The return of intelligent textbooks
Peter BrusilovskyAI Magazine
Sign up for access to the world's latest research
checkGet notified about relevant papers
checkSave papers to use in your research
checkJoin the discussion with peers
checkTrack your impact
Abstract
The advancement of computational Artificial Intelligence (AI) in the recent decade has been transformative for many domains, including AI in Education. One direction, where it has caused a noticeable increase in research activity, is application of AI technologies to enhance digital textbooks by making them more interactive, engaging, adaptive, and intelligent. For many researchers coming into this field, it would have seemed as if an intelligent textbook is a completely new idea. We would like to provide a historic outlook on this field and outline the important phases that it went through over the last three decades. We hope that such an account can inform interested readers and help them better understand the problems and the approaches of intelligent textbooks.
Related papers
The Intelligent Book: technologies for intelligent and adaptive textbooks, focussing on Discrete Mathematics
2008
This dissertation is not an Intelligent Book. It uses the same words to say the same thing to every reader regardless of whether or not they can understand it. It cannot help readers to work through example problems and it cannot say anything that is not already in the book. In many situations, a static unintelligent book like this is appropriate. This thesis has to be examined and that would be much harder to do if it changed every time it was read.
AI and voice-powered e-textbooks and e-books
International Journal of Social Science and Economic Research, 2020
Reading, whether as an end in itself as in language arts classes or as a means for learning when done through textbooks, has long been an integral part of classroom education. As much of the information world has moved online, so, too, have books followed. Unfortunately, commercially-available electronic textbooks (e-textbooks) and electronic books (e-books) are typically little more than .pdf versions of their paper counterparts, thus not exploiting other technologies that could be used to increase learning. The present paper describes technologies that use artificial intelligence (AI) and voice/natural language technologies to increase student learning in e-textbooks and e-books. As students learn a lesson, they can verbally ask the technology questions about the content and receive answers much the way they can when using personal assistants on smart phones. When students have completed the material, the technology assesses whether they have learned the material by verbally asking questions and allowing students to answer verbally. Any deficiencies are immediately remediated. When students finish the assessment in the e-textbook, they do practice problems as they would in a standard etextbook. The difference is that with the present technology, all work is done step-by-step on an electronic worksheet where the underlying AI technology monitors each step and provides hints when requested and feedback when mistakes are made. The present e-textbook technology was
Intelligent-Textbooks
L earning a scientific discipline such as biology is a daunting challenge. In a typical advanced high school or introductory college biology course, a student is expected to learn about 5000 concepts and several hundred thousand new relationships among them. 1 Science textbooks are difficult to read and yet there are few alternative resources for study. Despite the great need for science graduates, too few students are willing to study science and many drop out without completing their degrees. New approaches are needed to provide students with a more usable and useful resource and to accelerate their learning.
Introduction World-Wide Intelligent Textbooks
2003
New WWW technologies allow for integrating distance education power of WWW with interactivity and intelligence. Integrating on-line presentation of learning materials with the interactivity of problem solving environments and the intelligence of intelligent tutoring systems results in a new quality of learning materials that we call 13_ textbooks. In this paper, we describe the development of ELM-ART, an I 3 -textbook for learning programming that can be accessed via Internet and that is based on the on-site learning environment ELM-PE. Distance learning with Internet opens new ways of learning for many people. Now, educational programs and learning materials installed and supported in one place can be used by thousands of students from all over the world. World Wide Web (WWW) and WWW browsers provide a good example of powerful modern Internet facilities. Using WWW, a novice user can comfortably browse the Internet finding required pieces of information in different locations worldw...
MULTIPLE INTELLIGENCE BASED E-BOOKS
2001
This paper describes a study on the design of teaching-learning materials and the use of technology in school environment. One essential component of this study is the definition of models on how electronic textbooks (e-books), one of the fundamental tools in the school recently, should be designed to be practiced. We postulate that a crucial feature for children e-books would be to present contents by mixing different presentation modes (graphic page, talking page, hypermedia page and web page modes) and including various activities in each mode which support and nurture as many children's intelligences and learning styles as possible.
Automatic Concept Extraction for Domain and Student Modeling in Adaptive Textbooks
International Journal of Artificial Intelligence in Education, 2020
The increasing popularity of digital textbooks as a new learning media has resulted in a growing interest in developing a new generation of adaptive textbooks that can help readers to learn better through adapting to the readers' learning goals and the current state of knowledge. These adaptive textbooks are most frequently powered by internal knowledge models, which associate a list of unique domain knowledge concepts with each section of the textbook. With this kind of concept-level knowledge representation, a number of intelligent operations could be performed, which include student modeling, adaptive navigation support, and content recommendation. However, manual indexing of each textbook section with concepts is challenging, time-consuming, and prone to errors. Modern research in the area of natural language processing offers an attractive alternative, called automatic keyphrase extraction. While a range of keyphrase and concept extraction methods have been developed over the last twenty years, few of the known approaches were applied and evaluated in a textbook context. In this paper, we present FACE, a supervised feature-based machine learning method for automatic concept extractions from digital textbooks. This method has been created for building domain and student models that form the core of intelligent textbooks. We evaluated FACE on a newly constructed full-scale dataset by assessing how well it approximates concept annotations produced by human experts and how well it supports the needs of student modeling. The results show that FACE outperforms several state-of-the-art keyphrase extraction methods.
Creating Adaptive Textbooks with AHA!(An Interactive RoundTable)
2008
AHA! stands for the Adaptive Hypermedia Architecture, an adaptive authoring and delivery platform developed as part of the Adaptive Hypermedia for All (or AHA!) project. (See http://aha.win.tue.nl/.) Adaptation in on-line textbooks makes it possible for learners to study the textbook in different ways without encountering difficulties. Link hiding and annotation guide users towards subjects they are "ready" to study. Adaptive sequencing or sorting helps them decide on a reading order for pages that teach them about a given concept. Conditional inclusion of fragments and stretchtext make it possible to provide additional or prerequisite explanations when needed or desired. In this roundtable (paper) we discuss the authoring process for adaptive textbooks created with AHA!. We cover the different authoring tools for concepts, concept relationships (like prerequisites) and adaptive object inclusion (for additional explanations). We also cover the process of completing an application by creating content pages in standard XHTML (or in XHTML+SMIL or SMIL 2.0) and by setting up a server. AHA! applications can also be created using other authoring tools, including Interbook (Brusilovsky et al, 1998) and MOT (Cristea et al, 2003), but this is described elsewhere.
Supporting teachers as content authors in intelligent educational systems
International Journal of Knowledge and Learning, 2006
Intelligent Educational Systems (IESs) need large amounts of educational content that is typically not provided by the creators of these systems. In this paper we discuss a new approach for authoring practical IESs where core authoring is done by professional design teams, while the educational content is mainly developed by teachers who use the system in their classes. The major bottleneck of this approach is the lack of intelligent authoring support tools that allow regular teachers to author intelligent content that an IES needs in order to perform its functions. As a contribution to solving this problem, we present our recent work on authoring support for an adaptive vocabulary acquisition system, ELDIT. The paper describes the ELDIT system, the needs and challenges of language content authoring by teachers, and the two authoring support components that we have developed for two essential kinds of language learning content: illustrative examples and educational texts.
Artificial Intelligence in Education Editors
Mithra Publication Tamil Nadu, 2024
Artificial Intelligence in Education: The ground-breaking edited work "Transforming Pedagogical Practices, Administrative Efficiency, and Learning Experiences" examines how artificial intelligence affects modern education. Internationally diverse scholars and educational experts unite in this publication to explore how AI transforms modern learning conditions and educational procedures worldwide. The edited book presents its content through twenty-four individual sections which examine different applications of AI in educational systems. The initial sections excavate the capacity of AI to develop interactive educational experiences and strengthen emotional thinking while advancing social learning. Through these chapters we learn about how artificial intelligence enables educational systems to provide better personalized interactive learning and responsive assessments. The book evaluates how artificial intelligence advances both educational administration through data management and predictive analytics as well as decision-making capabilities that boost institutional efficiency. The AI's ethical dimensions through assessments which focus on technology distribution fairness while protecting educational data integrity. This manual presents a thorough exploration of the digital revolution happening in the educational sector. This resource combines theoretical frameworks with practical examples that confirm its status as an essential knowledge tool for educational administrators and policy creators and academic researchers studying future educational systems using AI technologies.
Related topics
Related papers
Concept Annotation for Intelligent Textbooks
ArXiv, 2020
With the increased popularity of electronic textbooks, there is a growing interests in developing a new generation of "intelligent textbooks", which have the ability to guide the readers according to their learning goals and current knowledge. The intelligent textbooks extend regular textbooks by integrating machine-manipulatable knowledge such as a knowledge map or a prerequisite-outcome relationship between sections, among which, the most popular integrated knowledge is a list of unique knowledge concepts associated with each section. With the help of this concept, multiple intelligent operations, such as content linking, content recommendation or student modeling, can be performed. However, annotating a reliable set of concepts to a textbook section is a challenge. Automatic unsupervised methods for extracting key-phrases as the concepts are known to have insufficient accuracy. Manual annotation by experts is considered as a preferred approach and can be used to produce...
Enriching Intelligent Textbooks with Interactivity: When Smart Content Allocation Goes Wrong
Fourth Workshop on Intelligent Textbooks (iTextbooks' 2022), 2022
One of the main directions of increasing the educational value of a digital textbook is its enrichment with interactive content. Such content can come from outside the textbooks - from multiple existing repositories of educational resources. However, finding the right place for such external resources is not always a trivial task. There exist multiple sources of potential problems: from mismatching metadata to mutually contradicting prerequisite-outcome structures of underlying resources, from differences in granularity and coverage to ontological conflicts. In this paper, we make an attempt to categorize these problems and give examples from our recent experiment on automated assignment of smart interactive learning content to the chapters of an intelligent textbook in a programming domain.
Intelligent tutoring systems D. Sleeman and J.S. Brown, (Academic Press, New York, 1982); 345 pages, $39.50
Artificial Intelligence, 1985
Intelligent Tutoring Systems: Past, Present, and Future.
1994
Abstract: In this paper, we address many aspects of Intelligent Tutoring Systems (ITS) in our search for answers to the following main questions;(a) What are the precursors of ITS?(b) What does the term mean?(c) What are some important milestones and issues across the 20+ year history of ITS?(d) What is the status of ITS evaluations? and (e) What is the future of ITS? We start with an historical perspective.
Brusilovsky, P., Knapp, J., and Gamper, J. (2006) Supporting teachers as content authors in intelligent educational systems. International Journal of Knowledge and Learning 2 (3/4), 191-215.
Intelligent Educational Systems (IESs) need large amounts of educational content that is typically not provided by the creators of these systems. In this paper we discuss a new approach for authoring practical IESs where core authoring is done by professional design teams, while the educational content is mainly developed by teachers who use the system in their classes. The major bottleneck of this approach is the lack of intelligent authoring support tools that allow regular teachers to author intelligent content that an IES needs in order to perform its functions. As a contribution to solving this problem, we present our recent work on authoring support for an adaptive vocabulary acquisition system, ELDIT. The paper describes the ELDIT system, the needs and challenges of language content authoring by teachers, and the two authoring support components that we have developed for two essential kinds of language learning content: illustrative examples and educational texts.
Advancements of Artificial Intelligence in Education: Overview
AI has offered a total shift in the educational world. From spotting different learning styles, to multiple intelligences, reaching mental and physical disabilities, AI has helped in soothing the learning and teaching experience. It is offering learners opportunities to learn better and peruse their objectives (Schmelzer, 2019). Some advancements that AI added to the educational field can be summed as follows.
BBookX: Creating Semi-Automated Textbooks to Support Student Learning and Decrease Student Costs
2019
Open educational resources (OERs) are increasingly looked to as one approach for reducing costs and increasing access to educational materials. Unfortunately, developing OERs and operationalizing their use is fraught with difficulty. Users are challenged to search OER repositories for materials that are content-appropriate and high quality. Our team developed a new semi-automated text-authoring tool, BBookX [1, 2] to address these issues. We introduce BBookX, and discuss the utilization of a book generated using BBookX in an introductory information sciences and technology course. Survey results from students who used the book, as well as who engaged in creating their own books using BBookX, are presented. While BBookX has not been adopted for the use of creating open textbooks, the AI powering BBookX, along with faculty user testing, has led to similar derivative works in development to assist teachers with identifying relevant educational content and in creating assessments.
Transformation of PDF Textbooks into Intelligent Educational Resources
2020
The paper presents Intextbooks the system for automated conversion of PDF-based textbooks into intelligent educational Web resources. The papers focuses on the new component of Intextbooks responsible for transformation of PDF-based content into semanticallyannotated HTML/CSS. The architecture of the system, the design of the client application rendering resulting textbooks and a short validation experiment demonstrating the quality of the transformation workflow are presented.
Survey of Intelligent Tutoring Systems Up To the End of 2016
2019
The main goals of Intelligent Tutoring Systems (ITS) are: providing highly developed instructional guidance on a one-toone foundation that is improved than what is attained with traditional computer aided instruction and is analogous to that of a decent human tutor; and developing and testing models of intelligent processes associated with instruction. ITS is a subfield of artificial intelligence. ITS consists of four interacting components: the student model which embodies the student's present knowledge state, the pedagogical module which comprises appropriate instructional measures which are depending on the content of the student model, the knowledge model which contains the domain knowledge, and the user interface model which permits an effective dialog among ITS and the user. Usually, the knowledge model is the central part in the instructional process but there is a diversity of approaches that also put the stress on the other components. In this paper we have surveyed 55...
Authoring Intelligent Tutoring Systems: An Analysis of the State of the Art
This paper consists of an in-depth summary and analysis of the research and development state of the art for intelligent tutoring system (ITS) authoring systems. A sevenpart categorization of two dozen authoring systems is given, followed by a characterization of the authoring tools and the types of ITSs that are built for each category. An overview of the knowledge acquisition and authoring techniques used in these systems is given. A characterization of the design tradeoffs involved in building an ITS authoring system is given. Next the pragmatic questions of real use, productivity findings, and evaluation are discussed. Finally, I summarize the major unknowns and bottlenecks to having widespread use of ITS authoring tools.
Loading Preview
Sorry, preview is currently unavailable. You can download the paper by clicking the button above.