scholarly journals Predicting Students' Attention Level with Interpretable Facial and Head Dynamic Features in an Online Tutoring System (Student Abstract)

2020 ◽  
Vol 34 (10) ◽  
pp. 13895-13896 ◽  
Author(s):  
Shimeng Peng ◽  
Lujie Chen ◽  
Chufan Gao ◽  
Richard Jiarui Tong
Keyword(s):  
Mean Squared Error ◽  
Video Recording ◽  
Vital Role ◽  
Dynamic Features ◽  
Learning Context ◽  
Tutoring System ◽  
Consensus Definition ◽  
Online Tutoring ◽  
Mouth Movement ◽  
Synchronized Measurements

Engaged learners are effective learners. Even though it is widely recognized that engagement plays a vital role in learning effectiveness, engagement remains to be an elusive psychological construct that is yet to find a consensus definition and reliable measurement. In this study, we attempted to discover the plausible operational definitions of engagement within an online learning context. We achieved this goal by first deriving a set of interpretable features on dynamics of eyes, head and mouth movement from facial landmarks extractions of video recording when students interacting with an online tutoring system. We then assessed their predicative value for engagement which was approximated by synchronized measurements from commercial EEG brainwave headset worn by students. Our preliminary results show that those features reduce root mean-squared error by 29% compared with default predictor and we found that the random forest model performs better than a linear regressor.

scholarly journals Prediction of Confusion Attempting Algebra Homework in an Intelligent Tutoring System through Machine Learning Techniques for Educational Sustainable Development

2018 ◽  
Vol 11 (1) ◽  
pp. 105 ◽  
Author(s):  
Syed Abidi ◽  
Mushtaq Hussain ◽  
Yonglin Xu ◽  
Wu Zhang
Keyword(s):  
Machine Learning ◽  
Sustainable Development ◽  
Teaching And Learning ◽  
Performance Metrics ◽  
Intelligent Tutoring ◽  
Intelligent Tutoring System ◽  
Vital Role ◽  
Machine Learning Techniques ◽  
Tutoring System ◽  
Learning Techniques

Incorporating substantial, sustainable development issues into teaching and learning is the ultimate task of Education for Sustainable Development (ESD). The purpose of our study was to identify the confused students who had failed to master the skill(s) given by the tutors as homework using the Intelligent Tutoring System (ITS). We have focused ASSISTments, an ITS in this study, and scrutinized the skill-builder data using machine learning techniques and methods. We used seven candidate models including: Naïve Bayes (NB), Generalized Linear Model (GLM), Logistic Regression (LR), Deep Learning (DL), Decision Tree (DT), Random Forest (RF), and Gradient Boosted Trees (XGBoost). We trained, validated, and tested learning algorithms, performed stratified cross-validation, and measured the performance of the models through various performance metrics, i.e., ROC (Receiver Operating Characteristic), Accuracy, Precision, Recall, F-Measure, Sensitivity, and Specificity. We found RF, GLM, XGBoost, and DL were high accuracy-achieving classifiers. However, other perceptions such as detecting unexplored features that might be related to the forecasting of outputs can also boost the accuracy of the prediction model. Through machine learning methods, we identified the group of students that were confused when attempting the homework exercise, to help foster their knowledge and talent to play a vital role in environmental development.

4MALITY: Coaching Students with Different Problem-Solving Strategies Using an Online Tutoring System

2011 ◽  
pp. 359-364
Author(s):  
Leena Razzaq ◽  
Robert W. Maloy ◽  
Sharon Edwards ◽  
David Marshall ◽  
Ivon Arroyo ◽  
...  
Keyword(s):  
Problem Solving ◽  
Tutoring System ◽  
Online Tutoring ◽  
Problem Solving Strategies

scholarly journals SEMIOTICS ANALYSIS OF RUANGGURU ADVERTISING IN TELEVISION MEDIA

2020 ◽  
Vol 5 (2) ◽  
pp. 104
Author(s):  
Al Mutia Gandhi
Keyword(s):  
Research Method ◽  
Video Recording ◽  
Blue Color ◽  
Data Resource ◽  
New School ◽  
Online Tutoring ◽  
Descriptive Approach ◽  
Television Media ◽  
Practice Questions ◽  
Academic Year

RuangGuru is one of the most successful startups in Indonesia, which is engaged in online tutoring. The application user has reached up to 15 million students. This achievement is the result of the advertisements that often appear on television media, especially during new school academic year or new semester. This study examines advertisements on television media less than 30 seconds to attract customers. This study uses semiotic to analyze television ads for the product. The research method uses an interpretive descriptive approach to analyze the signs used in advertisements. The data resource is four video recording advertisements on television media. The analysis starts with transcription and making video screenshots to sharpen the analysis. The results indicate that to attract television viewers, RuangGuru uses signs that indicate superior features. The features such as animated learning videos, practice questions, discussion, and ease of learning through applications. The celebrity figures in the advertisement represent students and parents who will later become consumers of RuangGuru. The ad also has a sign indicating how easy it is to pay and how cheap it is to subscribe to the Ruang Guru application compared to conventional tutoring. The blue color, which is the dominance of advertisements, shows that the RuangGuru app is trustworthy and can increase students' confidence in facing classroom learning.

scholarly journals Modified Liu estimators in the linear regression model: An application to Tobacco data

PLoS ONE ◽  
2021 ◽  
Vol 16 (11) ◽  
pp. e0259991
Author(s):  
Iqra Babar ◽  
Hamdi Ayed ◽  
Sohail Chand ◽  
Muhammad Suhail ◽  
Yousaf Ali Khan ◽  
...  
Keyword(s):  
Linear Regression ◽  
Mean Squared Error ◽  
Prediction Interval ◽  
Evaluation Criteria ◽  
Absolute Error ◽  
Vital Role ◽  
Predictor Variables ◽  
Linear Regression Models ◽  
Squared Error ◽  
Optimal Value

Background The problem of multicollinearity in multiple linear regression models arises when the predictor variables are correlated among each other. The variance of the ordinary least squared estimator become unstable in such situation. In order to mitigate the problem of multicollinearity, Liu regression is widely used as a biased method of estimation with shrinkage parameter ‘d’. The optimal value of shrinkage parameter plays a vital role in bias-variance trade-off. Limitation Several estimators are available in literature for the estimation of shrinkage parameter. But the existing estimators do not perform well in terms of smaller mean squared error when the problem of multicollinearity is high or severe. Methodology In this paper, some new estimators for the shrinkage parameter are proposed. The proposed estimators are the class of estimators that are based on quantile of the regression coefficients. The performance of the new estimators is compared with the existing estimators through Monte Carlo simulation. Mean squared error and mean absolute error is considered as evaluation criteria of the estimators. Tobacco dataset is used as an application to illustrate the benefits of the new estimators and support the simulation results. Findings The new estimators outperform the existing estimators in most of the considered scenarios including high and severe cases of multicollinearity. 95% mean prediction interval of all the estimators is also computed for the Tobacco data. The new estimators give the best mean prediction interval among all other estimators. The implications of the findings We recommend the use of new estimators to practitioners when the problem of high to severe multicollinearity exists among the predictor variables.

scholarly journals A model to identify mathematics topics in MXit lingo to provide tutors quick access to supporting documentation

Pythagoras ◽  
2011 ◽  
Vol 32 (2) ◽  
Author(s):  
Laurie Butgereit ◽  
Reinhardt A. Botha
Keyword(s):  
University Students ◽  
Mobile Phones ◽  
School Curriculum ◽  
Tutoring System ◽  
Online Tutoring ◽  
Mathematics Homework ◽  
Volunteer Tutors ◽  
To Receive

Dr MathTM is a mobile, online tutoring system where learners can use MXitTM on their mobile phones to receive help with their mathematics homework from volunteer tutors. These conversations between learners and Dr Math are held in MXit lingo. MXit lingo is a heavily abbreviated, English-like language that is evolving between users of mobile phones that communicate using MXit. The Dr Math project has been running since January 2007 and uses volunteer tutors who are mostly university students who readily understand and use MXit lingo. However, due to the large number of simultaneous conversations that the tutors are often involved in and the diversity of topics discussed, it would often be beneficial to provide assistance regarding the mathematics topic to the tutors. This article explains how the μ model identifies the mathematics topic in the conversation. The model identifies appropriate mathematics topics in just over 75% of conversations in a corpus of conversations identified to be about mathematics topics in the school curriculum.

scholarly journals ‘I knew that you were there, so I was talking to you’: the use of screen-recording videos in online language learning research

2019 ◽  
pp. 146879411988504 ◽  
Author(s):  
Wing Yee Jenifer Ho
Keyword(s):  
Data Collection ◽  
Language Learning ◽  
Language Learners ◽  
Video Recording ◽  
Data Collection Tool ◽  
Learning Context ◽  
New Approach ◽  
Online Language Learning ◽  
Learning Research ◽  
Mobile Methods

As language learning has become increasingly globalised, mobile and online, instances of language learning of significant value cannot be obtained by using conventional means such as on-site observation or video recording in classrooms. In this article, I present a new approach to collecting data in the online language learning context with an aim to capture the multimodal and embodied nature of language learning. Screen-recording as a research tool is an under-explored area; this article discusses some methodological and practical issues that researchers would encounter when using this approach, and outlines the considerations researchers need to make when collecting data in such kind of contexts. The article argues that screen-recording is an innovative data collection tool in the research of language learning, and it should be included in the repertoire of mobile methods to study (im)mobilities of language learners, teachers and knowledge.

Sign in / Sign up

Export Citation Format

Share Document