The Machines Take Over: A Comparison of Various Supervised Learning Approaches for Automated Scoring of Divergent Thinking Tasks

Traditionally, researchers employ human raters for scoring responses to creative thinking tasks. Apart from the associated costs this approach entails two potential risks. First, human raters can be subjective in their scoring behavior (inter-rater-variance). Second, individual raters are prone to inconsistent scoring patterns (intra-rater-variance). In light of these issues, we present an approach for automated scoring of Divergent Thinking (DT) Tasks. We implemented a pipeline aiming to generate accurate rating predictions for DT responses using text mining and machine learning methods. Based on two existing data sets from two different laboratories, we constructed several prediction models incorporating features representing meta information of the response or features engineered from the response’s word embeddings that were obtained using pre-trained GloVe and Word2Vec word vector spaces. Out of these features, word embeddings and features derived from them proved to be particularly effective. Overall, longer responses tended to achieve higher ratings as well as responses that were semantically distant from the stimulus object. In our comparison of three state-of-the-art machine learning algorithms, Random Forest and XGBoost tended to slightly outperform the Support Vector Regression.     

On L-decomposability of random orderings

In the setting of random orderings, we study conditional independence properties related to L-decomposability. We show that if a random ordering satisfies L-decomposability for any labelling of the ranks, then it is quasi-independent, provided the number of alternatives is at least 4, and each ordering has a positive probability.     

Statistical inference and sensitivity to sampling in 11-month-old infants

Research on initial conceptual knowledge and research on early statistical learning mechanisms have been, for the most part, two separate enterprises. We report a study with 11-month-old infants investigating whether they are sensitive to sampling conditions and whether they can integrate intentional information in a statistical inference task. Previous studies found that infants were able to make inferences from samples to populations, and vice versa [Xu, F., & Garcia, V. (2008). Intuitive statistics by 8-month-old infants. Proceedings of the National Academy of Sciences of the United States of America, 105, 5012-5015]. We found that when employing this statistical inference mechanism, infants are sensitive to whether a sample was randomly drawn from a population or not, and they take into account intentional information (e.g., explicitly expressed preference, visual access) when computing the relationship between samples and populations. Our results suggest that domain-specific knowledge is integrated with statistical inference mechanisms early in development.     

Parent and Adolescent Gender Role Attitudes in 1990s Great Britain

Using data from the British Household Panel Survey, this short-term longitudinal study examined relationships between early- and mid-adolescents' gender role attitudes and the attitudes of their parents. Between 1994 and 1997, 602 families answered questions about the roles of husbands and wives, and whether or not having a working mother is harmful to families. Results confirmed that the gender differences that have been found consistently in the literature regarding adults extend back into early adolescence. Adolescent girls' attitudes were markedly more nontraditional than all other family members. However, results only partially supported our hypotheses regarding family influence on attitudes. In particular, we found little evidence that adolescent attitudes would more closely resemble those of the same-gender parent. Analysis of individual questions supports arguments that gender roles are complex and socially determined, and that British men of both adult and adolescent generations have begun in principle to accept nontraditional roles for wives but are less willing to support any erosion of male power in the family.     

Need for recovery, home-work interference and performance: Is lack of concentration the link?

This study examines the mechanisms through which experiences in the home domain influence work performance by bringing together the literature on recovery and the work-family interface. A longitudinal study among 123 employees from different organizations was conducted to investigate whether need for recovery and home-work interference (HWI) impeded concentration at work 1 month later, and whether concentration adversely affected in-role performance over time. Structural equation modeling analysis supported these hypotheses. Whereas need for recovery and HWI had negative, lagged effects on concentration, concentration had a positive lagged effect on in-role performance. Moreover, need for recovery and HWI were reciprocal and negatively related over time, suggesting that these two states may create a negative spiral in the home domain that could easily intrude into the work domain. These findings increase our insight in the processes leading to reduced performance at work, and suggest that organizations should facilitate opportunities for recovery.     

Random noun generation in younger and older adults

We examined age-related changes of executive functions by means of random noun generation. Consistent with previous observations on random letter generation, older participants produced more prepotent responses than younger ones. In the case of random noun generation, prepotent responses are nouns of the same category as the preceding noun. In contrast to previous observations, older participants exhibited stronger repetition avoidance and a stronger tendency toward local evenness—that is, toward equal frequencies of the alternative responses even in short subsequences. These data suggest that at higher adult age inhibition of prepotent responses is impaired. In addition, strategic attentional processes of response selection are strengthened, in particular the application of a heuristic for randomness. In this sense response selection is more controlled in older than in younger adults.     

The stability of adult personality varies across age: Evidence from a two-year longitudinal sample of adult New Zealanders

We model developmental patterns in the stability of Big-Six personality markers over a two-year period in a multi-cohort panel study of adult New Zealanders (n = 3910). Structural Equation Models testing patterns of linear, quadratic and cubic effects identified considerable variation in the stability of most aspects of personality across the adult age range (20–80 years). Agreeableness showed a slight linear decrease in consistency with increasing age. Extraversion, Conscientiousness, Neuroticism, Openness to Experience, and Honesty–Humility exhibited quadratic ‘inverted U’ patterns of rank-order stability. Unlike Agreeableness, the two-year consistency of these other personality dimensions increased from young adulthood towards middle age, then decreased as people progressed toward old age. Implications for personality research and emerging trends are discussed.     

Self-concept and academic achievement: a meta-analysis of longitudinal relations

The relation between self-concept and academic achievement was examined in 39 independent and longitudinal samples through the integration of meta-analysis and path analysis procedures. For relations with more than 3 independent samples, the mean observed correlations ranged from .20 to .27 between prior self-concept and subsequent academic achievement and from .19 to .25 between prior academic achievement and subsequent self-concept. Globality/specificity of self-concept was the only significant moderating factor in the relation between (a) prior self-concept and subsequent academic achievement and (b) prior academic achievement and subsequent self-concept. As high self-concept is related to high academic performance and vice-versa, intervention programs that combine self-enhancement and skill development should be integrated.     

Differentiating conscientious from indiscriminate responders in existing NEO-Five Factor Inventory-3 data

The mean Inter-Item Standard Deviation (M-ISD; i.e., the mean of several single-scale ISDs) is a post-hoc validity index that statistically differentiates conscientious responders (CRs) from indiscriminate responders (IRs) in psychological questionnaire data. We compared the M-ISD’s effectiveness against four other post-hoc indexes and an embeddable validity scale in three sets of NEO-Five-Factor Inventory-3 data. Results showed the M-ISD has superior classification ability over all other post-hoc indexes and even outperformed the embeddable validity scale. The average classification accuracy of the M-ISD and embeddable scale was 97% and 93%, respectively, whereas only one of the four remaining post-hoc indexes exceeded our classification accuracy criterion of 80%. These findings suggest researchers can use the M-ISD to differentiate valid from invalid data.