29,858 Hits in 5.6 sec

Review on Predictive Modelling Techniques for Identifying Students at Risk in University Environment

Mat Yaacob Nik Nurul Hafzan, Deris Safaai, Mat Asiah, Mohamad Mohd Saberi, Safaai Siti Syuhaida, Lim Meng Hee
2019 MATEC Web of Conferences  
Many different machine learning techniques have been implemented for predictive modelling in the past including decision tree, k-nearest neighbour, random forest, neural network, support vector machine  ...  Using analytics, administrators, instructors and student can predict what will happen in future.  ...  Predictive Modelling Techniques for identifying at-risk Student Predictive model is created from data trained using machine learning techniques.  ... 
doi:10.1051/matecconf/201925503002 fatcat:z3cy2tkro5dutcktvhnzt73zji

The interrelationship between concepts about agency and students' use of teachable-agent learning technology

Christopher Brett Jaeger, Alicia M. Hymel, Daniel T. Levin, Gautam Biswas, Natalie Paul, John Kinnebrew
2019 Cognitive Research  
We also found that students who used the Betty's Brain system distinguished human behavior from machine behavior more strongly than students who did not.  ...  We found that the students who made more intentional behavioral predictions about humans learned more effectively from the system.  ...  Students use the Betty's Brain program by reading provided texts and identifying the causal relationships among concepts described in those texts.  ... 
doi:10.1186/s41235-019-0163-6 fatcat:qy4il6t77refdmyxyqdwnifu34

Interpretability via Model Extraction [article]

Osbert Bastani and Carolyn Kim and Hamsa Bastani
2018 arXiv   pre-print
The ability to interpret machine learning models has become increasingly important now that machine learning is used to inform consequential decisions.  ...  We show how model extraction can be used to understand and debug random forests and neural nets trained on several datasets from the UCI Machine Learning Repository, as well as control policies learned  ...  At the same time, machine learning algorithms have been shown to exhibit unexpected defects when deployed in the real world; examples include causality (i.e., inability to distinguish causal effects from  ... 
arXiv:1706.09773v4 fatcat:pw5aubvncnarlgywxakuoxojdq

Using the Developmental Path of Cause to Bridge the Gap between AWE Scores and Writing Teachers' Evaluations

Hong Ma, Tammy Slater
2015 Writing & Pedagogy  
Findings suggested that if Criterion is to be used successfully in the classroom, writing teachers need to take a meaning-based approach to their assessment, which would allow them and their students to  ...  Using the developmental path of cause as an analytical framework for assessment may then help teachers assign grades that are more in sync with AWE scores, which in turn can help students gain more trust  ...  One of the teachers found it important for students to identify unique reasons for attending university.  ... 
doi:10.1558/wap.v7i2-3.26376 fatcat:oe53x6zwuvfpzltni7kzxur5iy

Big Data, Data Science, and Causal Inference: A Primer for Clinicians

Yoshihiko Raita, Carlos A. Camargo, Liming Liang, Kohei Hasegawa
2021 Frontiers in Medicine  
As machine learning algorithms become ubiquitous tools to handle quantitatively "big data," their integration with causal reasoning and domain knowledge is instrumental to qualitatively transform medicine  ...  It is the algorithms encoding causal reasoning and domain (e.g., clinical and biological) knowledge that prove transformative.  ...  learning MOOC Coursera: machine learning One of the most popular machine learning courses (as of January 2021, 3.9 million students have been enrolled).  ... 
doi:10.3389/fmed.2021.678047 fatcat:qplkduokxnf5fgf5um73lffkr4


2020 Statistics Education Research Journal  
and causal) as intuitive theories.  ...  Training programs for statisticians and data scientists in healthcare should give greater importance to fostering inductive reasoning toward developing a mindset for optimizing Big Data.  ...  Special thanks to my students, Mercy College, and the team from Canterbury Christ Church University, UK.  ... 
doi:10.52041/serj.v19i1.133 fatcat:bq6rrlldxvgpniens4zyyqv5ba

The Interaction of Children's Concepts about Agents and Their Ability to Use an Agent-Based Tutoring System [chapter]

Alicia M. Hymel, Daniel T. Levin, Jonathan Barrett, Megan Saylor, Gautam Biswas
2011 Lecture Notes in Computer Science  
After repeated exposure to a teachable agent, students did not make more intentional attributions for the agent than a computer, but a general understanding of agency predicted success in learning from  ...  We also tested whether individual differences in concepts about agent intentionality would affect children's ability to learn from the agent.  ...  Students use the Betty's Brain program by reading provided resources and identifying the causal relationships present among concepts described in the text.  ... 
doi:10.1007/978-3-642-21619-0_70 fatcat:uhdofqyltjfgnpcymoqvrcwtca

Using Group Model Building to Foster Learning for Strategic Sustainable Development

Matilda Watz
2020 Sustainability  
The potential of the group model building (GMB) process' steps and associated modeling to foster learning for strategic sustainable development (SSD) was analyzed using four case examples.  ...  This paper seeks to contribute to this discussion by asking 'in which way may group model building be used to foster learning that leads to competency for strategic sustainable development?'.  ...  Students at the transdisciplinary, 1-year, master's program in strategic leadership toward sustainability are taught, and encouraged to use, simplified CLDs as a core methodology to model and identify  ... 
doi:10.3390/su12208350 fatcat:vckl6kyftneyvogkbqjfml7k6u

Machine Learning Analysis of Heterogeneity in the Effect of Student Mindset Interventions [article]

Fredrik D. Johansson
2018 arXiv   pre-print
Our analysis uses machine learning (ML) to address the following associated problems: assessing treatment group overlap and covariate balance, imputing conditional average treatment effects, and interpreting  ...  We study heterogeneity in the effect of a mindset intervention on student-level performance through an observational dataset from the National Study of Learning Mindsets (NSLM).  ...  This class of bounds illustrate the bias-variance trade-off that is typical for machine learning and motivates the use of regularization to control model complexity.  ... 
arXiv:1811.05975v1 fatcat:4ytacklufvhencmpkhql6xh3r4

Supporting Mechanistic Reasoning in Domain-Specific Contexts

Paul J. Weinberg
2017 Journal of Pre-College Engineering Education Research  
Such a characterization of mechanistic reasoning illuminates what is easy and difficult about this form of reasoning, within the subdomain of simple machines.  ...  The data in this study comes from the Assessment of Mechanistic Reasoning Project (AMRP) (Weinberg, 2012), designed using item response theory modeling to diagnose individuals' mechanistic reasoning about  ...  Although the nation seems to be orienting toward a new emphasis on engineering education for K-12 students, there is not one single definition or orientation towards what that should entail.  ... 
doi:10.7771/2157-9288.1127 fatcat:g26zjgfhe5g6zati6hdbfigtvm

State of the Art in Fair ML: From Moral Philosophy and Legislation to Fair Classifiers [article]

Elias Baumann, Josef Lorenz Rumberger
2018 arXiv   pre-print
Machine learning is becoming an ever present part in our lives as many decisions, e.g. to lend a credit, are no longer made by humans but by machine learning algorithms.  ...  This work aims to give an introduction into discrimination, legislative foundations to counter it and strategies to detect and prevent machine learning algorithms from showing such behavior.  ...  [30] propose a new approach to detect and avoid discrimination in machine learning based on causal reasoning by Pearl [43] .  ... 
arXiv:1811.09539v1 fatcat:7e7hkumg2faffhmrgjvdxo2oiu

Moving from descriptive to causal analytics

Jack Schryver, Mallikarjun Shankar, Songhua Xu
2012 Proceedings of the 2012 international workshop on Smart health and wellbeing - SHB '12  
proper nudging students toward better options in their academic endeavors.  ...  Split into three main parts; the book identifies the primary reasons for an uncompromised implementation of analytics to gather, translate, and leverage data in a cyclic manner from simply reporting to  ...  Baer as a set of software tools, machine-learning techniques, and algorithms used for capturing, processing, indexing, storing, analyzing and visualizing data (p. 3), others who contributed to the book  ... 
doi:10.1145/2389707.2389709 dblp:conf/cikm/SchryverSX12 fatcat:74fwrxt2wjaezgrt4tdy5jppni

Modeling, Assessing, and Supporting Key Competencies Within Game Environments [chapter]

Valerie J. Shute, Iskandaria Masduki, Oktay Donmez, Vanessa P. Dennen, Yoon-Jeon Kim, Allan C. Jeong, Chen-Yen Wang
2009 Computer-Based Diagnostics and Systematic Analysis of Knowledge  
This provides (a) a way of reasoning about assessment design, and (b) a way of reasoning about student performance in gaming or other learning environments.  ...  With jMap, students create their causal maps using Excel's autoshape tools.  ... 
doi:10.1007/978-1-4419-5662-0_15 fatcat:qgjtrss4mzfwhkad6bslqf3qwu

Connecting Criterion scores and classroom grading contexts: A systemic functional linguistic model for teaching and assessing causal language

Hong Ma, Tammy Slater
2015 CALICO journal  
the implementation of AWE systems in classroom contexts, and would help students focus on the core of a cause-effect essay: appropriateness and sophistication of causal language.  ...  This 'path' has the potential to support validity arguments because it suggests how causal linguistic features can be organized in hierarchical order.  ...  We could reasonably assume that papers employing causal linguistic features towards the higher end of the path are scored higher by Criterion, which measures the number of discourse elements, length of  ... 
doi:10.1558/cj.v33i1.26562 fatcat:dbbayhartnfx5nku2r4223keje

Mathematical Description and Mechanistic Reasoning: A Pathway Toward STEM Integration

Paul J. Weinberg
2017 Journal of Pre-College Engineering Education Research  
In addition, the development of mathematical representation presents a viable pathway towards STEM integration.  ...  Participants were elementary, middle, and high school students as well as college undergraduates, and adults without college education.  ...  When students learn content in science and engineering, representing relations from mathematics involves the use of what Hall and Greeno (2008) term representational resources.  ... 
doi:10.7771/2157-9288.1124 fatcat:me5werep3bg4de4z5maxcggh5a
« Previous Showing results 1 — 15 out of 29,858 results