MOOC Data Research Articles

Solving the imbalanced data issue: automatic urgency detection for instructor assistance in MOOC discussion forums

In MOOCs, identifying urgent comments on discussion forums is an ongoing challenge. Whilst urgent comments require immediate reactions from instructors, to improve interaction with their learners, and potentially reducing drop-out rates—the task is difficult, as truly urgent comments are rare. From a data analytics perspective, this represents a highly unbalanced (sparse) dataset. Here, we aim to automate the urgent comments identification process, based on fine-grained learner modelling—to be used for automatic recommendations to instructors. To showcase and compare these models, we apply them to the first gold standard dataset for Urgent iNstructor InTErvention (UNITE), which we created by labelling FutureLearn MOOC data. We implement both benchmark shallow classifiers and deep learning. Importantly, we not only compare, for the first time for the unbalanced problem, several data balancing techniques, comprising text augmentation, text augmentation with undersampling, and undersampling, but also propose several new pipelines for combining different augmenters for text augmentation. Results show that models with undersampling can predict most urgent cases; and 3X augmentation + undersampling usually attains the best performance. We additionally validate the best models via a generic benchmark dataset (Stanford). As a case study, we showcase how the naïve Bayes with count vector can adaptively support instructors in answering learner questions/comments, potentially saving time or increasing efficiency in supporting learners. Finally, we show that the errors from the classifier mirrors the disagreements between annotators. Thus, our proposed algorithms perform at least as well as a ‘super-diligent’ human instructor (with the time to consider all comments).

Design of Embedded Knowledge Service Interactive System in University Library Based on MOOC Data Stream Retrieval

In view of this, the idea of applying knowledge graph to MOOC platform resource retrieval is proposed, and a knowledge graph oriented to MOOC data is constructed through entity recognition, relationship analysis, course knowledge point discovery and other methods, and applied to data stream retrieval on embedded devices The system architecture; improved the storage and retrieval efficiency during clustering; designed a clustering algorithm that can capture the temporal characteristics of the skewed distribution of data in a real-time or asynchronous manner. From the fields of scientific research, teaching and social science, a more comprehensive and analyzed the knowledge transfer service from the service process. Finally, it puts forward the embedded knowledge transfer service strategy of university library for the collaborative innovation of industry, university and research.

Ecological Construction of Distance Education Learning Behavior Analysis Model Based on MOOC Data

Ecological Construction of Distance Education Learning Behavior Analysis Model Based on MOOC Data

The Recommendation System of Innovation and Entrepreneurship Education Resources in Universities Based on Improved Collaborative Filtering Model.

In the huge number of online university education resources, it is difficult for learners to quickly locate the resources they need, which leads to “information trek.” Traditional information recommendation methods tend to ignore the characteristics of learners, who are the main subjects of education. In order to improve the recommendation accuracy, a recommendation algorithm based on improved collaborative filtering model is proposed in this paper. Firstly, according to the student behavior data, consider the behavior order to create the behavior graph and behavior route. Then, the path of text type is vectorized by the Keras Tokenizer method. Finally, the similarity between multidimensional behavior path vectors is calculated, and path collaborative filtering recommendations are performed for each dimension separately. The MOOC data of a university in China are introduced to experimentally compare the algorithm of the article as well as the control group algorithm. The results show that the proposed algorithm takes better values in evaluation indexes, thus verifying that this algorithm can improve the effectiveness of innovation and entrepreneurship education resources recommendation in universities.

Allocation of multi-dimensional distance learning resource based on MOOC data

In order to overcome the problems of allocation balance and low allocation efficiency in traditional distance teaching resource allocation methods, the paper proposes a multi-dimensional distance learning resource allocation method based on MOOC data. This method establishes a network model of MOOC resources, analyses the structure of the MOOC remote teaching platform, and collects MOOC data and learning resource information in layers on the basis of the model. Based on the data collection results, clustering of data resources can be achieved from multiple dimensions. Finally, by calculating the allocation of learning resources, a balanced allocation of multi-dimensional distance learning resources is achieved. Experimental results show that, compared with the traditional learning resource allocation method, the proposed method has a maximum allocation balance of 93% and a resource allocation efficiency of 96.2%.

Allocation of multi-dimensional distance learning resource based on MOOC data

Allocation of multi-dimensional distance learning resource based on MOOC data

A Proportional Sentiment Analysis of MOOCs Course Reviews Using Supervised Learning Algorithms

When anyone is looking to enroll for a freely available online course so the first and famous name comes in front of the searcher is MOOC courses. So here in this article our focus is to collect the comments by enrolled users for the specified MOOC course and apply sentiment analysis over that data. The significance of our article is to introduce a proficient sentiment analysis algorithm with high perceptive execution in MOOC courses, by seeking after the standards of gathering various supervised learning methods where the performance of various supervised machine learning algorithms in performing sentiment analysis of MOOC data. Some research questions have been addressed on sentiment analysis of MOOC data. For the assessment task, we have investigated a large no of MOOC courses, with the different Supervised Learning methods and calculated accuracy of the data by using parameters such as Precision, Recall and F1 Score. From the results we can conclude that when the bigram model was applied to the logistic regression, the Multilayer Perceptron (MLP) overcomes the accuracy by other algorithms as SVM, Naive Bayes and achieved an accuracy of 92.44 percent. To determine the sentiment polarity of a sentence, the suggested method use term frequency (No of Positive, Negative terms in the text) to calculate the sentiment polarity of the text. We use a logistic regression Function to predict the sentiment classification accuracy of positive and negative comments from the data.

Modified Associative Algorithm to Determine Frequent Pattern from Student Dataset

The phenomenal advances in Students produces huge amount of data like MOOC data and high throughput information that makes Electronic Student records (ESRs) expensive and complex. For the analysis of such a huge amount of data, AI and data mining techniques have been utilized along with Student services. Today, Data mining is utilized to detect performances using various informational datasets along with machine learning algorithms. There are many techniques available which are utilized for diagnosis of student performance like FP growth, Apriori and Associative algorithm etc. These techniques discover unknown patterns or relationships from large amount of data and these are utilized for making decisions for preventive and suggestive medicine. The main disadvantage of these techniques is it discovers fewer patterns. In this paper we proposed modified associative algorithm that discovers patterns to detect performance accurately. The results will help in predicting the performance quicker and more accurately, so that it leads to timely aware the students.

Adaptive recommendation for MOOC with collaborative filtering and time series

AbstractMassive Open Online Course (MOOC) has developed rapidly in recent years. However, the low satisfaction and the feelings of loneliness tend to cause more dropouts. A solution called Adaptive Recommendation for MOOC (ARM) is proposed aiming at the problem. Traditional MOOC recommendations are usually on the feature of interest. Among the recorded MOOC data, new recommendation features are selected for better balance on satisfaction. ARM trades off features adaptively according to the learner's requirement of satisfaction. Collaborative Filtering provides explicit information of similar learners and supports Collaborative Learning for less loneliness. ARM creatively combines Collaborative Filtering and time series to improve the recommendation accuracy. Specifically, Hawkes point process is improved to model the motivate and demotivate effect of score for future learning. Experiments with real‐world data show the accuracy of the ARM in recommendations and improvements in the dropout rate.

MOOC Teaching Mode of News Transmission Based on Network Audio Data Decoding Technology

MOOC, an online classroom development mode, has gradually developed due to its unique advantages under the background of big data. However, most online audio data of MOOC are acquired through the application software on PCs, which has limitations in the support of audio format. In the meanwhile, there are still some shortcomings in the existing research on the application and integration of the core technology of MOOC. Therefore, this study constructs the News Transmission MOOC course based on the network audio data decoding technology. Moreover, the course is applied to the actual teaching process to test the teaching effect and realize the organic integration of the core technology of computer and the teaching idea of MOOC. The practical teaching results show that the MOOC course not only improves the teaching effect, but also has significance and value for improving students’ ability and learning interest.

Toward the development of a dynamic dashboard for FutureLearn MOOCs

Open Online Courses (MOOCs). With the increase of available MOOC data, there is an opportunity tp provide insights to educators and developers into learners' behavior through learning analytics. Focusing on the FutureLearn platform (FL), standardized data files are offered to partner institutions. Additionally, a report is offered to stakeholders, but it is limited in a number of ways: it is static, it is limited in presenting relevant information and, most importantly, it does not provide 'real time' access to data. This paper provides an overview of the rationale and the development process of a dynamic and near real-time dashboard. It explores the viability of different types of visualizations with the available data, lessons learned, comparisons with similar efforts, and future directions are discussed.

Learning Behavior Analysis and Prediction Based on MOOC Data

Learning Behavior Analysis and Prediction Based on MOOC Data

From MOOCs to Learning Analytics: Scratching the surface of the 'visual'

The visualization of big MOOC data enables us to see trends in student behaviors and activities around the globe, but what is it that we are not seeing?