Marie Ann Bienkowski

In data mining and data analytics, tools and techniques once confined to research laboratories are being adopted by forward-looking industries to generate business intelligence for improving decision making. Higher education institutions are beginning to use analytics for improving the services they provide and for increasing student grades and ret...

The magnitude of the problem of unskilled labor for the U.S. workforce is known. More than 36 million adults in the United States do not have the basic literacy and math skills needed for many entry-level jobs and even less so for the types of jobs expected to dominate in the future. We also know that our federal- and state-funded adult basic educa...

Systematic endeavors to take computer science (CS) and computational thinking (CT) to scale in middle and high school classrooms are underway with curricula that emphasize the enactment of authentic CT skills, especially in the context of programming in block-based programming environments. There is, therefore, a growing need to measure students’ l...

The ability to explain something, e.g., the operation of a complex machine or program, is an important, but poorly understood, component of intelligent behavior. We discuss an artificial intelligence approach to the modeling of the explanation process within the framework of a graphics-based CAD system currently under development, which can describ...

Computational thinking is a core skill in computer science that has become a focus of instruction in primary and secondary education worldwide. Since 2010, researchers have leveraged Evidence-Centered Design (ECD) methods to develop measures of students’ Computational Thinking (CT) practices. This article describes how ECD was used to develop CT as...

As K-12 computer science (CS) education initiatives scale throughout the U.S., researchers seek to understand the context-specific relationships between CS instruction and student learning. Evaluation of instruction requires valid measures of curriculum implementation. We have developed measures for identifying conditions for successful implementat...

Headlines in the popular press like "How Silicon Valley Pushed Coding into American Classrooms" [8] and "Who Benefits from the Push to Teach Every Kid to Code? Tech Companies for One" [7] characterize computer science education initiatives as strictly top-down privatesector efforts to get public schools to prepare their future workforce. In our wor...

We demonstrate that, by using a small set of hand-graded student work, we can automatically generate rubric criteria with a high degree of validity, and that a predictive model incorporating these rubric criteria is more accurate than a previously reported model. We present this method as one approach to addressing the often challenging problem of...

Learning Analytics Goes to School presents a framework for engaging in education research and improving education practice through the use of newly available data sources and analytical approaches. The application of data-intensive research techniques to understanding and improving learning environments has been growing at a rapid pace. In this boo...

As K-12 computer science (CS) initiatives scale throughout the U.S., educators face increasing pressure from their school systems to provide evidence about student learning on hard-to-measure CS outcomes. At the same time, researchers studying curriculum implementation and student learning want reliable measures of how students apply their CS knowl...

We demonstrate that, by using a small set of hand-graded students, we can automatically generate rubric parameters with a high degree of validity, and that a predictive model incorporating these rubric parameters is more accurate than a previously reported model. We present this method as one approach to addressing the often challenging problem of...

Computational thinking (CT) comprises problem-solving skills such as iterative refinement, decomposing complex problems, debugging, and abstraction, in addition to appropriate use of algorithmic concepts to compose computational solutions. These skills are called out as essential components of computer science (CS) learning in efforts to promote “C...

K-12 classrooms use block-based programming environments (BBPEs) for teaching computer science and computational thinking (CT). To support assessment of student learning in BBPEs, we propose a learning analytics framework that combines hypothesis- and data-driven approaches to discern students' programming strategies from BBPE log data. We use a pr...

Many introductory programming environments generate a large amount of log data, but making insights from these data accessible to instructors remains a challenge. This research demonstrates that student outcomes can be accurately predicted from student program states at various time points throughout the course, and integrates the resulting predict...

Education researchers have extensively studied how secondary teachers adopt and adapt new curriculum and new teaching practices, especially in science and mathematics. Their goals are often to learn ways to help teachers enact new pedagogical approaches, so the results inform teacher professional development, as well as building knowledge in the fi...

How do learners in middle and high school enact computational thinking (CT) practices as they build computational artifacts in open-ended programming environments? What configurations and patterns of student behavior in open-ended programming environments provide evidence of their learning of CT process and practices? How can we design personalized...

Collaborative problem solving (CPS) is seen as a key skill in K-12 education—in computer science as well as other subjects. Efforts to introduce children to computing rely on pair programming as a way of having young learners engage in CPS. Characteristics of quality collaboration are joint exploring or understanding, joint representation, and join...

Authentic problem solving tasks in digital environments are often open-ended with ill-defined pathways to a goal state. Scaffolds and formative feedback during this process help learners develop the requisite skills and understanding, but require assessing the problem- solving process. This paper describes a hybrid approach to assessing process at...

As K-12 computer science educators and researchers seek ways to support learning of computational thinking (CT) through programming in blocks-based programming environments, they are hampered by a lack of understanding of “programming process” that includes hard-to-see sequences of actions signifying problem-solving strategies. To support learning...

High school computer science teaching can be informed by how science and engineering practices are defined in K-12 curriculum standards. In the United States, the Next Generation Science Standards (NGSS) are seen as broadly stated and widely accepted statements of what children should know about science and engineering to be literate citizens and t...

https://tech.ed.gov/files/2015/04/Developer-Toolkit.pdf

As computer science (CS) and computational thinking (CT) make their way into all levels of K-12 education, valid assessments aligned with new curricula can assist in measuring student learning, easing the way for adoption of new computing courses, and evaluation of pedagogical approaches for teaching computing ideas and concepts. Without attention...

Researchers, practitioners, and policymakers are (in most states) rallying around the Next Generation Science Standards. First released in 2012, the NGSS address the "mile wide, inch deep" science teaching so prevalent in K-12 and instead emphasize disciplinary core ideas, cross-cutting concepts, and practices in science and engineering. The NGSS m...

Presentation as part of the 2014 AERA Presidential Session: Learning Analytics: Capturing, Analyzing, and Visualizing Experiences of Lifelong Learning

This paper discusses the design process used to develop an assessment of computational thinking to support the adoption of a high school computer science curriculum. The domain analysis process started with the identification of core computational thinking practices as defined in the literature (including curriculum standards and related courses)....

The proliferation of online teaching, learning, and assessment resources is hampering efforts to make finding relevant resources easy. Metadata, while valuable for curating digital collections, is difficult to keep current or, in some cases, to obtain in the first place. Social metadata, paradata, usage data, and contextualized attention metadata a...

Science teachers inspire in part by their constant adaptation to the learning needs of their students and to evolving content, curriculum, technology, and student populations. Innovation--bringing novel things to a situation to confer a benefit--is an integral part of teaching overall, and in especially inspired science teaching. While innovation a...

Published in Educational Technology Publications Inc. journal Educational Technology. ISSN 00131962 In this article, the authors describe an open-source, open-data digital infrastructure for sharing information about open educational resources (OERs) across disparate systems and platforms. The Learning Registry, which began as a project funded by...

We describe our experimentation with the current implementation of a distribution system used to share descriptive and social metadata about learning resources. The Learning Registry, developed and released in a beta version in October 2011, is intended to store and forward learning-resource metadata among a distributed, de-centralized network of n...

This edited volume provides an overview of the latest advancements in adaptive training technology. Intelligent tutoring has been deployed for well-defined and relatively static educational domains such as algebra and geometry. However, this adaptive approach to computer-based training has yet to come into wider usage for domains that are less well...

Science teachers constantly adapt to the learning needs of their students and to evolving content, curriculum, technology, and student populations. Innovation – bringing novel things to a situation to confer a benefit – is an integral part of teaching overall and especially science teaching. While innovation and adaptation are recognized as critica...

The G1:1 international network of learning researchers met to identify major trends and uncertainties that could drive the evolution of learning technology. Using a technique called scenario-based planning, the group created stories of plausible futures that bring to life what collaborative learning may be like in 2015. These stories present contex...

The G1:1 international network of learning researchers met to identify major trends and uncertainties that could drive the evolution of learning technology. Using a technique called scenario-based planning, the group created stories of plausible futures that bring to life what collaborative learning may be like in 2015. These stories present contex...

This study examined the effects that different kinds of technology-based representational tools have on students' genetics learning. One form of tool represented phenomenological features of genetics - genes, pedigrees, and so on - and were embedded in a simulations-based software program. and another tool provided discursive representation to supp...

Intelligent problem solving systems must be able to express their results in a coherent and flexible manner. One way this can be done is by eztemporaneous elaboration, the method of language production that underlies more skilled tasks such as explanation. This paper outlines a computational model for extemporaneous elaboration that is implemented...

Those of us who are newly arrived on the agent scene have a variety of books available with which to increase our agent vocabulary. In this article, I provide a short review of five books related to agent research. I also discuss several overview papers and the recently published proceedings of the 1997 Autonomous Agents conference. Rather than pro...

Volume III is a system design report and user's manual for SIPE-2 in Integrated Feasibility Demonstration -4 (IFD-4). This report discusses the operational model used for feasibility estimation in IFD-4. Described are the systems modules and the SIPE -2 user interface. This report further discusses the integration design and implementation of SIPE-...

This report presents a preliminary working plan for the transfer of the technology and applications developed by SRI under the Joint Maritime Crisis Action Planning (JMCAP) project into operational Navy systems. The systems and concepts developed within the Advanced Concept Technology Demonstration (ACTD), sponsored by the Office of Naval Research...

This report describes Version 3 of the Air Campaign Planning Knowledge Base (ACP-KB). Discussed are the generation of Air and Maritime Campaign plans by SlPE-2. SIPE-2 is a domain independent, state-of-the practice artificial intelligence (AI) planning system. ACP-KB components are described in detail in sections three through eight. Also discussed...

We integrated three mature AI reasoning systems and several legacy military systems in order to provide human planners with advanced capabilities in a military planning domain. The integration demonstrates the operation of a diverse set of AI applications that present a unified system to a human planner in a realistic and meaningful context. We beg...

The ARPA/Rome Laboratory Knowledge Based Planning and Scheduling Initiative (ARPI) is an Advanced Research Projects Agency (ARPA) and Rome Laboratory (RL) sponsored initiative to promote the development of new knowledge-based planning and scheduling technology for use by the military in support of operational planning and scheduling problems. The A...

COA generation is interwoven with COA evaluation. SOCAP demonstrates its ability to aid in feasibility estimation by producing output for the Dynamic Analysis and Replanning Tool (DART) transportation feasibility estimator. The output of SOCAP is first used by an intermediate Force Module Enhancer and Requirements Generator (FMERG), which elaborate...

In this paper, we report on our past and recent experiences in applying an AI generative planning system, called System for Interactive Planning and Execution (SIPE-2), to the problem of generating crisis action operations plans in a joint military domain * . We describe our motivation for selecting a generative planner, the application itself (inc...

This paper describes a system that uses AI planning and representation techniques as the core of a decision support system. * The planning technology is supplemented with other AI and non-AI technologies. The overall system and initial application domain, military operations planning, are described first. We then describe the integration of SIPE-2,...

In the ARPA-Rome planning initiative, technology moves from researchers to users, and feedback is given by users to researchers. Integrated Feasibility Demonstrations are a vital part of this user-centered approach to software engineering: they demonstrate to members of the operational community how maturing technologies can work together to addres...

The CPE promotes the development of collaborative, distributed planners by combining a repository for shared software and data, integrated software systems, and a testbed for experimentation

Upon first encountering Etienne Wenger's book, "Artificial Intelligence and Tutoring Systems: Computational and Cognitive Approaches to the Communication of Knowledge," I assumed that it was the sort of book that would serve only as a reference. To find out about the EXCHECK tutoring system, I would just look it up in the exhaustive subject index....

An abstract is not available.

In changing your view, you must balance the amount of change involved against the improvement in explanatory coherence resulting from the change. Even if change and improvement in coherence are measured by simply counting, there can be no general requirements that the number of modified items (added or subtracted) be no greater than the number of n...

CADHELP is a graphics-based computer-aided design system which contains detailed knowledge bases intended to support three different types of intelligent behavior: (1) the generation of natural-language explanations concerning the operation of the graphical features, for use by naive users; (2) an animated display coordinated with the explanation,...

Five experiments are described on the processing of ambiguous words in sentences. Two classes of ambiguous words (noun-noun and noun-verb) and two types of context (priming and nonpriming) were investigated using a variable stimulus onset asynchrony (SOA) priming paradigm. Noun-noun ambiguities have two semantically unrelated readings that are noun...

This paper discusses an approach to the modelling of the explanation process within the framework of a graphics-based CAD system currently under development, which can describe its own use, including the common ways to make and recover from errors. With a coordinated textual and pictorial display, the system, CADHELP, simulates an expert demonstrat...

We are working on a system to support a community of science educators (Kindergarten through 12th grade teachers) and science education stakeholders in improving science education in part through the use of Web resources. We are establishing a web site called Science Forum that will provide the technology supports needed to create a community of sc...