International Journal of Continuing Engineering Education and Life-Long Learning (48 papers in press)
Research On The Evaluation Method For English Teaching Efficiency Based On Data Mining
by Zhonghui Man
Abstract: In order to overcome the problems of large errors and long time consuming in traditional evaluation methods for English teaching efficiency, a new method based on data mining is proposed. This paper first introduces the application of DEA in the evaluation of English teaching efficiency, combines the decision-making unit of DEA with data mining, and then cleans, supplements and repairs the acquired teaching data to complete the mining of the characteristic data of English teaching efficiency evaluation. At last, the data of English teaching efficiency evaluation of college students and teachers are obtained by questionnaire survey. The experimental results show that the proposed method has a small error and a short evaluation time in the evaluation of English teaching efficiency, which has a certain practical significance.
Keywords: Data mining; English teaching; Efficiency evaluation; Excellence rate; Reliability indicator.
Quasi-experimental study on the classroom flipping degree in the course of Information Technology and Application
by Ke Hong, Lu Jia
Abstract: Abstract: In recent years, the flipped classroom teaching mode is increasingly widely applied. We adopted the flipped classroom teaching mode in the course of Information Technology and Application in Nanchang University and achieved the good teaching effect. In order to deeply explore the relationship between flipped classroom and teaching effect, three groups of flipped classroom experiments were performed under three flipping degrees (25%, 50% and 75%) and the statistical data analysis was performed with the final experimental results. The analysis results indicated that the teaching effect was the best under a flipping degree of 50%.
Keywords: flipped classroom; classroom flipping degree; experimental comparison; data analysis.
Design and application of educational information management system based on SOA
by Liping Han
Abstract: Due to low throughput, long average response time and low operating efficiency of current educational information regulatory system, it is because of SOA framework designed. The hardware part includes system access port module, computer-aided instruction module and security management module. The software part uses the service bus of the SOA framework to complete the collection of educational information, realise the management of educational information through the service interface, calculate the average value of the time series of the teaching resource management data through the moving average method, filter the redundant data, and realise the collection and sharing of educational information To complete the design of service function of educational information. The experimental results show that the designed system has the characteristics of fast response, high efficiency and high throughput.
Keywords: SOA framework; Teaching resources; Management system design; Application research.
The Evaluation Method Of Distance Learning Engagement Based On The Multi-Level Linear Model
by Humin Yang
Abstract: The traditional evaluation process of distance learning engagement cannot solve the problem of hierarchical confusion of the data to be processed, which leads to low recovery rate of distance learning engagement data and large evaluation error. A distance learning engagement evaluation method based on multi-layer linear model is proposed. Establish the level index of distance learning curriculum, compile the questionnaire of students and teachers, and determine the influencing factors of distance teaching involvement. By constructing a multi-layer linear model of distance learning, this paper analyzes the curriculum effectiveness that affects students' engagement ability in distance learning, and evaluates the engagement degree of distance learning.The simulation results verify that the recovery rate of the proposed method is above 97%, and the error rate of the evaluation of distance learning engagement is below 0.002%.
Keywords: Multi-leveled linear model; Distance learning engagement; Evaluation.
Research On Evaluation Of Mooc Distance Learning Effect Based On Bp Neural Network
by Jiefeng Wang, Henry Loghej
Abstract: At present, MOOC learning effect evaluation method has the problems of large evaluation error and low evaluation efficiency. Therefore, this paper proposes a MOOC distance learning effect evaluation method based on BP neural network. Select the evaluation index, and the gray correlation analysis method is used to optimize the evaluation index, and the entropy weight method is used to calculate the index weight. The BP neural network model is constructed, which is used as the evaluator of MOOC distance learning effect. The sample data to be identified is input to minimize the accumulated evaluation residual and output the evaluation result of MOOC distance learning effect. After testing, the error rate of the design method is only 0.9259%, the evaluation time is always less than 1.0s, the evaluation error is small and the evaluation efficiency is high.
Keywords: MOOC; Distance learning effect; Gray correlation analysis; BP neural network.
A New Hybrid Teaching Platform for College English Based on Iot
by Fangqiong Liu
Abstract: In order to improve the practice ability of new hybrid teaching of college English, it is necessary to integrate hybrid English teaching resources, so a new hybrid teaching platform for college English based on the Internet of Things is proposed. In this paper, a new hybrid teaching resource information fusion model for college English is constructed, and hybrid teaching resource information about college English is scheduled using the big data statistical analysis method, and network modularization design is carried out for the new hybrid teaching platform for college English under the Internet of things. The simulation results demonstrate that the new hybrid teaching resource scheduling method for college English can provide good information fusion and contribute to high output stability and reliability of the teaching platform.
Keywords: Internet of things technology ; college English; new hybrid teaching; practice; resource fusion; big data.
The advantage resources mining of practical English with internet of things technology
by Chunzi Zhang
Abstract: In order to overcome the problems of low efficiency and accuracy of traditional methods for the advantage resources mining of practical English, this paper proposes a new method for the advantage resource mining of practical English which integrates Internet of things technology. Using the Internet of things technology to guide the focused crawler, the search strategy ACO-FC to collect practical English resources can be gotten, the features of practical English resources are extracted, the weight corresponding to the features of English resources by TF-IDF weight calculation method is calculated, and the practical English resources are classified by the nearest distance discrimination algorithm of class center vector, so as to complete the advantage resources mining of practical English. The experimental results show that compared with the traditional mining methods, the mining efficiency and mining accuracy of the proposed method are higher, and the highest mining accuracy can reach 98%.
Keywords: Internet of things technology; Advantage resources of practical English; Resource classification; Resource mining.
Research on Modeling and analysis of factors influencing students classroom communication ability based on support vector machine
by Jue Wang, Xi Chen, Yang Zhang
Abstract: In order to improve students classroom learning effect, the influencing factors of communication ability were analysed. The traditional method of analysing students classroom ability neglects the ordering of classroom communication ability factors, which results in poor fitting effect and high CPU consumption. This paper proposes an analysis model of influencing factors of students classroom communication ability based on support vector machine. The sample data were converted and cleaned to establish a SVM model for influencing factors and students classroom communication ability. The trained SVM model was used to analyse the degree of influence of each factor on students classroom communication ability, and the factors were ranked in importance, so as to clarify the influencing factors of students classroom communication ability. The simulation results show that the prediction results obtained by the research method are close to the fitting curve of the actual results. The CPU consumption of system operation is 15.88 Hz, which is lower than the traditional method.
Keywords: Support vector machine; Students classroom communication ability; modeling analysis of influencing factors.
Expectations for cooperative instruction supported by the Internet+Employment platform in work placement practice
by Xifeng Liao
Abstract: Close high-quality cooperation between a workplace employer and the college is a prerequisite for effective training of students in vocational education. Therefore, the researcher adopted the internet+employment platform as a typical case to analyse its main supportive functions for work placement instruction. Descriptive data analysis was employed to study the expectations of both vocational students and workplace supervisors for the cooperative teaching supported by the platform. The case study showed that the platform was weak in several areas such as in sharing teaching resources to facilitate employer-college cooperation. The results of the data analysis suggested that most students and workplace supervisors have a thorough understanding of the importance of closer cooperation and cooperative assessment by both the employer and the college. However, the expectations of the students and workplace supervisors were different in seven aspects. Among them, the students did not expect much cooperation that would lead to a closer monitoring of their work positions, and the willingness of the workplace supervisors to cooperate with college advisors in the use of cloud technology was quite limited. Suggestions for future development of the internet+employment platform were proposed. Combining the functions of this platform with those of other cloud platforms might support better employer-college cooperative instruction.
Keywords: student and employers expectation; cooperative instruction; work placement; workplace supervisor; cloud platform technology.
Multi-Interaction English Teaching Platform Based On Internet Of Things
by Xianglang Hou, Zongning Zhang
Abstract: There are some problems in college English teaching, such as poor level, which increase the interactive function of the classroom. An interactive foreign language teaching software is proposed. The platform consists of platform management layer, multiple interactive English teaching module, test paper assignment module and database module. The task of management analysing administrators, and setting instruction program, the multiple interactive English teaching module constructs the multiple interactive English teaching model, the paper exercise allocation module constructs the test paper quantitative model, and the database module specifies the information storage rules. The experimental results show that: the u-value of oral English and listening of the experimental group is less than 0.05, and the P-value of reading score is 0.059.
Keywords: internet of things technology; multi-interaction; teaching platform; platform management module; multi-interaction English teaching module; test paper quantitative model.
Research on Knowledge Tree Growth Model for Intelligent English Teaching System based on Hypertext Structure
by Shixin Sun, Haiyan Li
Abstract: At present, the knowledge management model of intelligent English teaching system has some problems, such as weak relevance of knowledge points and poor judgment accuracy of precursor knowledge points. This paper proposes a new knowledge tree growth model for intelligent English teaching system based on hypertext structure. Using hypertext structure resources for English teaching content model to build, packaging, the content of the metadata and completed the organisation of English teaching resources, through the tree of knowledge map, knowledge circulation knowledge teaching, the precursor of judgment, determine the level of knowledge mastery, and knowledge extraction process, realise the building of knowledge tree growth model. The experimental results show that the proposed knowledge tree growth model greatly improves the relevance of knowledge points and the accuracy of judgment of precursor knowledge points, improves the knowledge base of intelligent English, and improves the efficiency and quality of English teaching.
Keywords: hypertext structure; intelligence; English; teaching; knowledge tree; model.
Application of fuzzy ahp in the evaluation of students cognitive ability
by Zhaohui Wei, Ziyan Luo, Peng Sang, Juan Du
Abstract: Cognitive theory holds that each individuals cognitive ability is different. If teachers can adopt appropriate evaluation method, they will be able to accurately know each students cognitive ability and characteristics, which is conducive to personalised teaching implementation. Therefore, based on the revised Bloom cognitive theory, this paper establishes the evaluation index system of students cognitive ability by adopting the analytic hierarchy process (AHP) method, carries out fuzzy evaluation of students test scores with the fuzzy theory, works out the weight of each indicator of cognitive ability by expert scoring method, and finally obtains the comprehensive evaluation of students cognitive ability. It is proved that this method can be more objective and comprehensive in evaluation of the students cognitive ability, and it can reflect their achievement degree of each goal, show their strengths and weaknesses, offering some valuable information for students later study.
Keywords: Blooms cognitive theory; fuzzy logic; analytic hierarchy process; AHP.
The Method Of Interest Text Recommendation In English Education Based On Data Mining
by Linlin Fan
Abstract: In order to solve the problem of low accuracy and long time consuming of traditional English educational interest recommendation methods, a text recommendation method based on data mining was proposed. Build English education text classification system, according to the classification results determine user interest areas, based on the setting behaviour data information domain, recommended target clearly, get user browse English data matrix, standardising the user data, get the user interest degree apriori algorithm combining with data association rules with English education text, finally completed in English education text using association rule mining algorithm is recommended. The experimental results show that the proposed method has a high-precision of recommendation, and the precision and recall rate are significantly better than the traditional method, which provides effective theoretical support for the research in related fields.
Keywords: data mining; English education; text recommendation; interest text; association rules.
Research on Effectiveness Model of Online Learning for College Students in Big Data Era
by Xiaojun Zhang, Xiaoji Yang
Abstract: In order to enhance the effectiveness of online learning of college students in the era of big data, this paper puts forward the research on the effectiveness model of online learning of college students. This paper establishes a fusion clustering model for the evaluation of online learning effect, and uses fuzzy fusion grouping method to analyse the panel data of online learning effect evaluation of college students combined with big data mining method, analyses the characteristics of online learning behaviour of college students and mining association rules. Linear programming model is used to optimise the scheduling of online learning resources for college students. The experimental results show that the design method has high accuracy and reliability in predicting the online learning effect of college students in the era of big data, and improves the convergence and optimisation ability of learning process.
Keywords: learning analysis; big data era; online learning; effectiveness assessment.
Formative assessment method of English language application ability based on consistency assessment
by Guanguan Zeng
Abstract: Due to the fact that learners mastery of English language is not taken into account in the current methods, resulting in higher error and lower credibility of the assessment results, a formative assessment method of English language application ability based on consistency assessment is proposed. According to the principles of formative assessment, the implementation conditions of formative assessment include clear assessment objectives, diversified assessment means, determination of assessment criteria and timely feedback of information. Specific assessment tasks are defined and theoretical model of autonomous learning is constructed to realise the assessment of English language application ability. Taking the students of two classes of automobile maintenance major in college was the test objects; the final assessment scheme is set. Experimental results show that the proposed method can effectively reduce the assessment error and improve the credibility of the assessment results.
Keywords: consistency assessment; English language; application ability; formative; assessment.
Research on the integration and optimization of MOOC teaching resources based on deep reinforcement learning
by Kun Jiao, Xin Han, Li Xu, Terry Gao
Abstract: There are some problems in the merging of English MOOC learning information, such as high packet loss rate and high repetition rate. This paper designs a new method of resource data merging with the help of deep reinforcement learning. Analyse the operation mode of English MOOC platform, and collect teaching resources for the initial application of MOOC under this platform. The pre-processing of the initial collection of resources is completed through translation, Chinese word segmentation, semantic annotation of word segmentation results and other steps. The features of English MOOC teaching resources are extracted, and the deep enhancement learning algorithm is adopted to optimise. Through comparative experiments, it is found that the packet loss rate of the combined learning information is only 0.28% and the integrated resource repetition rate is only 0.89%.
Keywords: deep reinforcement learning; English teaching; MOOC teaching; integration of teaching resources; resource characteristics; feature weight value.
New Technologies in Personalisation of STEM and STEAM Education - International Context
by Todorka Glushkova, Krzysztof Gurba, Theo Hug, Nataliia Morze, Tatiana Noskova, Eugenia Smyrnova-Trybulska
Abstract: This article focuses on new technologies in personalisation of STEM and STEAM education in contemporary education, as viewed by experts from different countries: Austria, Bulgaria, Poland, Russia and Ukraine. The article aims to review research literature, and provide opinions, views and reflections presented by scientists and experts from several European universities. The research review includes the theoretical background of the discussed topic, a review of national and international research and literature, identification and definition of key concepts, examples of practical achievements, and a description of contemporary trends of STEM and STEAM Education and adaptive learning as well as microlearning- effective methods of e-learning. At the end a number of conclusions are drawn.
Keywords: STEM; STEAM; personalised learning; individual learning; experts; adaptive learning; microlearning; international context.
Research on online evaluation method of MOOC teaching quality based on decision tree-based big data classification
by Jiefeng Wang, Humin Yang
Abstract: In order to improve the online evaluation ability to massive open online course (MOOC) teaching quality, an online evaluation method of MOOC teaching quality based on decision tree-based big data classification is proposed. First, a big data statistical analysis model is built to identify fuzzy degree parameters. Then, the quality index system is obtained to realise big data fusion and cluster analysis. It is concluded that this method has high accuracy in online evaluation. In this paper, the method shows that the accuracy as high as 0.996 when the number of iterations reaches 500. Its innovation lies in the analysis of the global optimal solution of online evaluation of distance MOOC teaching quality by using the big data decision tree model, which improves the information management of MOOC online evaluation.
Keywords: big data statistical analysis; decision tree-based classification; MOOC teaching quality; online evaluation method; information fusion and clustering.
Advanced And Effective Teaching Design Based On BOPPPS Model
by Changdong Wu, Xiangzhen He, Hua Jiang
Abstract: To meet the requirement of teaching reform, effective teaching design is an important way to improve teachers teaching ability and students learning ability. How to design a high quality teaching content is a critical problem which should be considered. BOPPPS model is an advanced and effective teaching design method, which includes six parts such as bridge-in, outcome, pre-assessment, participatory learning, post-assessment and summary. In this process, it takes teacher as the instructor, problem-oriented, student-centred and participatory learning as the core. In order to apply the advanced teaching concept in teaching design, this paper takes series feedback voltage stabilising circuit as an example to build a teaching design based on BOPPPS model. In this process, many improved circuits based on the real teaching situation are analysed and discussed. It has been proved that the proposed method is an effective teaching model for promoting the teachers teaching quality and students learning ability.
Keywords: teaching design; teaching reform; BOPPPS model; circuit design; improved circuit.
The Role of Critical Thinking Development Technology in the Development of Students Intellectual Ability
by Bakhytkul Kaskatayeva, Maral Andassova
Abstract: This article discusses the role of critical thinking development technology in the formation of students' intellectual abilities. Purposeful formation of intellectual abilities of students allows to establish cause-and-effect relations between phenomena and laws of development of events that is necessary for the student for mastering scientific knowledge and foreign languages. The aim of the study is to reveal the essence of critical thinking of students in the learning process and to develop and test the technology of critical thinking as a tool for intellectual development of students. The study applied methods such as analysis of psychological, pedagogical, scientific, methodological and educational literature on the topic of research; monitoring the progress of the educational process; questioning; rating control; testing; conversations with teachers and students. The article proposes a solution to the problem of formation of intellectual qualities of students on the basis of technology of critical thinking.
Keywords: critical thinking; intellectual qualities; technology; higher education institution.
Research on teaching quality evaluation model of distance education in colleges based on analytic hierarchy process
by Xiao-long Wen
Abstract: There are some problems in the existing teaching quality evaluation methods, such as low evaluation accuracy, puts forward a model of distance education teaching quality evaluation in colleges and universities by means of analytic hierarchy process. From this perspective in students, peers and supervisors, obtain the evaluation index of teaching quality and calculate its weight value, analysing the hierarchical process is introduced. In this model, the evaluation indexes in the hierarchy are sorted and the consistency is verified, and the teaching quality evaluation model of distance education in colleges based on AHP. Through the research of the proposed method, the conclusion is drawn that the error of distance education effect of imparting knowledge evaluation by using the proposed model is relatively low, and it is feasible to some extent.
Keywords: distance education; effect of education; evaluation model; consistency verification.
Student as researchers: towards redefining undergraduate projects
by Suki Honey, Asiya Khan, Richard Pemberton, Priska Schoenborn, Andrew Edward-Jones
Abstract: The aim of this paper is to collect evidence of success and identify areas of good practice that can enable the process of re-defining undergraduate projects and lead to peer-review publications through student-staff collaborations. A pilot study was conducted with ten participants from STEM and non-STEM backgrounds. Based on the response and feedback, the questionnaire was revised and sent to a number of internal and external peers mainly in STEM. Twenty eight responses were received. Finally, four focus groups were hosted two with five internal members of staff and two with nine undergraduate students studying civil and mechanical engineering at the University of Plymouth. The findings show that the majority of undergraduate student projects resulting in publications were jointly chosen by tutors and student and positively impacted on student learning. The emphasis was on good quality data collection by the students. The biggest barrier identified was the time commitment required by staff to convert student reports to publishable papers.
Keywords: student projects; engineering; undergraduate research; peer-reviewed publications.
Research On The Method Of Educational Text Classification Based On Deep Learning
by Yuqin Wang
Abstract: To improve the efficiency of traditional text classification methods of education and the recall rate of research objectives, we proposed an educational text classification method based on the depth of learning. The English web pages covering the economics, politics, sports, entertainment, and life, etc., which involves carriers containing explanatory texts and discussion papers, etc., will be used as the source of English education texts for corresponding collection and processing. Upload the collected English educational texts, introduce deep learning algorithms, perform preprocessing and feature learning, and input the learning features into the deep learning Softmax classifier based on the learning results. The output of the classifier is the classification result of the educational text To complete the classification of educational texts. Experimental results show that the experimental results show that the proposed method of classification accuracy, higher recall rate, and time-consuming short, the average distribution time-consuming to 3.992 s. It shows that the proposed method can effectively improve the classification efficiency of educational texts.
Keywords: deep learning; educational text; text classification; learning characteristics; English education.
Detection Method Of Students Classroom Learning Behavior Based On Parallel Classification Algorithm
by Degang Lai, Ke Wang
Abstract: In order to overcome the problem that students learning behaviour process is easy to form misclassification in the process of serial classification, this paper proposes a method to detect students learning behaviour in class based on parallel classification algorithm. The parallel classification model is constructed. By measuring Kinect coverage and adjusting Kinect top view angle, the coordinates of each students position are transformed. The auxiliary feature vector is applied in behaviour recognition to realise the parallel combination and processing of multiple data sources, accurately extract the feature vector to form different relevance, and realise the detection of students classroom learning behaviour. The experimental results show that students can grasp the degree of interest in the course and the degree of seriousness in the whole teaching process. The detection rate is more than 90%, which is practical.
Keywords: classroom learning behaviour; parallel classification algorithm; Kinect; skeleton feature vector.
The problem-based learning mode for Teaching English to college students
by Lijuan Song
Abstract: This paper firstly introduced the traditional English teaching mode and then briefly introduced the problem-based learning (PBL) English teaching mode. Then, in order to test the effect of the PBL teaching mode, 200 college students were selected for relevant teaching tests. The final results demonstrated that the performance distribution of students who were taught by the traditional mode almost had no change after English teaching, and the performance distribution of students who were taught by the PBL mode in the experimental class had improvement. The questionnaire survey of students in the experimental class showed that most students agreed with the PBL mode.
Keywords: English; problem-based learning; PBL; teaching mode; listening; speaking; reading.
Evaluation model of College Students' online learning level difference based on support vector machine
by Kunzhe Liu, Xiqiang Ge, Jiefeng Wang
Abstract: There are some problems in the evaluation of online learning level differences among college students, such as low accuracy and long evaluation time, to propose a new research method. By extracting online learning behaviour characteristics, to determine behaviour evaluation indexes and evaluation standards, and by the depth of the residual neural network method to remove interference index, using the Lagrange multiplier method, the evaluation problem is transformed into the dual problem, and the nonlinear transformation, thus seeking the optimal classification plane, to obtain the optimal classification function, difference evaluation data accessed by the big data technology, through the normalised processing the data, obtain the final evaluation results, complete online learning evaluation level differences. Through comparison, the accuracy of this method is 97%, and the time cost of assessment is always less than 9.5 ms.
Keywords: support vector machine; online learning; difference evaluation; behaviour characteristics.
An online teaching process monitoring method of MOOC platform based on video recognition
by Humin Yang, Jiefeng Wang
Abstract: In order to overcome the problem of low monitoring accuracy of traditional methods, a new online teaching process monitoring method based on video recognition for MOOC platform is proposed. The weight coefficient of online teaching process monitoring information of MOOC platform is calculated, and the monitoring information is reconstructed. On this basis, video recognition method is used to mine the online teaching process monitoring information of MOOC platform. Through the construction of monitoring model, the online teaching process monitoring of MOOC platform is realised. The experimental results show that the mean square error analysis results of the monitoring method based on video recognition verify that the effect of different gender students is different. The method has high correction coefficient, high monitoring accuracy and good application effect, which can effectively improve the effect of students online learning.
Keywords: video recognition; MOOC platform; online teaching; process monitoring.
Design of reservation model of teaching equipment in NC laboratory based on BS mode
by Haibo Liu, Xinbo Zhang, Qingzhong Gong
Abstract: In order to solve the job scheduling problem of CNC laboratory equipment concurrent reservation, the design method of CNC laboratory teaching equipment reservation model based on BS mode is proposed. By using BS mode, the equipment management structure of numerical control laboratory is designed hierarchically. Build the reservation time series model to realise the load transmission and information estimation in the process of reservation. According to the statistical results, the reservation fitness function is designed, and the reservation scheduling and reservation algorithm are designed. Based on this, the database security storage function and SMS processing function of the model are designed to realise the construction of teaching equipment reservation model in CNC laboratory. Experimental results show that: compared with the traditional equipment design model, the model designed in this paper has higher reservation success rate and better application performance.
Keywords: BS mode; numerical control laboratory; teaching equipment reservation; statistical characteristic quantity; fitness function.
A balanced allocation method of English MOOC teaching resources based on QoS constraints
by Xiaodong Yuan
Abstract: In order to overcome the problems of long allocation time and high bandwidth consumption in traditional resource allocation methods, this paper proposes a new balanced allocation method of English MOOC teaching resources based on QoS constraints. With the support of big data and cloud computing technology, MOOC English teaching resources are mined and collected, and the resource balanced allocation model is constructed by using MMPs algorithm. The resource balanced allocation of virtual machine is realised through the selection of QoS constraint parameters, physical resource mapping and QESA resource allocation system. On the basis of experiments, the proposed method has the advantages of balanced resource allocation and execution time.
Keywords: QoS constraints; MOOC resources; MMPS algorithm; QESA system.
Developing a computer-assisted writing system to solve phraseological problems for Chinese graduate students academic writing
by Tong Zhao, Xiuhai Zhang, Zhongliang Zhan
Abstract: This study develops a computer-assisted writing system, consisting of the searching module and the text editing module. The searching module is characterised by part-of-speech (POS) collocation search which retrieves technical and general collocations from a customised corpus of research articles in a specialised field. The text editing module is characterised by next-word prediction which works on lexical bundle lists from COCA. Through the development of these modules and functions, the POS and position of collocations are specified, the word likely to follow a given sequence is predicted, English for technical use and general use are concerned, and the display of the retrieved information is optimised. At present, this system works well in the research field of tubulin. It could be applied to academic writing of other research areas if the customised corpus of that area is built and uploaded.
Keywords: phraseological learning; computer-assisted writing system; academic writing; Chinese graduate students; corpus.
Mobile learning determinants that influence Indian university students learning satisfaction during COVID-19
by Md Qamar, Mohd Ajmal, Abdullah Malik, Mohd. Ahmad, Juhi Yasmeen
Abstract: Due to the COVID-19 pandemic whole world went under strict lockdown, including educational institutes. This led to the quick reshaping of educational systems to provide uninterrupted education to the students. Preferably, both teachers and students switched from physical classrooms to online classrooms. This overnight change brought numerous challenges for a country like India. But the authors of this study see it as an opportunity and aim to explore mobile learning (m-learning) determinants that influence Indian university students learning needs during the COVID-19. For this, the data were gathered using a web-based questionnaire from 557 students of seven different universities (both public and private) in India. Next, the data were quantitatively analysed using reliability analysis, confirmatory factor analysis, and multiple regression analysis. The results show that out of three first-order m-learning variables, only two (system and service quality items) have a positive impact on students learning satisfaction in the Indian context. In the end, the implications of the study in the adoption of m-learning at different Indian universities have been discussed.
Keywords: COVID-19 and online learning; m-learning determinants; students learning satisfaction; India.
Automatic quantitative assessment of English writing proficiency based on multi feature fusion
by Fengtian Xu
Abstract: In the existing quantitative evaluation methods of English writing level, the accuracy of feature extraction is low and the error is high. An automatic quantitative evaluation method of English writing level based on multi-feature fusion is put forward. By using vector space model and Jekard similarity coefficient to determine the cosine similarity of English text, the features of English text are extracted by Manhattan distance. Through kernel function, the multi-feature fusion of English writing text is realised. The multivariate linear regression model is used to determine the feature weight of English text and to quantitatively process the feature data. The automatic quantitative evaluation model of English writing level is constructed to complete the automatic quantitative evaluation of English writing level. The experimental results show that the accuracy of the proposed automatic quantitative evaluation method is always higher than 90 and the minimum error of text feature extraction is about 2%.
Keywords: multi-feature fusion; English writing; automatic assessment; corpus.
Authentic learning environment for in-service trainings of cyber security: a qualitative study
by Mika Karjalainen, Anna-Liisa Ojala
Abstract: Todays rapidly digitalising world has led to business processes becoming digitalised, which necessitates paying attention to the cybersecurity issues inherent in those digital processes. The multi-disciplinary nature of working life and the complexity of cybersecurity issues place demands on learning environments. The present study examined the requirements for optimal in-service training to ensure individual and organisational learning of the competencies that are crucial for dealing with cybersecurity incidents. Building on theories of authentic learning and qualitative research methods, the study identified three fundamental components and four elements of optimal in-service cybersecurity training. The research found that practicing organisational actions increased readiness and competence to act in the face of a real cybersecurity incident. A comprehensive cyber arena supports the implementation of optimal training and thus the efficiency of in-service training.
Keywords: cyber security; cyber arena; cyber range; authentic learning environment; training; exercises; peadagogy; in-service training.
Teaching Practice-oriented Computer Vision Courses in COVID-19 Pandemic
by Jing Tian
Abstract: This paper aims to present an online teaching pedagogic experience for the practice-oriented computer vision course during the COVID-19 pandemic. COVID-19 has been disruptive to the education system worldwide, particularly to the computer vision course that usually requires face-to-face lectures and project collaboration during the study. This paper addresses three fundamental questions in teaching computer vision courses: 1) how to design the course topic and adapt to the online teaching format?; 2) how to conduct hybrid project collaboration in a hybrid mode?; 3) how to conduct the course assessment efficiently online? More specifically, this paper presents the pedagogic experience, including learning objectives, course curriculum structure, teaching methodologies, as well as final holistic assessments. The presented approach is an effective way of teaching practical computer vision courses, as verified by feedback from students. These experiences can be insightful to other lecturers who need to design, develop and deliver similar courses in the post pandemic era.
Keywords: engineering education; computer vision teaching; active learning.
Recommended methods for teaching resources in public English MOOC based on data chunking
by Zhenhua Wei
Abstract: In order to overcome the problems of time-consuming and high recommendation error in traditional public English MOOC teaching resource recommendation methods, this paper proposes a new public English MOOC teaching resource recommendation method based on data partition. The data of public English MOOC teaching resources are collected, and hierarchical clustering algorithm is used to preprocess public English MOOC teaching resources to support the recommendation demand of mobile MOOC teaching resources. According to the preprocessing results, the data block algorithm is used to divide the resource data iteratively. Finally, we calculate the similarity of users resource use and preference, and construct the public English MOOC teaching resource recommendation model based on the index weight results. Comparative validation results show, in the conventional method, the proposed method recommended consuming less and less precision compared to the recommended.
Keywords: data partition; public English; MOOC teaching resources; block partition.
An Evaluation Method of English Online Learning Behavior Based on Feature Mining
by Chao Han
Abstract: In order to overcome the problems of low precision of feature retrieval and poor clustering effect of traditional online learning behaviour evaluation methods, this paper designed an English online learning behaviour evaluation method based on feature mining. Firstly, the unbiased estimation theory is used to quantitatively sample English online learning behaviour. After data preprocessing, the clustering centre is divided, and the data is allocated to different clusters through clustering processing, and the feature mining results are obtained through iteration. Then the evaluation index system is constructed, and the final evaluation results are obtained on the basis of the grey interval clustering treatment of the evaluation index. According to the test results, the retrieval accuracy of behaviour features of method of this paper is closer to one, and its clustering effect on different online learning behaviour features is good, which proves that it has achieved the design expectation.
Keywords: online learning behaviour; data clustering; characteristics of the mining; evaluation indicators.
Personalized recommendation method of college English online teaching resources based on hidden Markov model
by Qing Tian
Abstract: Aiming at the problem of the high comprehensive evaluation index of recall and precision in the traditional personalised recommendation methods of college English online teaching resources, a personalised recommendation method of college English online teaching resources based on hidden Markov model is proposed. Extract label features, student learning behaviour features, and time weight features, and pre-process the extracted college English online teaching resource data, build a recommendation model based on the pre-processing results, and use a hidden Markov model to process the hidden data to obtain the maximum likelihood estimates the parameter, and inputs the parameter into the recommendation model to obtain the optimal parameter, that is, the optimal recommendation result. The simulation results show that the comprehensive evaluation index values of precision and recall of the recommended results of the proposed method are within 0.9 and 0.5, which has a good recommendation effect and meets the needs of the development of network teaching.
Keywords: hidden Markov model; university English; online teaching resources; personalised recommendation method.
Interactive design method of English online learning interface based on visual perception
by Shenglan Wang
Abstract: Due to the problems of long interaction time, poor data recovery effect and poor satisfaction of the existing interactive design methods of English online learning interface, an interactive design method of English online learning interface based on visual perception is proposed. Based on the principle of visual perception, this paper optimises the interface structure, enhances the data interactive processing ability of this method by using the interactive interface engine technology, improves the data recovery rate by combining with the data weight design, and realises the interactive design requirements of English online learning interface. Experimental results: the interaction time of the design method is generally less than 1.5s, the data recovery rate is generally more than 80%, and the teaching satisfaction is more than 90%, which shows that the method has good interaction, high information recovery rate, high satisfaction and strong practicability in the practical application process.
Keywords: visual perception; English online learning; interactive interface; engine technology.
Research on College Students' Emotional Experience in Online Learning
by Lifeng Wang, Zi Ye, Shaotong Zhu
Abstract: Online education is the main form of pedagogy during the COVID-19 pandemic. The description and analysis of the emotional experience of online education for college students are of considerable significance. This paper surveyed and investigated the online learning experience of 1,147 college students during the pandemic. Moreover, their experience of offline and online learning was analysed. The results demonstrate that college students prefer face-to-face learning. Online learning produces more negative emotions, whereas face-to-face learning induces more positive emotions; academic situation, self-management, learning atmosphere, interpersonal relationship, self-expression, collective honour are the leading causes of students emotions.
Keywords: face-to-face learning; online learning; emotional experience.
EXPLORATION OF GENDER SPECIFIC AND LEARNING ENVIRONMENT SPECIFIC COMFORT LEVEL IN COLLABORATIVE LEARNING
by Anitha D. Dhakshina Moorthy, Purnima Ahirao, Ramaa AnanthaMurthy, Vrinda Ullas
Abstract: Collaborative learning creates interest and engagement in learning. The collaborative learning activities can be conducted in one of the three learning environments or modes: face-to-face, completely online and blended mode and with different gender compositions. It is essential to understand the comfort level of students when working in different gender compositions and different learning environments. Hence, this research study is carried out with different group compositions in three different learning environments of collaborative learning: online, blended and face-to-face. One hundred seventy students from four educational institutions in India participated in this study. A survey is administered to them on the various parameters of comfortable learning. From the results obtained, it is observed that online or blended learning results in an increased comfort level of students than face-to-face learning sessions and the gender composition affects the comfort level.
Keywords: collaborative learning; learning environments; gender; comfort; team formation.
The method of online classroom teaching quality evaluation based on deep data mining
by Jing Hou
Abstract: In order to overcome the problems of traditional online classroom teaching quality evaluation methods, such as low accuracy of quality evaluation and poor effect of classroom teaching quality improvement, this paper proposes an online classroom teaching quality evaluation method based on deep data mining. Fuzzy comprehensive evaluation method is used to quantify the evaluation index of online classroom teaching quality; The evaluation matrix is constructed to calculate the weight of classroom teaching quality evaluation index; The online classroom teaching quality evaluation indicators are classified by naive Bayes classification algorithm; With the help of deep data mining algorithm, this paper evaluates the post classification evaluation index, constructs the online classroom teaching quality evaluation model, and completes the online classroom teaching quality evaluation. The experimental results show that the accuracy of the proposed method is about 0.9, and it can effectively improve the quality of online classroom teaching.
Keywords: Deep data mining; Classifier; Naive Bayes classification algorithm; Evaluation matrix.
Corpus-driven recommendation algorithm for English online autonomous learning resources
by Chao Han
Abstract: In order to overcome the problems of the traditional recommendation algorithm of English online learning resources, such as low accuracy, poor convergence and low success rate of recommendation. This paper proposes a recommendation algorithm for online language autonomous learning resources driven by CORUS. Based on the learning vector quantisation (LQN) algorithm, the model of subject word generation based on vector corpus resources is established. In the parameter training of the classification model, the vector weight is normalised to complete the optimisation of the corpus resource classification LVQ subject model. According to the binary particle swarm optimisation algorithm, the personalised recommendation model of autonomous learning resources is implemented. Experimental results show that the proposed vector quantisation network algorithm has high convergence, and the recommended success rate is 99.5%. Therefore, the method proposed in this paper can effectively complete the recommendation of English online autonomous learning resources.
Keywords: corpus; English learning; learning resources; recommendation algorithm; binary particle swarm.
An English listening and speaking ability training system based on binary decision tree
by Yu Wang
Abstract: In order to solve the problems of low speech resolution accuracy and poor auxiliary training effect of traditional auxiliary training system, a design method of English listening and speaking ability auxiliary training system based on binary decision tree is proposed. The hardware design includes English listening and speaking data extraction module, storage module and training module. In terms of software, the binary decision tree algorithm is used to construct the binary decision tree training model of English listening and speaking training. Through the algorithm, the data information of English learners in the process of listening and speaking ability training is extracted and the training data is evaluated. The experimental results show that: this system has high accuracy in the discrimination and evaluation of English speech data, and low occupancy rate of system storage space, which is conducive to improving students English listening and speaking ability and English learning achievement.
Keywords: binary decision tree; data extraction module; storage module; ability training module; effect evaluation.
A personalized recommendation of mobile learning model based on content awareness
by Yuanyuan Luo
Abstract: In order to overcome the problems of traditional recommendation methods such as large error in recommendation results and long time-consuming process of recommendation results generation, the paper proposes a personalised recommendation method based on content-aware mobile learning mode. First, design the recommendation process architecture, which mainly includes a user demand analysis module, a user preference analysis module, and a mobile learning model resource library decision module. Then, use the energy function and insert the dataset to design the content perception process. Finally, according to the perceptual results, a user emotional topic model with a supervision mechanism is used to complete personalised recommendation. The experimental results show that the average absolute error value of the recommendation results obtained by the method in this paper is between 0.060.15, the maximum recommendation result generation process takes only 4.5s, and the clustering effect of different mobile learning modes is better.
Keywords: mobile learning model; personalised recommendation; recommender process architecture; energy function; content awareness; affective thematic model.
Effect of personal response systems on students' academic performance and perception in online teaching
by Hongjiang Wang, Zuokun Li, Xiaojin Wang
Abstract: To minimise the negative impact of the epidemic on education, online teaching was taking off all over the world. In order to improve the interactive effect of online teaching, some scholars have applied personal response systems (PRSs) during the online teaching process. However, there is few experimental studies to validate the effectiveness of PRSs, such as students performance and perceptions. In the paper, based on the quantitative and qualitative mixed analysis method, which is the best way to gain information of specific experience, 98 sophomores majoring in Applied Mathematics are sampled to test students academic performance and perception in online teaching using PRSs, e.g., UMU. Some conclusions can be drawn: 1) the experimental groups academic performance was higher than the control group; however, there was no significant difference between them; 2) majority of students have positive perceptions, such as learning motivation (LM), learning engagement (LE) and learning satisfaction (LS) towards PRSs. And there was no significant difference in gender perception. At last, the paper concluded the advantages, disadvantages and suggestions of PRSs used in online teaching. The limitation of research and the direction of future research are discussed.
Keywords: personal response systems; PRSs; academic performance; perception; online teaching.
Investigating the Effect of Online Teaching using a SPOC
by Hongtao Yu
Abstract: The outbreak of COVID-19 in 2019 brought about unprecedented changes to higher education. Following the deployment of the Education Ministry, Chinese higher learning institutions carried out practical activities in response to the classes suspended but learning continues appeal by making use of internet technologies. In order to understand the effect of online teaching, this research uses qualitative research methods to study online learning of students in a certain university, and selects four case classes with different learning abilities. After conducting a comparative analysis of final exam scores, student questionnaire surveys and interviews, analysis of the effectiveness of students online learning of the course, the results show that students online learning performance is positively correlated with the scores of the preceding courses, and the online learning duration is positively correlated. Online learning is more suitable for students with strong self-discipline and three suggestions are given for effective teaching in the future.
Keywords: SPOC; online learning; empirical research.
Special Issue on: Critical Issues in Educational Technology
The development technology of MOOC teaching resources based on web crawler
by Tian Hui-Xia
Abstract: In order to improve the quality of MOOC teaching resource services, this article proposes to introduce educational big data into MOOC teaching resource development model research. Web crawlers are used to collect MOOC-related teaching data resources, analyse the acquired resources, and structure the content information, and then classify and save the data in the MySQL database. Based on the MOOC educational big data of web crawlers, an integrated development service platform for MOOC teaching resources was designed and constructed. Mainly designed and analysed the overall structure, function modules, database and main module operation program of the teaching resource development platform resource library. The operation program of the resource library mainly includes online teaching, online learning and online teaching resources. It can be seen from the experiment that the function operation result of the MOOC teaching resource integrated development service platform is the same as the expected result, which is feasible.
Keywords: web crawler; education big data; MOOC teaching resources; development mode.
Special Issue on: Technology and Innovation Management in Education
Study on abnormal behavior recognition of MOOC online English learning based on multidimensional data mining
by Fengxiang Zhang, Feifei Wang
Abstract: In order to overcome the problems of low recognition accuracy and long recognition time of traditional English learning abnormal behaviour recognition methods, this paper proposes MOOC online English learning abnormal behaviour recognition method based on multidimensional data mining. Firstly, set up the multi-dimensional association item set of MOOC online English learning behaviour, mine the learning behaviour data for correction. Secondly, students MOOC online English learning behaviour characteristics are extracted from students target contour and blinking behaviour characteristics. Then, taking this as the training sample subset, the individual member classifier is constructed by the mixed perturbation method to classify the learning behaviour. Finally, the abnormal behaviour identification of MOOC online English learning is completed. The experimental results show that the proposed method has high accuracy and short recognition time.
Keywords: multidimensional data mining; MOOC online English learning; abnormal behaviour; mixed perturbation method; individual member classifier.