in knowledge graph construction, where significant achievements have been made. However, research on hyper-relational knowledge graphs in the industrial domain remains relatively weak. Traditional construction methods suffer from low automation, high cost, and poor reproducibility and portability. To address these challenges, this paper proposes an optimized construction process for a hyper-relational knowledge graph for mine hoist faults based on large language models. This process leverages the strengths of large language models and the logical connections of fault knowledge, employing GPT's powerful reasoning abilities. A combined strategy of template-based and template-free prompts is designed to generate fault entities and relationships. To address potential data incompleteness caused by prompt engineering, link prediction is used to optimize the initial data generated by GPT o1-preview. We integrated the graph's topological structure with domain-specific logical rules and applied the Variational EM algorithm for alternating optimization while also incorporating text embeddings to comprehensively enhance data optimization. Experimental results show that compared to the unoptimized MHSD, the optimized MHSD achieved a 0.008 improvement in MRR. Additionally, compared to the latest KICGPT, the optimized MHSD showed a 0.002 improvement in MRR. Finally, the optimized data were successfully imported into Neo4j for visualization. [ABSTRACT FROM AUTHOR]

These figures display gender-and education-related gaps in U.S. gender attitudes from 1977 to 2018. The authors use data from the General Social Survey (N = 57,224) to estimate the historical trajectory of U.S. attitudes about women in politics, familial roles, and working motherhood. Of all attitudes analyzed, Americans hold the most liberal attitudes toward women in politics, with no gender gap and little educational difference on this issue. Attitudes toward familial roles have the largest educational gap but a small gender difference. The gender gap in attitudes toward working motherhood has persisted over time, with women holding more egalitarian attitudes than men. The educational disparity on this issue disappeared during the mid-1990s “stalled gender revolution” but has widened since. Although the “stall” occurred among all gender and educational groups on all four gender attitude measures, the decline was starkest among the college educated regarding working motherhood.

We examine the pathways by which parents influence adolescents’ close friendships, focusing on three types of behavioral styles: hostile, warm, and problem solving. Structural equation models are estimated using data at two time points from the Iowa Youth and Families Project (N = 227 friendship pairs). Results suggest that the lives of adolescents and both their mother and father are inexorably linked. Observed interactions with a close friend at Time 2 reveal teens recreate their parents’ original hostile, supportive, and problem-solving styles from Time 1. This outcome depends on (a) type of behavior and (b) gender. Mothers’ supportive behavior, fathers’ problem solving, and both parents’ hostile behavior significantly influence adolescents’ comparable interaction styles. Adolescents’ subsequent behavior toward their friend significantly affects friendship quality. Lower levels of hostile behavior in female youth, increased problem solving by males, and supportive actions toward a friend for both relate positively to rewarding friendships.

The Asia Barometer Survey of 2,000 respondents reveals that substantial majorities of the Chinese people experience feelings of happiness, enjoyment, and accomplishment. In fact, the proportion experiencing these indicators of a high quality of life are larger in China than in some more prosperous countries. Favorable historical comparison, sustained high economic growth, satisfaction with interpersonal life, and a high percentage of married people are among the explanations for China's prevalence of subjective well-being. The Chinese people's high levels of satisfaction with their interpersonal, material, and nonmaterial life domains, their positive assessments of their relative living standards, and their high rate of marriage are three direct positive influences on subjective well-being. Value priorities and other demographic characteristics also have indirect bearings on subjective well-being in China.

Data from the 'Directory of Occupational Titles' is used to create six multi-item scales to measure occupational characteristics for the 1960, 1970 and 1980 Census classifications. Substantive Complexity is an occupational dimension which requires high intelligence and academic capabilities. Motor Skills is the level of physical dexterity, and Physical Perception reflects the level of general perceptual ability required by an occupation. Social skill is the people-oriented dimension, Physical Demands is the physical requirement and Working Conditions reflects the environmental aspects.