scholarly journals Personalized Online Learning Resource Recommendation Based on Artificial Intelligence and Educational Psychology

2021 ◽  
Vol 12 ◽  
Author(s):  
Xin Wei ◽  
Shiyun Sun ◽  
Dan Wu ◽  
Liang Zhou

The objective of the study is to explore an effective way for providing students with the appropriate learning resources in the remote education scenario. Artificial intelligence (AI) technology and educational psychology theory are applied for designing a personalized online learning resource recommendation scheme to improve students' learning outcomes. First, according to educational psychology, students' learning ability can be obtained by analyzing their learning behaviors. Their identities can be classified into three main groups. Then, features of learning resources such as difficulty degree are extracted, and a LinUCB-based learning resource recommendation algorithm is proposed. In this algorithm, a personalized exploration coefficient is carefully constructed according to student's ability and attention scores. It can adaptively adjust the ratio of exploration and exploitation during recommendation. Finally, experiments are conducted for evaluating the superior performance of the proposed scheme. The experimental results show that the proposed recommendation scheme can find appropriate learning resources which will match the student's ability and satisfy the student's personalized demands. Meanwhile, by comparing with existing state-of-the-art recommendation schemes, the proposed scheme can achieve accurate recommendations, so as to provide students with the most suitable online learning resources and reduce the risk brought by exploration. Therefore, the proposed scheme can not only control the difficulty degree of learning resources within the student's ability but also encourage their potential by providing suitable learning resources.

Author(s):  
Muhammad Arif Liputo

This research aims to look at how great online learning resource utilization on students at the Faculty of Economics Education status of teacher training and educational sciences of the University of Jambi. This research method using ex-post facto research, namely the investigation of empirically, and not in control of the free variable (X1) directly. For learning outcome or variable (Y) is the result of student learning at the end of the even semester (June 2017) on the 2016 host students. While the population in this research is of 121 students. While the sample is taken by 30% of the population that is of 36 students. The results showed that online learning resource utilization is less good (44.45%) of students who use or take advantage of online learning resources. While others still use print learning resources and other learning resources.


Author(s):  
Xuebin Wang ◽  
Zhengzhou Zhu ◽  
Jiaqi Yu ◽  
Ruofei Zhu ◽  
DeQi Li ◽  
...  

The accuracy of learning resource recommendation is crucial to realizing precise teaching and personalized learning. We propose a novel collaborative filtering recommendation algorithm based on the student’s online learning sequential behavior to improve the accuracy of learning resources recommendation. First, we extract the student’s learning events from his/her online learning process. Then each student’s learning events are selected as the basic analysis unit to extract the feature sequential behavior sequence that represents the student’s learning behavioral characteristics. Then the extracted feature sequential behavior sequence generates the student’s feature vector. Moreover, we improve the H-[Formula: see text] clustering algorithm that clusters the students who have similar learning behavior. Finally, we recommend learning resources to the students combine similarity user clusters with the traditional collaborative filtering algorithm based on user. The experiment shows that the proposed algorithm improved the accuracy rate by 110% and recall rate by 40% compared with the traditional user-based collaborative filtering algorithm.


2021 ◽  
Author(s):  
Yang Min ◽  
Li Jinrong ◽  
Gao Xiaolin ◽  
Li Weiran ◽  
Qiao Lina

Abstract Background: To minimize the risk of infection during the COVID-19 pandemic, the learning mode of universities in China has been adjusted, and the online learning of clinical medicine is facing great challenges. This study preliminarily discusses the experience of express team-based learning (eTBL) combined with a flipped classroom (FC) and case-based learning (CBL) online for nonclinical medical students and addresses the distribution of online learning resources used in pediatrics. This study helps to document additional experience in online learning during the global trend of digital learning. Methods: When online learning was fully launched at Sichuan University in the spring of 2020, 236 penultimate-year students of nonclinical medicine majors were selected as the research objects. The penultimate-year students of the same majors in the spring of 2019 were taken as the reference objects. The research objects successively used the methods of eTBL combined with FC and CBL methods to conduct online learning in pediatrics, and students were encouraged to search and share online learning resources. The reference objects used the method of eTBL combined with CBL for offline face-to-face learning, and the test results of the two learning environments were compared. At the end of the pediatrics course in the spring of 2020, the research objects were invited to participate anonymously in an online questionnaire survey involving 12 items on a 5-point Likert scale (1 = strongly disagree, 5 = strongly agree) to evaluate the participation, satisfaction, and distribution of online learning resources used in pediatrics. Results: 1. Student participation and test scores: i. A total of 75.8% (179/236) of the respondents completed the questionnaire effectively, and 7 items on the Likert scale indicated that online learning with eTBL + FC had higher student participation than eTBL + CBL (4.64 vs 4.27, P < 0.001). ii. In the spring of 2019 and 2020, the average scores of the last four subjects were higher than those of the first four subjects (P < 0.001). The average scores of online learning courses in the spring of 2020 were higher than those of offline learning in the spring of 2019 (P < 0.001). 2. Online learning resources: i. The main motivations for students to use online learning resources were pre-class preparation (4.83), class discussion (4.28) and pre-class testing (3.79). ii. A total of 72.9% (129/179) of the students “most or all of the time” searched online learning resources in the pre-class preparation stage. iii. Students' online learning resources mainly included Chinese academic databases, search engines, teaching platforms and foreign databases. iv. The information retrieval ability of students was improved after the above online learning methods (after versus before, Mdn 5 VS 4, U = 591.0, P = 0.007). 3. More students thought that the online learning method of eTBL + CBL was more beneficial for understanding than that of eTBL + FC (P = 0.044), while the online learning method of eTBL + FC was more conducive for online learning resource retrieval than that of eTBL + CBL (P = 0.034), and the workload was greater (P = 0.001). Both of the online learning methods were conducive to online learning resource sharing (P = 0.298). 4. The results of five items on the Likert scale in the questionnaire showed that students' satisfaction with the online learning mode was high (4.16). Conclusion: i. During the COVID-19 pandemic, online eTBL shortened the learning time of typical TBL. After online learning with eTBL, in combination with FC, CBL and the use of online learning resources, students had high rates of participation and satisfaction. ii. Online learning test results were as good as offline test results. iii. The main motivation for students to use online learning resources came from learning tasks. Chinese academic databases and search engines were the main learning resources for nonclinical medical students. iv. Both online combined learning methods were helpful for students to share online learning resources. eTBL + FC was more helpful in retrieving online learning resources, and the workload was also larger, while eTBL + CBL was more helpful for students to understand course content.


2015 ◽  
Vol 3 (1) ◽  
pp. 168
Author(s):  
Wen-wen Cheng ◽  
Su-ching Lin ◽  
Ming-sui Wu

<p>For the past two decades, language center in almost every university in Taiwan has attempted to implement the notion of independent learning through online learning resources. To many student learners, the easy and inexpensive access of Internet has made innumerable learning resources provided by language centers available for self-access language learning. However, whether students have cultivated self-access learning ability through appropriate learning practices online is the main point that school authorities are eager to find out. In order to know the effectiveness of self-access learning in online resource-based context, many universities take different ways to evaluate students’ achievement. Since evaluations of self-access learning are important for student learners to know if they gradually and individually move towards autonomy, their assessments must be more objective. The purpose of this one-year study, therefore, was to examine whether selected online learning resources and evaluation methods affected students’ self-access learning attitudes and whether students cultivated self-access learning ability and learned successfully in online resource-based context. To gather the data, one hundred and twelve non-English majored students from a university of Southern Taiwan were recruited as samples and two types of objective evaluation, an assessment test and online learning records, were used in this study. Major findings indicated that language students’ self-access learning attitudes improved and they did make progress in online resource-based context. However, the training for students toward self-access learning needs to be strengthened. Suggestions were also included in this paper.</p>


Author(s):  
Kasun Somadasa ◽  
Monarindu Karunadhipathi ◽  
Nishan Wickramasinghe ◽  
Sampath Subasingha ◽  
Nuwan Kodagoda ◽  
...  

2003 ◽  
Author(s):  
Arnold N. Pears ◽  
Lars Pettersson ◽  
Carl Erickson

Sign in / Sign up

Export Citation Format

Share Document