273 Hits in 5.4 sec

Incorporating Features Learned by an Enhanced Deep Knowledge Tracing Model for STEM/Non-STEM Job Prediction [article]

Chun-kit Yeung, Zizheng Lin, Kai Yang, Dit-yan Yeung
2018 arXiv   pre-print
To tackle this challenge, we first estimate the expected knowledge state of students with respect to different mathematical skills using a deep knowledge tracing (DKT) model and an enhanced DKT (DKT+)  ...  We then combine the features corresponding to the DKT/DKT+ expected knowledge state with other features extracted directly from the student profile in the dataset to train several machine learning models  ...  Question-and-answer interaction is the most common type of interaction in KT, and is usually represented as an ordered pair (qt, at) where qt is the question being answered at time t and at is the answer  ... 
arXiv:1806.03256v1 fatcat:jzl3gkz7bre43c2c6kfudp5ova

Tracking Changes in Students' Online Self-Regulated Learning Behaviors and Achievement Goals Using Trace Clustering and Process Mining

Michelle Taub, Allison M. Banzon, Tom Zhang, Zhongzhou Chen
2022 Frontiers in Psychology  
Students' SRL behavior was measured by analyzing their clickstream event traces interacting with online learning modules via a combination of trace clustering and process mining.  ...  This paper studies how students' SRL behavior and achievement goal orientation change over time in a large (N = 250) college introductory level physics course taught online.  ...  Leaning Systems and Technology team at the Center for Distributed Learning of University of Central Florida led by Francisca Yonekura, who developed the Obojobo learning objects platform for hosting the Online  ... 
doi:10.3389/fpsyg.2022.813514 pmid:35369254 pmcid:PMC8968150 fatcat:2du6qkzj6zephg7sskf5lpxuoi

What's happened in MOOC Posts Analysis, Knowledge Tracing and Peer Feedbacks? A Review [article]

Manikandan Ravikiran
2020 arXiv   pre-print
Learning Management Systems (LMS) and Educational Data Mining (EDM) are two important parts of online educational environment with the former being a centralised web-based information systems where the  ...  Notable works, on ASG, includes that of Zhang, Shah, and Chi (2016) which studied feature from the answer, questions, and student models, both individually and combined, integrating them in different machine  ...  Empirical Reviews: Following DKT, there were a series of works that focused on deeper analysis, questioning the results of Deep Knowledge Tracing (DKT).  ... 
arXiv:2001.09830v1 fatcat:fwxjsrusfncjjpv4vdrglm4s2m

System design for using multimodal trace data in modeling self-regulated learning

Elizabeth Brooke Cloude, Roger Azevedo, Philip H. Winne, Gautam Biswas, Eunice E. Jang
2022 Frontiers in Education  
., concurrent verbalizations, eye movements, on-line behavioral traces, facial expressions, screen recordings of learner-system interactions, and physiological sensors) to investigate triggers and temporal  ...  Our overall goals are to (a) advance the science of learning by creating links between multimodal trace data and theoretical models of SRL, and (b) aid researchers or instructors in developing effective  ...  Assuming these questions are answered, how can researchers be guided to make instructional decisions that support and enhance learners' SRL processes?  ... 
doi:10.3389/feduc.2022.928632 fatcat:rpgfc4zpxzdtdfbdvephijbp3q

What do Students' Interactions with Online Lecture Videos Reveal about their Learning?

Guojing Zhou, Tetsumichi Umada, Sidney D'Mello
2022 Proceedings of the 30th ACM Conference on User Modeling, Adaptation and Personalization  
We analyzed data from 10,492 students who used an online learning platform for their Algebra 1 course.  ...  network models to predict after-video quiz scores (N = 32,482) from the sequences in a student-independent fashion.  ...  Knowledge tracing research aims to model students' learning on specific knowledge components based on their responses to items (problems, assessments, questions).  ... 
doi:10.1145/3503252.3531315 fatcat:3whjph7dlnap3nvdpp7j4qjkzq

Time-series Insights into the Process of Passing or Failing Online University Courses using Neural-Induced Interpretable Student States [article]

Byungsoo Jeon, Eyal Shafran, Luke Breitfeller, Jason Levin, Carolyn P. Rose
2019 arXiv   pre-print
available in the records of students at large, online universities.  ...  We propose a time series model that constructs an evolving student state representation using both clickstream data and a signal extracted from the textual notes recorded by human mentors assigned to each  ...  With this in mind, we answer the question of how student state information may be extracted from mentor's notes through application of LDA to the notes.  ... 
arXiv:1905.00422v1 fatcat:p2ijvc32pndr5cqgqc4oz5svum

The Usefulness of Video Learning Analytics in Small Scale E-Learning Scenarios

César Córcoles, Germán Cobo, Ana-Elena Guerrero-Roldán
2021 Applied Sciences  
A variety of tools are available to collect, process and analyse learning data obtained from the clickstream generated by students watching learning resources in video format.  ...  We have developed a solution to collect clickstream analytics data applicable to smaller scenarios, much more common in primary, secondary and higher education, where videos are watched tens or hundreds  ...  Answers to the Research Questions The answer to the first research question ("Are data generated by students watching educational videos perceived as useful by teachers in small scale learning scenarios  ... 
doi:10.3390/app112110366 fatcat:626g246cgfhovosp2pqjyrw2ua

Understanding student learning pathways in traditional online history courses: utilizing process mining analysis on clickstream data

Matt Crosslin, Kimberly Breuer, Nikola Milikić, Justin T. Dellinger
2021 Journal of Research in Innovative Teaching & Learning  
that is student-directed.Design/methodology/approachProcess mining analysis was utilized to examine and cluster clickstream data from an online college-level History course designed with dual modality  ...  This paper examines some of the results from different approaches to clustering the available data.FindingsBy examining how often students interacted with others, whether they were more internal or external  ...  Research question Based on the need to understand how students engage with SMLP, this study investigated one primary research question: (1) What patterns, clusters or characteristics of students' pathway  ... 
doi:10.1108/jrit-03-2021-0024 fatcat:itmr35iutfgpxgw3msr5krd3hq

The benefits and caveats of using clickstream data to understand student self-regulatory behaviors: opening the black box of learning processes

Rachel Baker, Di Xu, Jihyun Park, Renzhe Yu, Qiujie Li, Bianca Cung, Christian Fischer, Fernando Rodriguez, Mark Warschauer, Padhraic Smyth
2020 International Journal of Educational Technology in Higher Education  
Such data enable researchers and instructors to collect information at scale about how each student navigates through and interacts with online education resources, potentially enabling objective and rich  ...  Student clickstream data-time-stamped records of click events in online courses-can provide fine-grained information about student learning.  ...  Third, engagement data from online classes can be missing for a number of reasons. For instance, clickstream data only capture students' interactions with online materials.  ... 
doi:10.1186/s41239-020-00187-1 fatcat:5rzof6fxtbhq7pvayp5ctmkzsi

Building an Apparatus: Refractive, Reflective, and Diffractive Readings of Trace Data

Carsten Østerlund, Syracuse University,USA, Kevin Crowston, Corey Jackson, Syracuse University,USA, "University of California, Berkeley, USA"
2020 Journal of the AIS  
We argue that a diffractive methodology allows us to explore how trace data are not given but created through the construction of a research apparatus to study trace data.  ...  Recently, he has been particularly interested in how we can merge qualitative and quantitative methodologies to study trace data associated with AI systems.  ...  Our answers to these questions and thus how we demarcate the apparatus have consequences for the phenomena: namely, learning.  ... 
doi:10.17705/1jais.00590 fatcat:e4irmundung2lax6vmroaefc3e

EDM and Privacy: Ethics and Legalities of Data Collection, Usage, and Storage

Mark Klose, Vasvi Desai, Yang Song, Edward F. Gehringer
2020 Educational Data Mining  
With no names, no birth dates, no connections to the school, you would think it impossible to track the answers back to the class.  ...  We explore four major types of data used in EDM: (i) clickstream data, (ii) studentinteraction data, (iii) evaluative data, and (iv) demographic data.  ...  Students can be identified and targeted on the basis of their answering patterns, e.g., what questions they answered correctly.  ... 
dblp:conf/edm/KloseDSG20 fatcat:dv7uf7wnkzhuxbzol6xg5gfrzy

Behavior-Based Latent Variable Model for Learner Engagement

Andrew S. Lan, Christopher G. Brinton, Tsung-Yen Yang, Mung Chiang
2017 Educational Data Mining  
A learner's latent concept knowledge is assumed to dictate their observed performance on in-video quiz questions.  ...  features we propose that quantify the learner's interaction with the lecture video.  ...  to high knowledge, while small, negative values lead to lower chances of answering a question correctly, thus corresponding to low knowledge.  ... 
dblp:conf/edm/LanBYC17 fatcat:qvqq4hxmifbaboq3uvs6gc5pmi

Using Educational Data Mining Techniques to Identify Profiles in Self-Regulated Learning: An Empirical Evaluation

Eric Araka, Robert Oboko, Elizaphan Maina, Rhoda Gitonga
2022 International Review of Research in Open and Distance Learning  
Furthermore, these profiles could provide insights on how to design a learning management system which could promote SRL, based on learner behaviors.  ...  Second, through correlation analysis, our study established that there is a significant relationship between the SRL profiles and students' final results.  ...  The inductive miner algorithm was used to produce process models that demonstrated students' learning behaviors. The process models reproduced students' interaction on the LMS.  ... 
doi:10.19173/irrodl.v22i4.5401 doaj:7c394d8192fd4d1a9f80b3d9b7d54d66 fatcat:pzr2fbeylzbh7nnrdf7est7sfq

Reflections on Different Learning Analytics Indicators for Supporting Study Success

Dirk Ifenthaler, Jane Yin-Kim Yau
2020 International Journal of Learning Analytics and Artificial Intelligence for Education (iJAI)  
Key indicators may include GPA, learning history, and clickstream data.  ...  <p class="0abstract"><span lang="EN-AU">Common factors, which are related to study success include students' sociodemographic factors, cognitive capacity, or prior academic performance, and individual  ...  Key indicators: trace data (clickstream) and assessment data.  ... 
doi:10.3991/ijai.v2i2.15639 fatcat:e3x3etdhr5hcdful5bupgjozeu

Analysis of the Factors Influencing Learners' Performance Prediction with Learning Analytics

Pedro Manuel Moreno-Marcos, Ting-Chuen Pong, Pedro J. Munoz-Merino, Carlos Delgado Kloos
2020 IEEE Access  
In this direction, this work aims to analyze how several factors can make an influence on the prediction of students' performance.  ...  Predictive power was also better for concept-oriented assignments and best models usually contained only the last interactions.  ...  [32] used Bayesian Knowledge Tracing to forecast students' answers in multiple tests, including the final exam.  ... 
doi:10.1109/access.2019.2963503 fatcat:lla7xz4v2jfohfck7ygnfsgnhu
« Previous Showing results 1 — 15 out of 273 results