Accurate language achievement prediction method based on multi-model ensemble using personality factors

Author(s):  
Yuping Lin ◽  
Panpan Song ◽  
Hong Long
Author(s):  
Zhai Mingyu ◽  
Wang Sutong ◽  
Wang Yanzhang ◽  
Wang Dujuan

AbstractData-driven techniques improve the quality of talent training comprehensively for university by discovering potential academic problems and proposing solutions. We propose an interpretable prediction method for university student academic crisis warning, which consists of K-prototype-based student portrait construction and Catboost–SHAP-based academic achievement prediction. The academic crisis warning experiment is carried out on desensitization multi-source student data of a university. The experimental results show that the proposed method has significant advantages over common machine learning algorithms. In terms of achievement prediction, mean square error (MSE) reaches 24.976, mean absolute error (MAE) reaches 3.551, coefficient of determination ($$R^{2}$$ R 2 ) reaches 80.3%. The student portrait and Catboost–SHAP method are used for visual analysis of the academic achievement factors, which provide intuitive decision support and guidance assistance for education administrators.


2019 ◽  
Vol 9 (24) ◽  
pp. 5539 ◽  
Author(s):  
Shaojie Qu ◽  
Kan Li ◽  
Bo Wu ◽  
Shuhui Zhang ◽  
Yongchao Wang

With the development of data mining technology, educational data mining (EDM) has gained increasing amounts of attention. Research on massive open online courses (MOOCs) is an important area of EDM. Previous studies found that assignment-related behaviors in MOOCs (such as the completed number of assignments) can affect student achievement. However, these methods cannot fully reflect students’ learning processes and affect the accuracy of prediction. In the present paper, we consider the temporal learning behaviors of students to propose a student achievement prediction method for MOOCs. First, a multi-layer long short-term memory (LSTM) neural network is employed to reflect students’ learning processes. Second, a discriminative sequential pattern (DSP) mining-based pattern adapter is proposed to obtain the behavior patterns of students and enhance the significance of critical information. Third, a framework is constructed with an attention mechanism that includes data pre-processing, pattern adaptation, and the LSTM neural network to predict student achievement. In the experiments, we collect data from a C programming course from the year 2012 and extract assignment-related features. The experimental results reveal that this method achieves an accuracy rate of 91% and a recall of 94%.


Author(s):  
Marc Allroggen ◽  
Peter Rehmann ◽  
Eva Schürch ◽  
Carolyn C. Morf ◽  
Michael Kölch

Abstract.Narcissism is seen as a multidimensional construct that consists of two manifestations: grandiose and vulnerable narcissism. In order to define these two manifestations, their relationship to personality factors has increasingly become of interest. However, so far no studies have considered the relationship between different phenotypes of narcissism and personality factors in adolescents. Method: In a cross-sectional study, we examine a group of adolescents (n = 98; average age 16.77 years; 23.5 % female) with regard to the relationship between Big Five personality factors and pathological narcissism using self-report instruments. This group is compared to a group of young adults (n = 38; average age 19.69 years; 25.6 % female). Results: Grandiose narcissism is primarily related to low Agreeableness and Extraversion, vulnerable narcissism to Neuroticism. We do not find differences between adolescents and young adults concerning the relationship between grandiose and vulnerable narcissism and personality traits. Discussion: Vulnerable and grandiose narcissism can be well differentiated in adolescents, and the pattern does not show substantial differences compared to young adults.


2004 ◽  
Vol 12 (3) ◽  
pp. 102-115 ◽  
Author(s):  
Manfred Amelang ◽  
Petra Hasselbach ◽  
Til Stürmer

Abstract. Ten years ago a sample of N = 5.133 male and female subjects (age 28-74) responded to questionnaires including scales for personality, life style, work stress as well as questions on prevalent disease. We now report on the follow-up regarding self-reported incidence of cardiovascular disease and cancer. During a mean follow-up of 10 years, 257 participants had died. Of those alive, N = 4.010 (82%) participated in the follow-up. Of these, 120 and 180 persons reported incident cardiovascular disease and cancer, respectively. The incidence of cardiovascular disease could be significantly predicted by the personality factors “Emotional Lability”, “Behavioral Control” and “Type-A-Behavior” as well as by the “Rationality/Antemotionality”-scale according to Grossarth-Maticek. After controlling for age, gender and smoking behavior only the significant effect of “Emotional Lability” remained and the predictors according to Grossarth-Maticek had no incremental validity. Cancer could not be predicted by any personality factors.


Crisis ◽  
2003 ◽  
Vol 24 (1) ◽  
pp. 7-16 ◽  
Author(s):  
Antoon A. Leenaars

Summary: Older adults consistently have the highest rates of suicide in most societies. Despite the paucity of studies until recently, research has shown that suicides in later life are best understood as a multidimensional event. An especially neglected area of research is the psychological/psychiatric study of personality factors in the event. This paper outlines one comprehensive model of suicide and then raises the question: Is such a psychiatric/psychological theory applicable to all suicides in the elderly? To address the question, I discuss the case of Sigmund Freud; raise the topic of suicide and/or dignified death in the terminally ill; and examine suicide notes of the both terminally ill and nonterminally ill elderly. I conclude that, indeed, greater study and theory building are needed into the “suicides” of the elderly, including those who are terminally ill.


2011 ◽  
Vol 32 (1) ◽  
pp. 47-53 ◽  
Author(s):  
Julie Aitken Schermer ◽  
Andrew M. Johnson ◽  
Philip A. Vernon ◽  
Kerry L. Jang

The relationship between self-report abilities and personality was examined at both the phenotypic (zero-order) level as well as at the genetic and environmental levels. Twins and siblings (N = 516) completed self-report ability and personality questionnaires. A factor analysis of the ability questions revealed 10 factors, including politics, interpersonal relationships, practical tasks, intellectual pursuits, academic skills, entrepreneur/business, domestic skills, vocal abilities, and creativity. Five personality factors were examined, including extraversion, conscientiousness, dependence, aggression, and openness. At the phenotypic level, the correlations between the ability factor scores and personality factor scores ranged from 0 to .60 (between political abilities and extraversion). The relationship between the two areas at the genetic level was found to range between –.01 and .60; the environmental correlations ranged from –.01 to .48. The results suggest that some of the self-report ability scores are related to self-report personality, and that some of these observed relationships may have a common genetic basis while others are from a common environmental factor.


Sign in / Sign up

Export Citation Format

Share Document