Filters








178 Hits in 6.7 sec

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

Anuj Kumar Singh, Sandeep Kumar, Shashi Bhushan, Pramod Kumar, Arun Vashishtha
2021 Ingénierie des Systèmes d'Information  
learning methods where the performance of various supervised machine learning algorithms in performing sentiment analysis of MOOC 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  ...  There are a number of researches on student reviews about courses, but none of them provide a comprehensive study from the standpoint of sentiment analysis.  ... 
doi:10.18280/isi.260510 fatcat:hnt7twuii5geloj2xmnbe3ms7i

A Bayesian CNN-LSTM Model for Sentiment Analysis in Massive Open Online Courses MOOCs

Khaoula Mrhar, Lamia Benhiba, Samir Bourekkache, Mounia Abik
2021 International Journal of Emerging Technologies in Learning (iJET)  
Massive Open Online Courses (MOOCs) are increasingly used by learn-ers to acquire knowledge and develop new skills.  ...  In this pa-per, we propose a novel approach to sentiment analysis that combines the advantages of the deep learning architectures CNN and LSTM.  ...  Experimentation and analysis The use of deep learning supervised approach in the sentiment analysis in MOOC has several limitations mainly the need of dataset for training.  ... 
doi:10.3991/ijet.v16i23.24457 fatcat:2rgghpj6avdbbnwsn6qb3yjezq

Evaluating On-line Courses via reviews mining

Cong Qi, Shudong Liu
2021 IEEE Access  
MOOC learners usually share some learning experiences and release millions of course-related comments in discussion forum.  ...  Thus, this paper constructs a curriculum evaluation system based on MOOC reviews, which quantifies the curriculum from different topics.  ...  [31] propose an efficient sentiment classification framework with a high predictive performance of MOOC reviews, which is based on conventional supervised learning methods, ensemble learning methods  ... 
doi:10.1109/access.2021.3062052 fatcat:e2v3cy75onc5fd5lz7pyjydv3y

Semantic Analysis of Learners' Emotional Tendencies on Online MOOC Education

Ling Wang, Gongliang Hu, Tiehua Zhou
2018 Sustainability  
In this paper, we present a semantic analysis model (SMA) to track the emotional tendencies of learners in order to analyze the acceptance of the courses based on big data from homework completion, comments  ...  In the experiments, we made a comprehensive evaluation of the students' overall learning status by kinds of learners and emotional tendencies.  ...  Conflicts of Interest: The authors declare that there is no conflict of interest regarding the publication of this paper.  ... 
doi:10.3390/su10061921 fatcat:6zrgta3jrfbafbr7tsoouiympe

Modeling and Analysis of Learners' Emotions and Behaviors Based on Online Forum Texts

Mingyong Li, Mingyuan Ge, Honggang Zhao, Ziye An, Ahmed Mostafa Khalil
2022 Computational Intelligence and Neuroscience  
Under the continuous impact of the epidemic, online learning methods represented by MOOC have developed rapidly.  ...  The course forum area has produced a large amount of text-based unstructured data, which can reflect the potential characteristics of learners' emotional states and behavioral interactions, and has an  ...  Recently, some researchers have proposed a parallel combination of CNN + LSTM network structure and self-attention mechanism for the MOOC course review sentiment classification task, so as to better retain  ... 
doi:10.1155/2022/9696422 pmid:35096051 pmcid:PMC8794649 fatcat:6gefu5cho5gwvej2t4xf75uaya

Co-Training Semi-Supervised Deep Learning for Sentiment Classification of MOOC Forum Posts

Jing Chen, Jun Feng, Xia Sun, Yang Liu
2019 Symmetry  
Sentiment classification of forum posts of massive open online courses is essential for educators to make interventions and for instructors to improve learning performance.  ...  Lacking monitoring on learners' sentiments may lead to high dropout rates of courses.  ...  J.F. supervised the research and helped J.C. at every step, especially framework building, analysis of the results, and writing of the manuscript.  ... 
doi:10.3390/sym12010008 fatcat:gl5t5w5smbcxlcybj6ecqf5uwy

Unsupervised and Supervised Methods to Estimate Temporal-Aware Contradictions in Online Course Reviews

Ismail Badache, Adrian-Gabriel Chifu, Sébastien Fournier
2022 Mathematics  
The analysis of user-generated content on the Internet has become increasingly popular for a wide variety of applications.  ...  This article aims to estimate the contradiction intensity (strength) in the context of online courses (MOOC).  ...  We studied the influence of the sentiment analysis algorithm on the results.  ... 
doi:10.3390/math10050809 fatcat:5xzmc3lgzfekvhxsc43thxb3vy

Analytical Framework for Binarized Response for Enhancing Knowledge Delivery System

Chethan G S, Vinay S
2021 International Journal of Advanced Computer Science and Applications  
BoW model is considered for features extraction, and two probabilistic supervised machine learning models are used for comment classification.  ...  Most of the existing works are limited to sentiment polarity computation only, and teacher evaluation is carried out without considering the aspects of the teaching.  ...  In this work, the authors considered various aspects of teaching and used supervised learningbased sentiment analysis using multi-layer LSTM.  ... 
doi:10.14569/ijacsa.2021.0121157 fatcat:kao6jofrpvdbflnf5xahfy6mby

Unsupervised Embedding for Latent Similarity by Modeling Heterogeneous MOOC Data [chapter]

Zhuoxuan Jiang, Shanshan Feng, Weizheng Chen, Guangtao Wang, Xiaoming Li
2017 Lecture Notes in Computer Science  
Recent years have witnessed the prosperity of Massive Open Online Courses (MOOCs).  ...  One important characteristic of MOOCs is that video clips and discussion forum are integrated into a one-stop learning setting.  ...  Results and Analysis As a ranking result, the measure metric we use is precision averaged by 10 times of runs.  ... 
doi:10.1007/978-3-319-57529-2_53 fatcat:yxxhjodwnrc3notb5jrh5bovm4

On the Effectiveness of Self-Training in MOOC Dropout Prediction

Yamini Goel, Rinkaj Goyal
2020 Open Computer Science  
In practice, however, scarcity of massive labelled data makes training difficult. Therefore, this study uses self-training, a semi-supervised learning model, to develop predictive models.  ...  An interplay between different learning analytics strategies and MOOCs have emerged as a research area to reduce dropout rate.  ...  Acknowledgement: We thank Rishabh Narang, MS Computer Science, Columbia University and Shristi Mudgal, MS Computer Science, Technical University of Munich for useful discussions.  ... 
doi:10.1515/comp-2020-0153 fatcat:smo4g32k4fgkvnadrh66c2tm6y

Predicting Learning Behavior Using Log Data in Blended Teaching

Shu-Tong Xie, Zong-Bao He, Qiong Chen, Rong-Xin Chen, Qing-Zhao Kong, Cun-Ying Song, Jiwei Huang
2021 Scientific Programming  
in a college's "Java Language Programming" course.  ...  In the article, we conducted a study on students' learning behavior analysis and student performance prediction based on the data about students' behavior logs in three consecutive years of blended teaching  ...  Acknowledgments is work was supported in part by the Natural Science Foundation of Fujian Province of China (nos. 2020J01697, Total score, attendance rate, Java data types, and reference types-courseware  ... 
doi:10.1155/2021/4327896 fatcat:hu6itan64vanpiamrga4x7pbuq

Deep Learning for Discussion-Based Cross-Domain Performance Prediction of MOOC Learners Grouped by Language on FutureLearn

Ismail Duru, Ayse Saliha Sunar, Su White, Banu Diri
2021 Arabian Journal for Science and Engineering  
Analysing extracted numeric features using baseline machine learning algorithms performed well to predict the learners' future performance in MOOCs.  ...  One of the deep learning architecture, Bidirectional LSTM, trained with discussions on the language learning 73% successfully predicted learners' performance on a different MOOC.  ...  The dataset used in this paper is provided by the University of Southampton for the ethically approved collaborative study (ID: 23593).  ... 
doi:10.1007/s13369-020-05117-x pmid:33425646 pmcid:PMC7786318 fatcat:ve3bf4vxwrcjhoi453n3uvo4ai

Predicting Student Outcomes in Online Courses Using Machine Learning Techniques: A Review

Areej Alhothali, Maram Albsisi, Hussein Assalahi, Tahani Aldosemani
2022 Sustainability  
This paper presents a comprehensive review of state-of-the-art studies that examine online learners' data to predict their outcomes using machine and deep learning techniques.  ...  extraction methodologies used to predict the outcomes, describe the metrics used for evaluation, provide a taxonomy to analyze related studies, and provide a summary of the challenges and limitations  ...  Conflicts of Interest: The authors declare no conflict of interest.  ... 
doi:10.3390/su14106199 fatcat:uprot74fkrclnlwelhlxeycjwa

A Review of the Trends and Challenges in Adopting Natural Language Processing Methods for Education Feedback Analysis

Thanveer Shaik, Xiaohui Tao, Yan Li, Christopher Dann, Jacquie McDonald, Petrea Redmond, Linda Galligan
2022 IEEE Access  
Machine learning, deep learning, and natural language processing (NLP) are subsets of AI to tackle different areas of data processing and modelling.  ...  Contextbased challenges in NLP like sarcasm, domain-specific language, ambiguity, and aspect-based sentiment analysis are explained with existing methodologies to overcome them.  ...  Li, formal analysis: T. Shaik and X. Tao, investigation: T. Shaik, X. Tao, Y.  ... 
doi:10.1109/access.2022.3177752 fatcat:fqc5337phndufia2lofgsg3bzi

A Comparative Analysis of Selected Studies in Student Performance Prediction

Michael Mogessie Ashenafi
2017 International Journal of Data Mining & Knowledge Management Process  
in non-traditional educational platforms to predict end-of-course performance and to those that show how student progress can be tracked in a continuous manner.  ...  A total of 56 studies published since the nineties are discussed. Views on strengths and weaknesses as well as observed opportunities for improvement are presented.  ...  students' social and study behaviour and academic performance ( [41] ) and those that perform Sentiment Analysis of discussion form posts in MOOCs ( [42] ).  ... 
doi:10.5121/ijdkp.2017.7402 fatcat:3ovbwwqv5fbohlnrgi4vufh4k4
« Previous Showing results 1 — 15 out of 178 results