Learner Behavior Research Articles

Adapt, Explain, Engage—A Study on How Social Robots Can Scaffold Second-language Learning of Children

Social robots are increasingly applied to support children’s learning, but how a robot can foster (or may hinder) learning is still not fully clear. One technique used by teachers is scaffolding, temporarily assisting learners to achieve new skills or levels of understanding they would not reach on their own. We ask if and how a social robot can be utilized to scaffold second-language learning of children at kindergarten age (4--7 years). Specifically, we explore an adapt-and-explain scaffolding strategy in which a robot acts as a peer-like tutor who dynamically adapts its behavior or the learning tasks to the cognitive and affective state of the child, and provides verbal explanations of these adaptations. An evaluation study with 40 children shows that children benefit from the learning adaptation and that the explanations have a positive effect especially for slower learners. Further, in 76% of all cases the robot managed to “re-engage” children who started to disengage from the learning interaction, helping them to achieve an overall higher learning gain. These findings demonstrate that a social robot equipped with suitable scaffolding mechanisms can increase engagement and learning, especially when being adaptive to the individual behavior and states of a child learner.

Predictors of cyberloafing among high school students: unauthorized access to school network, metacognitive awareness and smartphone addiction

Cyberloafing is one of the phenomena that adversely affects the efficiency and productivity in learning and teaching activities in educational settings. Increased ICT (information and communication technology) access status in educational environments and personal mobile devices lead to a wide range of cyberloafing behaviors of learners. In this regard, the aim of this study was to investigate cyberloafing behaviors of high school students in terms of several variables, including gender, ICT usage, unauthorized access to school network, metacognitive awareness and smartphone addiction. In this study, the relational screening model from descriptive research methods was used. A total of 269 9th grade students, 123 of whom were male and 146 of whom were female, were recruited. Hierarchical linear multilevel regression analysis was employed in the data analysis. The findings indicate that four of the five models designed to investigate cyberloafing behaviors in educational settings were found to be statistically significant. In other words, four hypotheses were supported. It has been concluded that the unauthorized access to the school network of learners has a significant impact on the cyberloafing behaviors in educational contexts. Additionally, the smartphone addiction and metacognitive awareness levels of students, as well as daily social media usage time are fundamental predictors of the cyberloafing behaviors.

A machine learning-based methodology to predict learners’ dropout, success or failure in MOOCs

Purpose Even if MOOCs (massive open online courses) are becoming a trend in distance learning, they suffer from a very high rate of learners’ dropout, and as a result, on average, only 10 per cent of enrolled learners manage to obtain their certificates of achievement. This paper aims to give tutors a clearer vision for an effective and personalized intervention as a solution to “retain” each type of learner at risk of dropping out. Design/methodology/approach This paper presents a methodology to provide predictions on learners’ behaviors. This work, which uses a Stanford data set, was divided into several phases, namely, a data extraction, an exploratory study and then a multivariate analysis to reduce dimensionality and to extract the most relevant features. The second step was the comparison between five machine learning algorithms. Finally, the authors used the principle of association rules to extract similarities between the behaviors of learners who dropped out from the MOOC. Findings The results of this work have given that deep learning ensures the best predictions in terms of accuracy, which is an average of 95.8 per cent, and is comparable to other measures such as precision, AUC, Recall and F1 score. Originality/value Many research studies have tried to tackle the MOOC dropout problem by proposing different dropout predictive models. In the same context, comes the present proposal with which the authors have tried to predict not only learners at a risk of dropping out of the MOOCs but also those who will succeed or fail.

A Computer-Vision Based Application for Student Behavior Monitoring in Classroom

Automated learning analytics is becoming an essential topic in the educational area, which needs effective systems to monitor the learning process and provides feedback to the teacher. Recent advances in visual sensors and computer vision methods enable automated monitoring of behavior and affective states of learners at different levels, from university to pre-school. The objective of this research was to build an automatic system that allowed the faculties to capture and make a summary of student behaviors in the classroom as a part of data acquisition for the decision making process. The system records the entire session and identifies when the students pay attention in the classroom, and then reports to the facilities. Our design and experiments show that our system is more flexible and more accurate than previously published work.

Dental Students' Intent to Practice in Rural Communities Before and After Community-Based Rotations in a Rural Area.

Community-based dental education (CBDE) has the potential to positively impact the educational process in a manner that both contributes to educational outcomes and shapes the learner's behavior. The aim of this study was to determine the correlation between dental students' intended practice location and the size of their hometown and to assess any impact their CBDE rotation in a rural location had on practice location intention. From March 7, 2016, to August 12, 2018, fourth-year students at one U.S. dental school were invited to complete a ten-item questionnaire prior to and after their four-week clinical rotations at a rural clinic. Of the 123 dental students on rotation at the clinic during this time, 106 completed the pre-rotation survey and 112 the post-rotation survey, for response rates of 86% and 91%, respectively. Prior to the rotation, 58.6% selected one of the rural locations as an ideal practice location, and that percentage increased slightly to 61.4% after the rotation; the difference was not statistically significant (p=0.984). The results did show a significant increase from pre to post rotation for women intending to practice in rural communities (p=0.0413). This study found that students' intent to practice in a rural location was not significantly affected by a clinical rotation in a rural clinic; however, there was strong evidence that students from rural communities intended to practice in rural communities after graduation.

THE COPING STRATEGIES APPLIED TOWARDS THE UNDESIRABLE BEHAVIORS OF EFL LEARNERS

The purpose of this study is to find out the strategies that EFL instructors apply to cope with undesirable behaviors of language learners at the tertiary level. The study was conducted with 20 EFL instructors working in the preparatory school at a university in 2017-2018 academic years. The data was gathered through a survey including 10 open-ended questions. Content analysis technique was used to assess the data. The results of the study reveal that EFL instructors apply 12 coping strategies towards the undesirable behaviors of language learners at tertiary level. The instructors use body language, verbal and facial expressions to warn their students. In addition, keeping silent, asking a question, finding out the reason of the undesirable behavior and the needs of the disruptive students, raising awareness, increasing motivation, talking in person, attracting attention, and ignoring the undesirable behavior are the other coping strategies .

A predictive model for the identification of learning styles in MOOC environments

Massive online open course (MOOC) platform generates a large amount of data, which provides many opportunities for studying the behaviors of learners. In parallel, recent advancements in machine learning techniques and big data analysis have created new opportunities for a better understanding of how learners behave and learn in environments known for their massiveness and openness. The work is about predicting learners’ learning styles based on their learning traces. The Felder Silverman learning style model (FSLSM) is adopted since it is one of the most commonly used models in technology-enhanced learning. In order to attend our objective, we analyzed data collected from the edX course “statistical learning” (session Winter 2015 and Winter 2016), administered via Stanford’s Logunita platform. The results show that decision tree performs best for all 3 dimensions, with an accuracy of higher than 98% and a reduced risk of overfitting the training data.

Neural Networks in the Educational Sector: Challenges and Opportunities

Abstract Given their increasing diffusion, deep learning networks have long been considered an important subject on which teaching efforts should be concentrated, to support a fast and effective training. In addition to that role, the availability of rich data coming from several sources underlines the potential of neural networks used as an analysis tool to identify critical aspects, plan upgrades and adjustments, and ultimately improve learning experience. Analysis and forecasting methods have been widely used in this context, allowing policy makers, managers and educators to make informed decisions. The capabilities of recurring neural networks—in particular Long Short-Term Memory networks—in the analysis of natural language have led to their use in measuring the similarity of educational materials. Massive Online Open Courses provide a rich variety of data about the learning behaviors of online learners. The analysis of learning paths provides insights related to the optimization of learning processes, as well as the prediction of outcomes and performance. Another active area of research concerns the recommendation of suitable personalized, adaptive, learning paths, based on varying sources, including even the tracing of eye-path movements. In this way, the transition from passive learning to active learning can be achieved. Challenges and opportunities in the application of neural networks in the educational sector are presented.

Analyzing Learners Behavior and Resources Effectiveness in a Distance Learning Course: A Case Study of the Hellenic Open University

Analyzing Learners Behavior and Resources Effectiveness in a Distance Learning Course: A Case Study of the Hellenic Open University

Technology Attributes Stimulating Learner Behaviors and Outcomes of Language Learning

Technology Attributes Stimulating Learner Behaviors and Outcomes of Language Learning

Promotion of learner autonomy within the framework of a flipped EFL instructional model: perception and perspectives

This study investigated the effects of the flipped classroom model on EFL learner autonomy in a content-based instructional context. The participants involved were students enrolled in two linguistics classes, divided into an experimental group (n = 64) which received a flipped classroom (FC) instruction and a control group (n = 60) taught in a non-flipped classroom. In the FC, various functions were embedded in a Moodle course management system (CMS), including video lectures, online quizzes, resources and e-journals. The comparison between the pre- and post-questionnaire on perceived learner autonomy showed no difference between the groups prior to instruction; however, significant statistical differences were found between the groups following instruction, especially in the constructs of learner autonomous strategy, learner behavior and learner confidence. The examination of e-journals revealed that learner autonomy had been improved in terms of strategy use, behavior, interaction with the materials, the use of social resources and self-management of learning. The CMS log analysis showed significant correlations between online learning activities and perceived learner autonomy. Furthermore, the data collected from the pre- and post-questionnaires, e-journal and interviews were analysed and interpreted to explain the fostered learner autonomy from psychological, technical, sociocultural and political–critical perspectives.

We Don’t Train in Vain: A Systematic Review and Meta-Analysis of Human and Canine Caregiver Training

ABSTRACT The present review assessed the current knowledge regarding caregiver- training effectiveness for human and human-canine dyads. Most canine-related sources (66%; n = 19) were case studies reporting a decrease of learner undesired behavior when using oral instruction (21%; n = 6). Most human-related research used single-case designs (57%; n = 26) reporting an increase in desired learner behavior (22%; n = 10) when caregivers received multi-component training packages (17%, n = 8). The meta-analysis (n = 18) revealed that interventions had a large effect (Hedges’ g = 0.88, 95%CI [0.68–1.07]), with packages yielding a slightly larger moderate effect (Hedges’ g = 0.76, 95%CI [0.60–0.91]) than oral instruction alone (Hedges’ g = 0.74, 95%CI [0.32–1,15]). Although the effectiveness of caregiver training is promising, the results should be interpreted cautiously. Due to the preponderance of case studies within canine literature and the insufficient reporting of data across sources, only few studies could be included in the meta-analysis. Overall, more systematic and comparative research regarding the efficacy of caregivers in behavior change programs across species is needed.

Predicting cognitive load in acquisition of programming abilities

In this paper, we propose a method to predict cognitive load and its factors affecting the learning efficiency in programming learning from the learning behavior of learners. Generally, since the concepts of programming are difficult for learners, some of them suffer inappropriate cognitive load to understand them. Although teachers must keep cognitive load of such learners appropriate, it is difficult for them to find learners who has inappropriate cognitive load from a large number of learners. To find learners with inappropriate cognitive load, we construct models with the random forest algorithm, using learning behavior collected from learners solving fill-in-the-blank tests. An experiment shows the models can detect cognitive load for IL and GL along with their factors. Teachers must address adjustment of cognitive load of learners. This result clarifies the learning factors affecting cognitive load of learners, which enables teachers to address the adjustment with small burdens.

Building pipelines for educational data using AI and multimodal analytics: A “grey‐box” approach

AbstractStudents' on‐task engagement during adaptive learning activities has a significant effect on their performance, and at the same time, how these activities influence students' behavior is reflected in their effort exertion. Capturing and explaining effortful (or effortless) behavior and aligning it with learning performance within contemporary adaptive learning environments, holds the promise to timely provide proactive and actionable feedback to students. Using sophisticated machine learning (ML) algorithms and rich learner data, facilitates inference‐making about several behavioral aspects (including effortful behavior) and about predicting learning performance, in any learning context. Researchers have been using ML methods in a “black‐box” approach, ie, as a tool where the input data is the learner data and the output is a given class from the chosen construct. This work proposes a methodological shift from the “black‐box” approach to a “grey‐box” approach that bridges the hypothesis/literature‐driven (feature extraction) “white‐box” approach with the computation/data‐driven (feature fusion) “black‐box” approach. This will allow us to utilize data features that are educationally and contextually meaningful. This paper aims to extend current methodological paradigms, and puts into practice the proposed approach in an adaptive self‐assessment case study taking advantage of new, cutting‐edge, interdisciplinary work on building pipelines for educational data, using innovative tools and techniques. Practitioner NotesWhat is already known about this topic Capturing and measuring learners' engagement and behavior using physiological data has been explored during the last years and exhibits great potential. Effortless behavioral patterns commonly exhibited by learners, such as “cheating,” “guessing” or “gaming the system” counterfeit the learning outcome. Multimodal data can accurately predict learning engagement, performance and processes. What this paper adds Generalizes a methodology for building machine learning pipelines for multimodal educational data, using a modularized approach, namely the “grey‐box” approach. Showcases that fusion of eye‐tracking, facial expressions and arousal data provide the best prediction of effort and performance in adaptive learning settings. Highlights the importance of fusing data from different channels to obtain the most suited combinations from the different multimodal data streams, to predict and explain effort and performance in terms of pervasiveness, mobility and ubiquity. Implications for practice and/or policy Learning analytics researchers shall be able to use an innovative methodological approach, namely the “grey‐box,” to build machine learning pipelines from multimodal data, taking advantage of artificial intelligence capabilities in any educational context. Learning design professionals shall have the opportunity to fuse specific features of the multimodal data to drive the interpretation of learning outcomes in terms of physiological learner states. The constraints from the educational contexts (eg, ubiquity, low‐cost) shall be catered using the modularized gray‐box approach, which can also be used with standalone data sources.

Research on the Difficulty Points Marking System of Online Learning Process

There exists a notable problem in MOOCs that teachers can’t find the difficulties during the learners’ learning process because of their inefficiency of supervising the learners’ real learning status. To solve this problem, we model the learning behavior of online learners based on facial expression information and mouse track data, and propose a method for marking learner’s difficulties in online learning process based on machine learning. At same time, we design and implement a prototype system for marking difficulties based on our method. Experiments show that our method can improve the efficiency and quality of marking learner’s difficulties effectively.

A System to Match Behaviors and Performance of Learners From User-Object Interactions

Intelligent environments in educational settings are aimed at supporting the learning process with an unobtrusive monitoring of the student while doing his/her activities. A desk is a common object in these settings, so if it is enhanced with sensing capabilities, it would enable gathering information of user-object interaction in a natural and unobtrusive way. An intelligent system is needed to analyze that information to reach conclusions faster than with traditional, manual observational process, and to provide timely valuable information. In this article, a design of a system to semi-automatically identify relationships between behaviors and the task performance of learners from user-object interaction logs is presented. The aim of detecting such relationships is to help teachers and students in the learning process, supporting their activities to identify special needs. Its components are designed to address four main functions: data acquisition, behavior identification, student performance identification, and computing relationships between student task performance and behaviors.

PENGEMBANGAN GERAKAN GO GREEN DI SEKOLAH DALAM MENINGKATKAN NASIONALISME (Studi Di SMP Negeri 2 Dawuan Kabupaten Subang)

Environmental problem sarieas a result of human activity itself, from time to time a threat to Increasing environmental damage. Society has not shown aware nessin maintaining and managing the real environment.Many various illegal logging, exploitation of natural resources, littering, waste management out of control, are the kinds of actions that pollute and damage the environment. Looking at this, it is important and urgent agenda to do is build a culture of Go Green in every spheres of life. Forthat purpose, the schoolas an educational institution, can bein seminated and rooting media values- based culture of clean living environment that is useful for individuasl and public life learners. Schools must develop order and social-pedagogical culture that is conducive to the growth of a variety of personal qualities loving environment. The findings of this study are: (1) the behavior of learners in the development of the Go Green movement can boost nationalism, (2) the existence of barriers and obstacles in the development and implementation of the Go Green at the school, (3) Go Green movement prospects to the school, community and environment. The study recommends to stakeholders SMPN 2 Dawuan Subang to reinforce the perception of the Go Green movement, and the creation of school cultures that manifest Go Green environmentally friendly school with discipline frame so that learner sincreased nationalism.

Applying and Evaluating Visualization Design Guidelines for a MOOC Dashboard to Facilitate Self-Regulated Learning Based on Learning Analytics

With the help of learning analytics, MOOCs have wider potential to succeed in learning through promoting self-regulated learning (SRL). The current study aims to apply and validate visualization design guidelines for a MOOC dashboard to enhance such SRL capabilities based on learning analytics. To achieve the research objective, a MOOC dashboard prototype, LM-Dashboard, was designed and developed, reflecting the visualization design guidelines to promote SRL. Then, both expert and learner participants evaluated LM-Dashboard through iterations to validate the visualization design guidelines and perceived SRL effectiveness. The results of expert and learner evaluations indicated that most of the visualization design guidelines on LM-Dashboard were valid and some perceived SRL aspects such as monitoring a student’s learning progress and assessing their achievements with time management were beneficial. However, some features on LM-Dashboard should be improved to enhance SRL aspects related to achieving their learning goals with persistence. The findings suggest that it is necessary to offer appropriate feedback or tips as well as to visualize learner behaviors and activities in an intuitive and efficient way for the successful cycle of SRL. Consequently, this study contributes to establishing a basis for the visual design of a MOOC dashboard for optimizing each learner’s SRL.

Beyond the Present Indicative: Lexical Futures as Indicators of Development in L2 Spanish

AbstractThe present study investigates to what extent first‐language (L1) and second‐language (L2) speakers use lexical futures, whether such forms provide evidence of development, and whether these forms are constrained differently from the present indicative (PI) according to linguistic predictors. It uses a combined approach through its concept‐oriented consideration of an underreported form and analysis of the behavior of individual learners, along with applying variationist methods to determine whether independent linguistic predictors differentiate between lexical futures and a formally similar structure (i.e., the PI). The study includes 120 English‐speaking learners of Spanish from 5 course levels and 20 native speakers (NSs) of Spanish. Participants completed an oral production task, in which they responded to 8 personal prompts. Results indicate that NSs used lexical futures robustly and that part of the development associated with the acquisition of future‐time expression included increases in the overall rates of lexical future use and the inventory of lexical future periphrases. Mixed‐effects models revealed that from the earliest level lexical futures could be differentiated from the PI as predicted by independent variables, and that independent variables patterned in a more target‐like way as course level increased.

Positive Behavior Supports in South Africa: Training Teachers to Implement a Systemic Strategy

Given that behavioral challenges contribute to learner exclusion in schools, there is a demand for behavior support strategies and practices that (a) extend beyond punitive measures, (b) aid the development of school customs and mores, (c) are based on nonviolence, and (d) promote positive self-discipline. This column explores behavior management practices in South African schools and emphasizes the value of teacher agency and enabling to support the argument that the outcomes of challenging learner behavior need not result in the exclusion of learners.