Search

The Generalized Intelligent Framework for Tutoring (GIFT) is a research prototype with three general goals associated with its functions and components: 1) lower the skills and time required to author Intelligent Tutoring Systems (ITSs) in a variety of task domains; 2) provide effective adaptive instruction tailored to the needs of each individual learner or team of learners; and 3) provide tools and methods to evaluate the effectiveness of ITSs and support research to continuously improve instructional best practices. This special issue focuses primarily on the third goal, GIFT as a research testbed. A discussion thread covers each article within this special issue and discusses its actual and potential impact on GIFT as a research tool for AIED. Our primary motivation was to introduce the AIED community to GIFT not just as a research tool, but as an extension of familiar challenges taken on previously by AIED scientists and practitioners. This preface provides a high level overview of the GIFT functions (authoring, instructional delivery and management, and experimentation) and presents its primary design principles. To learn more about GIFT, freely access the software, documentation, and associated technical papers visit www.GIFTtutoring.org .

This paper examines approaches to improve training technology design with the goal of enhancing transfer of training, the effect that knowledge and skills acquired during training have on problem solving or knowledge acquisition in work or operational environments. Specifically, we address the design of adaptive instructional systems (AISs), a category of learning technology that includes intelligent tutoring systems (ITSs), intelligent mentors and other recommender systems that tailor instruction to more efficiently meet the needs of individual learners and teams. Since tailored training requires more content and instructional decisions and therefore more authoring time than non-tailored computer-based training, we also examine how AIS design and transfer of training might be influenced by AIS authoring processes and interfaces. Design challenges are also discussed and include factors such as the ease of authoring that influence transfer of training.

This paper examines the application of intelligent agents to guide and adapt instruction in a class of learning technologies known as adaptive instructional systems (AISs). AISs are artificially-intelligent, computer-based systems that guide learning experiences by tailoring instruction and recommendations based on the goals, needs, and preferences of each individual learner or team in the context of domain learning objectives. Intelligent agents are autonomous entities which observe the conditions in their environments through percepts (e.g., sensors) and then act upon the environment using actuators. Their activity is intelligently directed to strategies (plans for action) and tactics (actions executed by the AIS) which enhance the progress of the learner toward the achievement of assigned goals and objectives. To optimize agent and learner performance we examine a notional set of principles that is needed to guide adaptive instructional designers and system developers toward adaptation vectors that support both instructionally meaningful (effective) and doctrinally correct (relevant and tactically plausible) actions by the AIS. In conclusion, we explore the literature to understand the design of adaptation vectors and provide recommendations for future AIS research and standards development.

The adaptive instruction provided by Intelligent Tutoring Systems (ITSs) tailors direction, support, and feedback to enhance/maintain the learning needs (e.g., lack of knowledge or skill) of each individual. Today, ITSs are generally developed to support desktop training applications, with the most common domains involving cognitive problem solving tasks (e.g., mathematics and physics). In recent years, implementations of game-based tutors authored using the Generalized Intelligent Framework for Tutoring (GIFT), an open-source tutoring architecture, provided tailored training experiences for military tasks through desktop applications (e.g., games including Virtual Battlespace and Virtual Medic). However, these game-based desktop tutors have also been limited to adaptive instruction for cognitive tasks (e.g., problem solving and decision-making). The military requires adaptive instruction to extend beyond the desktop to be compatible with the physical nature of many tasks performed by soldiers, sailors, and airmen. This article examines how commercial sensor technologies might be adapted to work with GIFT and support tailored computer-guided instruction in the psychomotor domain for a military medical training task, specifically hemorrhage control. Toward this goal, we evaluated the usability and system features of commercial smart glasses and pressure-sensing technologies. Smart glasses were selected as the focus of this study over handheld mobile devices in order to promote a hands-free experience during the training of hemorrhage-control tasks on a mannequin. Pressure sensors were selected to provide direct measures of effectiveness during the application of tourniquets and pressure bandages. Each set of technologies (smart glasses and pressure sensors) was evaluated not with respect to each other, but with respect to their capabilities to support adaptive instruction in the wild at the learner’s point-of-need and criteria based on established usability heuristics. Instruction in the wild is training provided in an environment outside the classroom and areas where tracking and sensing infrastructure are available (e.g., deployed areas of operation). We examined a wide range of features and capabilities, and evaluated their compatibility with the hemorrhage-control task, to answer the following question: what system design features (e.g., usability and interaction) are needed to support adaptive instruction for this individual psychomotor task at the point-of-need in locations where no formal training infrastructure is available?

In this paper we investigate intelligent tutoring communications in game-based learning platforms and examine its effect on perceived flow and immersion. The technology influencing this research is the open-source Generalized Intelligent Framework for Tutoring (GIFT), a domain-independent architecture used to author, deliver, and evaluate intelligent tutoring technologies. Influenced by theoretical underpinnings associated with flow, the resulting experiment looks at the application of Embodied Pedagogical Agents (EPA) in a game-based training environment used for communicating tutor generated feedback. Conditions were structured to examine tradeoffs between embedding an EPA directly in a game, embedding an EPA in GIFT’s browser-based Tutor-User Interface (TUI), or using audio prompts alone. Statistical analyses are presented examining treatment effects on an individual’s perceived sense of flow during interaction, along with examination of game characteristics required to support immersion. Outcomes support the use of an EPA present in GIFT’s TUI when compared to flow outcomes on audio prompts alone and the game embedded EPA.

GIFT Cloud is the recently released web-based application version of GIFT, an open-source computer-based tutoring architecture that supports authoring, deployment, and evaluation of intelligent tutoring system technologies. This paper presents the GIFT Cloud Authoring Tools, through the lens of usability. Each major element within the authoring tools is described, along with usability design considerations that were made in order to reduce occurrence of error, to organize information, and to support end-user goals. The initial release of GIFT Cloud supports an iterative design approach, informed by user data and feedback, with an overall goal of making tutor authoring practical for subject matter experts without computer programming or instructional design knowledge. As such, lessons learned from this release, as well as plans for future research and usability improvements, are discussed.

Instruction that adapts to individual learner characteristics is often more effective than instruction that treats all learners as the same. A practical approach to making MOOCs adapt to learners may be by integrating frameworks for intelligent tutoring systems (ITSs). Using the Learning Tools Interoperability standard (LTI), we integrated two intelligent tutoring frameworks (GIFT and CTAT) into edX. We describe our initial explorations of four adaptive instructional patterns in the PennX MOOC "Big Data and Education." The work illustrates one route to adaptivity at scale.

This paper describes methods for enhancing the experience application program interface (xAPI) to improve the assessment of domain competency modeling for adaptive instruction. xAPI is an e-learning software specification which allows individual learning experiences and achievements to be amassed in a Learning Record Store (LRS). Adaptive instruction includes tailored training or educational experiences usually delivered and guided by Intelligent Tutoring Systems (ITSs). ITSs can more effectively tailor or adapt instruction when they have more accurate models of the learner's prior knowledge or competency. This paper examines the potential effect of methods to more accurately model learner experiences and domain competency in an LRS. Specifically, we recommend five methods to improve xAPI statements by documenting: 1) achievement types; 2) experience duration; 3) experience source information; 4) domain learning and forgetting; and 5) assessment within learning experiences.

The current paper and presentation provide background on the different uses of intelligent tutoring systems (ITSs) in context of course instruction, discusses specific instructor considerations that are associated with their use, and ways to use ITSs for educational research. Instructor considerations include the time necessary to plan prior to constructing an ITS, the process of constructing ITS lessons for use by students, the method in which students will interact with the ITS, approaches to incorporating ITS use into classes, and the information that instructors would find useful to be output from the ITS. Specifically, the Generalized Intelligent Framework for Tutoring (GIFT), an open-source, domain independent ITS framework will be discussed as an approach to creating adaptive tutoring content for classroom use. GIFT includes straightforward authoring tools for instructors and Subject Matter Experts (SMEs). These authoring tools are powerful, do not require a background in computer science to use, and result in fully adaptive computer-based lessons. Additionally, GIFT provides the flexibility for instructors to bring their pre-generated and already existing instructional material to the system and use it to create ITS lessons. The authoring tools allow the instructor to determine the path of their lesson and the components that their students will experience (i.e. surveys, quizzes, lesson materials, videos). The paper includes details about the development of an instructor dashboard in GIFT, ways for an instructor to use GIFT for educational research, and a discussion of general output information from ITSs that would be relevant to instructors.

The Generalized Intelligent Framework for Tutoring (GIFT) is an open-source domain-independent intelligent tutoring system (ITS) framework. It provides the tools and capabilities to design a complete ITS, manage student instruction, and serve as a testbed for experimentation and analysis. GIFT was developed to provide a cost-effective and efficient means for developing ITSs that have interchangeable parts and can be reused. Additionally, GIFT provides the ability for human factors professionals to develop and run complete experiments in a computer-based environment. This demonstration will provide an introduction to GIFT, along with the motivation behind its design. Further, a demonstration of the tools that are useful to human factors practitioners and psychologists will be provided, and examples of courses that have been developed using GIFT will be shown.

This paper discusses tools and methods which are needed to support adaptive instruction for individual learners within the Generalized Intelligent Framework for Tutoring GIFT, an open source architecture for authoring, adapting instruction, and evaluating intelligent tutoring systems. Specifically, this paper reviews the learning effect model LEM which drives adaptive instruction within GIFT-based tutors. The original LEM was developed in 2012 and has been enhanced over time to represent a full range of function encompassing both the learner's and the tutor's interactions and decisions. This paper proposes a set of 10 functions to enhance the scope and functionality of the LEM and to extend it to be a career-long model of adaptive instruction and competency.

This paper discusses critical elements of adaptive instruction in support of training and education. Modeling and assessing learners and teams, optimizing adaptive instructional methods, applying domain modeling outside of traditional training and educational domains, automating authoring processes, and assessing the learning effect of instruction are among the challenges reviewed.

Head Mounted Displays (HMDs) have traditionally been and are currently utilized in a variety of applications including training, entertainment, and military operations. Most applications of HMDs seek to provide the user with enriched information, that is, information beyond that of what a human can gather with only biological vision. The Land Warrior is an operational system that utilizes a HMD. For Land Warrior, the HMD provides the Soldier better battle field situational understanding through text by communicating command and control information. Other Land Warrior battlefield tasks include target detection and recognition. This paper evaluates the visual components of the current Ground Soldier System (GSS), Land Warrior HMD, analyzes embedded training requirements (specifically detection ranges for embedded virtual targets and human performance issues associated with HMDs), and proposes an optical model to overcome some of the limitations inherent to the current commercial version of the Land Warrior HMD and other commercially-available HMDs. The design quality of the Land Warrior HMD has a direct impact on a soldier's performance in the field. The varying stringent environment in which LW operates provides HMD visual component design challenges, due to the correlation between the equipment style, information formatting, and use environment. Information formatting affects a Soldier's workload. The current LW HMD visual implementation contains information formatting limitations based on its ability to scale to other resolutions and size linearly. By increasing the performance of the HMD of the Land Warrior System, the potential to improve readiness and survivability also increase. Forty-five thousand sets of Land Warrior equipment will be fielded between 2001 and 2014.

The tutorial described in this report was conducted at the Interservice/Industry Training Simulation and Education Conference (IITSEC) in Orlando, FL, in December 2014. The purpose of this tutorial is 5-fold: 1) understand the differences between adaptive and adaptable systems; 2) understand the key components of Intelligent Tutoring Systems (ITSs); 3) understand the potential of ITSs as one-to-one tutors and where ITS technologies are most applicable in the training and educational domain; 4) understand the concept of self-regulated learning (SRL); and 5) understand how ITS design can support SRL.

The purpose of this technical report is to provide an exemplar for conducting an analysis of a qualitative dataset using machine learning techniques. Qualitative data are measured or expressed as a natural language description (e.g., category or attribute) rather than numbers as in quantitative datasets. It is often difficult to evaluate the relationship between qualitative variables of interest and outcomes (dependent variables), but machine learning techniques offer simplified methods to classify these outcomes. WEKA, the Waikato Environment for Knowledge Analysis, is a popular set of machine learning algorithms developed at the University of Waikato in New Zealand, which can be used to analyze both qualitative and quantitative data. To illustrate the use of WEKA on a qualitative dataset, we selected a known set of primate species with the desire to classify them into 1 of 3 classes (prosimians, monkeys, and apes) based on 7 qualitative attributes. When an existing dataset is used with known relationships, it allows us to evaluate a large number of WEKA algorithms in a relatively short time and validate their accuracy with the goal of identifying best practices for analyzing qualitative data.

It is well-known that personalised and adaptive training, such as from a human tutor, is dramatically more effective than traditional classroom training (Bloom, 1984; VanLehn, 2011). Due to a variety of reasons, however, tutoring systems are not yet ubiquitous within the training market. The US Army Research Laboratory is working to address this problem and has recently published a series of research vector outlines, which guide research in the various areas. The research within the architectural vector naturally exists to support the other vectors and to investigate, standardise, componentise, and commodise the processes and functions of the various tutoring system aspects. This paper serves as an expansion and companion to the similarly named 2015 International Defense and Homeland Security Simulation Workshop paper and yet-to-be-published ARL architectural research plan, expanded in order to discuss the progress made to date, clarify the role of the architecture in the research, and discuss some of the advantages of a unified system as part of measuring training effectiveness and overall system improvement.

The tutorial described in this report was conducted at the Human-Computer Interaction International Augmented Cognition Conference in Creta Maris, Crete, Greece, in June 2014. The purpose of this tutorial was 3-fold: 1) familiarize participants with the fundamental principles of adaptive Intelligent Tutoring System (ITS) design; 2) illustrate how ITS design influences/enables self-regulated learning; and 3) discuss the need for standards for authoring of ITS, modeling of learners and experts, automated instructional strategies, and methods of analysis for ITS technologies.

During computer-based tutoring sessions, Intelligent Tutoring Systems (ITSs) adapt planning and manage real-time instructional decisions. The link between learner data and enhanced performance is the adaptive tutoring learning effect chain through which learner data informs learner state classification which in turn informs optimal instructional decisions to enhance performance. This paper examines the roles and influence of learner data in both short-term (also called run-time or session) and long-term (also called persistent) learner models used to support adaptive tutoring decisions within the Generalized Intelligent Framework for Tutoring (GIFT). To enhance the usability of tutoring systems and learner performance, recommendations for the design of future learner models are also presented.

Famously, individual expert tutoring holds the promise of two standard deviations of improvement over classroom-based instruction. Current content-scaling techniques have been able to prove one standard deviation of improvement. However, just as expert tutors take the motivation and emotional state of the student into account for instruction, so too must computer instructors. Differences between individuals and individual baselines make this difficult, but this information is known across one training session. The construction of assessing modules in realtime, from the available performance and sensor datastreams, skirts these problems, but is technically difficult. This research investigates automated student model construction in realtime from datastreams as a solution from which to base pedagogical strategy recommendations.

In reflecting on a recent emphasis on self-directed learning using game-based simulations and virtual worlds, the authors considered key challenges in transforming serious games and virtual worlds into adaptive training tools. This article reflects specifically on the challenges and potential of cognitive modeling techniques for game-based tutors and game integration with computer-based. Finally, as we integrate tutors and games, a rubric is offered to identify some of the salient characteristics of adaptive game-based, tutoring systems.