ACTNext Newsletter: July 2019
Welcome to the ACTNext Newsletter!
Dear colleague,
Welcome to the first installment of the ACTNext newsletter! I hope you’ll find it full of useful information regarding our research, projects and other points of interest as well.
Our latest news is that we’ve just wrapped-up demonstrating our new ACT skill for Amazon Alexa at ISTE ’19 (press release & related coverage) and I’d like to personally invite you to sign-up for a chance to give your input during the beta release later this year.
I’d also like to take this opportunity to invite you to our annual event, the Education Technology and Computational Psychometrics Symposium held October 9 & 10 in Coralville, IA. Registration and the call for poster presentations will open in July, but please visit the ETCPS ’19 website below for more information and to view the outstanding speaker line-up we’ve put together this year.
In closing, thank you for subscribing to our newsletter and if you find it interesting, please forward it to your colleagues. We will also host this content on our new Medium.com publication, Navigator, where you’ll also find a collection of our blogs on topics at the intersection of technology, learning, psychometric research, and society.
Best regards,
Alina von Davier
Senior Vice President
ACTNext — ACT
ETCPS 2019
Join us Oct. 9 & 10 for our annual conference, the ACTNext Computational Psychometrics and Education Technology Symposium!
In conjunction with ETCPS ’19, ACT’s Center for Equity in Learning and ACTNext have co-organized a pre-conference panel and round table discussion, free and open to the public. Geared toward educators, topics will focus on bridging the gap in the digital divide, both in the classroom and in education policy.
Featured ACTNext Research
Framework for effective teamwork assessment in collaborative learning and problem solving
This paper presents an interactive team collaborative learning and problem-solving (ITCLP) framework for effective teamwork learning and assessment. Modeling the dynamics of a collaborative, networked system involving multimodal data presents many challenges. This framework incorporates an Artificial Intelligence (AI), a Machine Learning (ML) and computational psychometrics (CP) based methodology,system architecture, and algorithms to find patterns of learning, interactions, relationships, and effective teamwork assessment from a collaborative learning environment (CLE).
A Framework for Community Detection in Large Networks using a Game-theoretic Modeling
Regular and synthetic complex networks have motivated intense interest in studying the fundamental unifying principles of various complex networks. This paper presents a new game-theoretic approach towards community detection in large-scale complex networks based on modified modularity; this method was developed based on modified adjacency, modified Laplacian matrices and neighborhood similarity.
Few models have been more ubiquitous in their respective fields than Bayesian knowledge tracing and item response theory. This paper illustrates a fundamental connection between these two models. A research agenda is outlined which answers how to move forward with modeling learner data.
From the Blog…
As we strive to continue to improve education and prepare students for success, it’s important to think about all of the different ways in which learning occurs.
Read more to see the insights we can glean about learning from the incredible achievement babies make when they learn to walk.
Guest Research
Rural Students: Technology, Coursework, and Extracurricular Activities
A closer look at rural students’ access to technology, coursework, and extracurricular activities opportunities in various facets of their high school experiences.
What We’re Reading/Watching
Favorites from the ACTNext team:
Machine Behavior — Nature
Machines powered by artificial intelligence increasingly mediate our social, cultural, economic and political interactions. Understanding the behaviour of artificial intelligence systems is essential to our ability to control their actions, reap their benefits and minimize their harms. This article outlines a set of questions that are fundamental to this emerging field and then explores the technical, legal and institutional constraints on the study of machine behaviour.
The StarCraft Multi-Agent Challenge
In the last few years, deep multi-agent reinforcement learning (RL) has become a highly active area of research. Standardised environments such as the ALE and MuJoCo have allowed single-agent RL to move beyond toy domains, such as grid worlds. However, there is no comparable benchmark for cooperative multi-agent RL. As a result, most papers in this field use one-off toy problems, making it difficult to measure real progress. In this paper, the StarCraft Multi-Agent Challenge (SMAC) is proposed as a benchmark problem to fill this gap.
Is Super-intelligence Impossible?
Philosophy and AI
Check out this video from Saturday, March 9, when more than 1200 people jammed into Pioneer Works in Red Hook, Brooklyn, for a conversation between two of our greatest philosophers, David Chalmers and Daniel C. Dennett.
© 2019 ACT, Inc.
All rights reserved.
500 ACT Drive
Iowa City, IA 52243
