The objective of this study is to understand the current mental status of college students in China's Mainland. In this study, 60 thousand college students＇ microblog content from January 2014 to June 2014 was co...The objective of this study is to understand the current mental status of college students in China's Mainland. In this study, 60 thousand college students＇ microblog content from January 2014 to June 2014 was collected. An emotional energy level, which was developed by a psychologist David R Hawkins, was taken as a basis for ontology database to divide the student＇s emotion into three parts--positive, negative and neutral status. An ontology-based semantic analysis method was used to analyze the microblog data. The result shows that 46.38% of Sina microblog data reflects positive psychological status, and the ratios of neutral and negative psychological status are 19.77% and 33.85%, respectively. It means that almost one third microblog reflects some negative mentality. The semantic analysis of the big data suggests that most students have healthy mental status, and the negative status of the students should not be ignored.展开更多
Rather than maintaining the classic teaching approach, a growing number of schools use the blended learning system in higher education. The traditional method of teaching focuses on the result of students' progres...Rather than maintaining the classic teaching approach, a growing number of schools use the blended learning system in higher education. The traditional method of teaching focuses on the result of students' progress. However, many student activities are recorded by an online programming learning platform at present. In this paper, we focus on student behavior when completing an online open-ended programming task. First, we conduct statistical analysis to examine student behavior on the basis of test times and completed time. By combining these two factors, we then classify student behavior into four types by using k-means algorithm. The results are useful for teachers to enhance their understanding of student learning and for students to know their learning style in depth. The findings are also valuable to re-design the learning platform.展开更多
In order to find an effective way to improve the quality of school management,finding valuable information from students' original data and providing feedback for student management are necessary. Firstly,some new...In order to find an effective way to improve the quality of school management,finding valuable information from students' original data and providing feedback for student management are necessary. Firstly,some new and successful educational data mining models were analyzed and compared. These models have better performance than traditional models( such as Knowledge Tracing Model) in efficiency,comprehensiveness,ease of use,stability and so on. Then,the neural network algorithm was conducted to explore the feasibility of the application of educational data mining in student management,and the results show that it has enough predictive accuracy and reliability to be put into practice. In the end,the possibility and prospect of the application of educational data mining in teaching management system for university students was assessed.展开更多
There is a growing body of literature that recognizes the importance of data mining in educational systems. This recognition makes educational data mining a new growing research community. One way to achieve the highe...There is a growing body of literature that recognizes the importance of data mining in educational systems. This recognition makes educational data mining a new growing research community. One way to achieve the highest level of quality in a higher education system is by discovering knowledge from educational data such as students’ enrollment data. Many mining tools that aim to discover exciting correlations, frequent patterns, associations, or casual structures among sets of items in educational data sets have been proposed. One of the widely used tools is association rules. In this paper, the Apriori algorithm is used to generate association rules to discover the importance and correlation between factors that influence student’s decision to enroll in higher education institutions in Sudan. The algorithm is applied using a student’s enrollment data set that was created using a questionnaire and 800 students enrolled in governmental and private sector universities as a sample. This paper classifies factors that influence enrollment into: student’s demographic factors and four categories of enrollment related factors (Student and Society, Educational Institution, Admission, and Employment related factors), and determines the most influential factors in determining student’s decision to enroll in Sudanese universities. The analysis result shows that the Educational Institution related factors (50%) and Admission related factors (40%) are strongly influencing students’ enrollment decision, while the Employment related factors (10%) and Student and Society related factors (0%) have weak influence. The factors out of the 14 Educational Institution related factors that have a high impact are: reputation, diversity of study, quality of education, education facilities, and feasibility.展开更多
基金Supported by the Natural Science Foundation of Hubei Province(2013CFB292)
文摘The objective of this study is to understand the current mental status of college students in China's Mainland. In this study, 60 thousand college students＇ microblog content from January 2014 to June 2014 was collected. An emotional energy level, which was developed by a psychologist David R Hawkins, was taken as a basis for ontology database to divide the student＇s emotion into three parts--positive, negative and neutral status. An ontology-based semantic analysis method was used to analyze the microblog data. The result shows that 46.38% of Sina microblog data reflects positive psychological status, and the ratios of neutral and negative psychological status are 19.77% and 33.85%, respectively. It means that almost one third microblog reflects some negative mentality. The semantic analysis of the big data suggests that most students have healthy mental status, and the negative status of the students should not be ignored.
基金supported by the National Grand R&D Plan (Grant No.2016YFB1000805)National Natural Science Foundation of China (Grant No.61702534,61432020,61472430,61502512)
文摘Rather than maintaining the classic teaching approach, a growing number of schools use the blended learning system in higher education. The traditional method of teaching focuses on the result of students' progress. However, many student activities are recorded by an online programming learning platform at present. In this paper, we focus on student behavior when completing an online open-ended programming task. First, we conduct statistical analysis to examine student behavior on the basis of test times and completed time. By combining these two factors, we then classify student behavior into four types by using k-means algorithm. The results are useful for teachers to enhance their understanding of student learning and for students to know their learning style in depth. The findings are also valuable to re-design the learning platform.
基金Sponsored by the Ability Enhancement Project of Teaching Staff in Harbin Institute of Technology(Grant No.06)
文摘In order to find an effective way to improve the quality of school management,finding valuable information from students' original data and providing feedback for student management are necessary. Firstly,some new and successful educational data mining models were analyzed and compared. These models have better performance than traditional models( such as Knowledge Tracing Model) in efficiency,comprehensiveness,ease of use,stability and so on. Then,the neural network algorithm was conducted to explore the feasibility of the application of educational data mining in student management,and the results show that it has enough predictive accuracy and reliability to be put into practice. In the end,the possibility and prospect of the application of educational data mining in teaching management system for university students was assessed.
文摘There is a growing body of literature that recognizes the importance of data mining in educational systems. This recognition makes educational data mining a new growing research community. One way to achieve the highest level of quality in a higher education system is by discovering knowledge from educational data such as students’ enrollment data. Many mining tools that aim to discover exciting correlations, frequent patterns, associations, or casual structures among sets of items in educational data sets have been proposed. One of the widely used tools is association rules. In this paper, the Apriori algorithm is used to generate association rules to discover the importance and correlation between factors that influence student’s decision to enroll in higher education institutions in Sudan. The algorithm is applied using a student’s enrollment data set that was created using a questionnaire and 800 students enrolled in governmental and private sector universities as a sample. This paper classifies factors that influence enrollment into: student’s demographic factors and four categories of enrollment related factors (Student and Society, Educational Institution, Admission, and Employment related factors), and determines the most influential factors in determining student’s decision to enroll in Sudanese universities. The analysis result shows that the Educational Institution related factors (50%) and Admission related factors (40%) are strongly influencing students’ enrollment decision, while the Employment related factors (10%) and Student and Society related factors (0%) have weak influence. The factors out of the 14 Educational Institution related factors that have a high impact are: reputation, diversity of study, quality of education, education facilities, and feasibility.
