TITLE STYLE: 10PT TIMES ROMAN, ALL CAPS, CTR, R



myenglishteacher: a www multi-agent distance learing system of academic english

|ALEXANDRA CRISTEA |TOSHIO OKAMOTO |

AI & KNOWLEDGE ENGINEERING LAB., GRADUATE SCHOOL OF INFORMATION SYSTEMS

University of Electro-Communications

Choufu, Choufugaoka 1-5-1, Tokyo 182-8585, Japan

{alex, okamoto}@ai.is.uec.ac.jp

ABSTRACT

As distances constantly grow smaller and the Internet links remote parts of the world, English gradually becomes the lingua franca for information exchange. Especially in the academic field, in research and development, where international cooperation is necessary, English is used frequently. Academic English is International English. Therefore, one has to be able to understand a multitude of accents from all around the world to be able to function in now-a-days society. However, although accents are more or less variable, the spoken, but mostly, the written academic language has still its rules and etiquette. This paper describes our research on building a free, evolutionary, Internet-based, agent-based, long-distance teaching environment for academic English.

INTRODUCTION

Web English Teaching environments are few, and mostly they imply a fee. However, none of them considers the challenges the non-native English-speaking academician has to face.

Academics usually know some English and have a more or less wide English vocabulary. However, especially in Japan, but in other non-English speaking countries as well, there exists the phenomenon that, although a person can read academic papers in English, when it comes to writing a paper by oneself, or to make an academic presentation in English, serious problems appear. Therefore, we embed these necessary rules and etiquette in our teaching environment. The main aim of our system is to help academics exchange meaningful information with their peers, through a variety of information exchange ways: academic homepages, academic papers, academic presentations, etc. As far as we know, this type of English teaching system is new. Some English teaching environments on the Web appeared, but, as in [Aspera PrivaTeacher] or [EnglishLearner], they have two main defects: they are not free, and/or they are not automatic, but based on real human teachers at the end of the line. Good on-line dictionaries (e.g., [Jeffrey], [Dictionary]) and several collections of English on-line books (e.g., [Bartleby]) exist, but those can only act as auxiliary helpers during the English learning process.

Our aim is to have a system capable to function autonomously, without human interference, as a virtual, long-distance classroom, embedding the necessary tutoring functions within a set of collaborating agents that will serve the student.

The course is called ‘MyEnglishTeacher', because of its evolutionary nature, of adapting over time to the needs and preferences of individual users. These needs can be expressed explicitly, or can be implicitly deduced by the system, represented by its agents. We are currently in the process of adding more AI-based intelligent adaptation capabilities.

Users can find in our virtual classroom situational examples of academic life, presented as Multimedia, with Audio and/or Video presentations, Text explanations and pointers to the main patterns introduced with each lesson, exercises to test the user’s understanding, moreover, adaptive correction, explanation and guidance of the user’s mistakes. The general guidelines for this system were proposed by our course design researcher in [Chen] and elaborated by us in [Cristea].

Here we will describe some of the design and implementation aspects of the system prototype, focusing especially on the intelligent agents that are used for adaptive user feedback: the Global Agent (GlA) and the Personal Agent (PA). We will also describe the Priority and Relatedness Connections Knowledge Base, that is used by these agents in order to give meaningful guidance to the student. Some testing results of the system prototype will be also shown.

The paper is organized as follows. In the next section, we describe the background on which our current research is based, by connecting ours with similar approaches and explaining the differences between them. In the following section 3, we show the main modules and features of our system. Section 4 describes in more detail one of the main modules of our system, the story editor environment, and section 5, the other main module, the learning environment. Section 6 presents a discussion of our present results, shows the orientation of our future research, and draws some conclusions.

BAckground

Virtual environments in education and distance-learning systems are the recent trends in education worldwide. This trend is determined by the current spread of the Internet, as well as by a real demand for better, easy-to-access, and cheaper educational facilities. Therefore, universities everywhere respond to the academic demand for technological and pedagogical support in course preparation, by developing specialized software environments [Collis]. As bandwidths grow, the traditional text environments gradually switch to multimedia and Video-on-Demand (VOD) systems ([Tomek]).

The problems in the current language education systems, as well as the motivation of our research, as pointed out by our language specialist team member and [Levy], can be resumed as follows:

· the lack of learning activities for checking learners’ constructive understanding (requiring the learner not only to memorize, but also to summarize, generate, differentiate, or predict);

· the lack of a variety of problem-solving tasks to motivate students to think about their reading; the learning process does not enable learners to become active participants;

· in the current Computer Aided Language Learning (CALL) systems, learners cannot key-in the target language’s sentences freely;

· lack of explanatory feedback (telling the user why);

· lack of exercises related to the learner’s individual characteristics;

· lack of considerations about the effectiveness of different physical attributes of the presentations, on the students’ learning;

· lack of analysis of the interaction between learner and learning environment, with special focus on assimilation and accommodation.

These problems could not be solved by traditional systems, mostly due to their lack of adaptability, or in other words, intelligence. In [Weiss], it is stated: “there is the need to endow these systems with the ability to adapt and learn, that is, to self-improve their future performance”.

The objective of this research is to help learners achieve academic reading and writing ability. The course is intended for students whose starting English level is intermediate and upper-intermediate, who have some vocabulary of English, but not much practice in using it. The tutoring strategy used is to give the reader insight into his or her implicit or explicit learning strategies. The methodology applied is the communicative teaching approach, allowing communication and interaction between student and tutoring system, via agents. The interactive reading strategies applied and yet to apply include bottom-up theory, top-down theory, and schemata theory. The topics and stories used are mainly passages from textbooks, journals, reference works, conference proceedings, and academic papers, in other words, real-life academic products.

System features and modules

The system is implemented as a multimedia environment for Academic Reading, Writing and Comprehension, allowing text, graphics, audio and video representation of the presented material. Programming and scripting languages used are CGI, Perl, Javascript and Java. Therefore, user browsers accessing it should, generally speaking, support these languages, HTML frames, and should install the free downloadable plug-in for audio and video presentation called ‘Media Player’. The plug-ins for different environments are reachable from within the system environment, so the student-user overhead is kept low.

The system can also be described with the following set of keywords: multimedia language learning system, AI-based knowledge extraction, interactive human - machine communication system.

Figure 1 shows the simplified system overview, represented as a set of interacting modules. The system offers two interfaces, one for the teacher/tutor user, for course-authoring purposes, and the other one for the student user, who is supposed to learn.

The information exchange from tutor to system contains input of lessons, texts, links between them, etc., but also asking for help in editing. The data from the tutor is stored in six different structured databases, including a library of expressions that appear in the text, a VOD database, a background image database, an audio database of listening examples, a full text database and a link database.

The information exchange with the student is more complex. It contains usage of the presented materials, implicit or explicit advice, the student’s advice requests, queries, searches, gathering of data on the student by the two agents, the Global Agent (GlA) and the Personal Agent (PA). Each of these agents has its own database on the student(s). The GlA stores general features on students, and the PA stores the private features of each student.

User modeling follows many patterns, and has many applications. [Di Lascio] proposes a fuzzy-based, stereotype collecting user model for hypermedia navigation. [Virvou] elaborates on the Human Plausible Theory. ([Collins]) provides intelligent help for determining the cause of errors in software usage. [Sa] has shown how prior belief (belief bias) can influence the correctness of judgment of the human (users). Other authors, like [Elliot] have studied the relation between achievement goals, study strategies and exam performance.

A realistic user model has to take into consideration the influences a system can achieve on the user, in order to allow an easy interpretation of the current state, as well as an easy and clear implementation of the user model. We will discuss the user model implementation in more details further on (section 5.1).

The Authoring System Module (Story Editor)

Our most important goal is to design a meaningful, evolutionary feedback for the user. In order to build such a system, an authoring tool is necessary for flexibility purposes: our colleagues researching the optimal material for academic English teaching should be able to add or delete freely the available resources. In a way, they are also clients/users, and should be restricted to build a courseware, which conforms to the capabilities of the system. In the following, these restrictions and their purposes are explained. These restrictions are necessary instruments for the two system agents to work with, as will be shown later in this paper. These structures and restrictions are also reflected by the system feedback, as can be seen in figure 4.

Texts

Each video/audio recording has to have a corresponding TEXT (of dialog, etc.). For each text, it is analyzed if video is necessary, or if audio suffices, as audio requires less memory space and allows a more compact storage and a speedy retrieval. Each TEXT also has (beside of main text, etc.), the following attributes: a short title, keywords, explanation, patterns to learn, conclusion, and finally, exercises.

Titles and keywords are naturally used for search and retrieval, but the explanation and conclusion files can be also used for the same purpose, as will be explained later on (section 4.3).

Lessons

One or more TEXTs (with video or not) make up a LESSON. Each LESSON also has (beside of texts, etc.) the following attributes: title, keywords, explanation, conclusion, combined exercises (generated automatically or not).

Next, a text or a lesson will be referred as ‘SUBJECT’.

Priority and Relatedness Connections

When introducing one or more subjects, the teacher has to specify the Priority Connections, i.e., to show the required learning order, with a directed graph (arrows). When there is no order, subjects will have the same priority, and build a set.

The teacher (courseware author) should also add connections between related SUBJECTS, with indirect links. This means, the teacher has to add Relatedness Connections between subjects, for which no specific learning order is required, but which are related. These relations are useful, e.g., during tests: if one of the subjects is considered known, the other one should be also tested.

The main differences between the priority connections and the relatedness connections is that the first ones are directional, weightless connections, whereas the latter are non-directional, weighted connections. We will discuss the setting of the weights later on in this paper (section 5.2).

After these priorities and links are set, the system will then automatically add more links via keyword matching, from explicit keyword files and keyword search within subjects. Priorities among the texts of a lesson are set implicitly according to the order of the texts, but can be modified, if necessary.

The teacher / multimedia courseware author can decide if it is more meaningful to connect individual texts, or entire lessons, for each lesson. The way a new lesson is introduced, by asking the teacher to set at least the previous and the following lesson in the lesson priority flow, is shown in figure 2 (steps 1,2).

As can be noticed from figure 2, priority connections, with no respective relatedness connection, can exist. This can happen when, e.g., common course design knowledge dictates that respective priority, but the learning contents of the lessons are quite different. These kinds of priorities are optimal student learning strategy related connections, not similar contents connections.

These priorities help the system to place the current subject in the global subject map. Final priorities will be set by the system according to findings (teacher's input, keyword matching). This final result can be shown to the teacher or not, depending on the options under which the system is running. We are currently testing if it is wise to allow the teacher to have add/modify/delete rights. The final graph is used for the student, and it can be shown to the student upon request, serving as a map guide.

Numbering

SUBJECTS are numbered automatically in the order of their creation. Teachers are prohibited to use numbering. This is because otherwise, every time new material is brought, the numbering should be changed according to the new order of priorities.

TEXTs are automatically numbered inside a lesson, and are referred from outside with two numbers: the LESSON number and the text number.

Test Points

The teacher should mark TEST POINTS (figure 2), at which it is necessary to pass a test in order to proceed (these tests can be at any SUBJECT level). Section 5.4 gives more details, explanations and motivations regarding this point.

Important points in courseware design

We are trying to observe the following points we consider important in courseware design:

· to make user think and actively process the input ;

· reading and interaction information and opinion-sharing mechanisms, to encourage intensive reading and to develop top-down reading skills;

· text exploration activities to develop bottom-up skills to make the reader aware of the common discourse features of academic texts;

· application tasks designed to encourage the reader to apply the strategies developed.

The Learning Environment

Student models and agents

The system gradually builds two evolutionary student models: a global student model (GS) and an individual student model (IS), managed by two intelligent agents: the personal agent (PA) and the global agent (GlA). The reason for doing so is that some features, which are common to all students, can be captured in the GS. However, many studies have shown [Tomek] that personalized environments and especially, personalized tutors, have a better chance of transferring the knowledge information from tutor to student. This is true even in the more general sense of a tutor and student, where the tutor can be man or machine, and the student likewise.

In this work, we mean by agent a “computer system situated in some environment”, “capable of autonomous action”, “in the sense that the system should be able to act without the direct intervention of humans”, “and should have control over its own actions and internal state” [Jennings]. These agents’ intelligence is expressed by the fact that each agent “is capable of flexible autonomous action in order to meet its design objectives”, and that it is “responsive” (it perceives its environment), “proactive” (opportunistic, goal-directed), “social” (able to interact) [Jennings], and of an “anticipatory” nature (having a model of itself and the environment, and the capability to pre-adapt itself according to these models) [Ekdahl].

In the following, the raw data stored for the two student models, the GS and IS, is presented.

The GS

The GS contains the global student features:

· the common mistakes;

· favorite pages, lessons, texts, videos, audios, grading of tests’ difficulty (according to how many students do each test well or not);

· search patterns introduced, subjects accessed afterwards: if many IS use the same order, than they are recorded in the GS.

The IS

The IS contains the personal student features:

· the last page accessed;

· grades for all tests taken, mistakes and their frequency; if the student takes the test again and succeeds, his/her last grade is deleted, but his/her previous mistakes are collected for future tests;

· the order of access of texts inside each lesson;

· order of access of lessons (this can be guide to other students: “when another student was in your situation, he/she chose...”);

· frequency of accessing texts/ lessons/ videos/ audios, etc. - for guidance and current state check;

· search patterns introduced, subjects accessed afterwards (to link patterns with new subjects that the system didn't link before).

The PA

The role of the personal agent is to manage the information gathered on the user, and to extract from this information useful user guidance material. Each step taken by the user inside the environment is stored, and compared with both what was proposed to the user, as well as with what the user was expected to do (from the PA’s point of view). The differences between previous expectation and current state are exploited, in order to be used for new guidance generation.

Beside of analyzing the own user and extracting knowledge from the data on him/her, the PA is able to request information from the GlA, about, for instance, what other users chose to do in a similar situation to the current one of the PA’s own user.

Furthermore, the PA can contact other PA’s with similar profiles (after a matchmaking process), and obtain similar information as from the GlA, only with more specificity. The PA can decide to turn to another PA if the information from the GlA is insufficient for a decision about the current support method.

The PA decides, every time a user enters the system, what material should be studied during that particular session, and generates a corresponding list. This can be seen in figure 3, where user chen is offered two lessons. Therefore, the course index is dynamic, not static. To this material, the PA will add or subtract, according to the interaction with the user during the session.

According to [Maes], the PA is therefore an interface agent (“a computer program to provide assistance to a user dealing with a particular computer application” – in this case, a learning environment). However, the PA’s job description is a little wider than this, as can be seen also in the following.

The GlA

The global agent averages information from several users, in order to obtain a general student model. The deductions of the global agent are bound to be non-specific.

The GlA is necessary, because otherwise, the system will not profit from the fact that different users interacted with the system, and each new interaction can smoothen the path for following users.

The GlA is to be referred before the PA starts looking for information from other PAs, process that can be more time-consuming. Therefore, the role of the GlA is to offer to the PAs condensed information, in an easily accessible, swiftly loadable form.

From this description, it is clear that the GlA is subordinate to the PA (from the student user’s point of view). The GlA cannot directly contact the student user – unless the PA explicitly requests it.

If the GlA considers that its intervention is required, it still has to ask for permission from the PA. In this way, the generation of confusing advice is avoided.

Subject material’s relatedness weight computation

The way lessons and texts are connected via a link database was explained previously. In figure 2, these connections and their meaning can be seen. In this section we will first discuss the way the two agents, the GlA and the PA, interact with this link database, then we will give more details on how they interact with each other and the user.

As shown previously, the priority connections between lessons have no weight attached, but the relatedness connections have weights. These weights are changed interactively, as they reflect ‘how connected’ two subjects are. This information is useful for both guiding of the student during learning, as well as for testing the student.

Weights’ values are initialized as strong, when a teacher selects the respective links, and they are weaker, if the system (via the GlA) deduced them out of keyword search information (eq.1). The weights are changed by the GlA, according to the behavior of the students within the ‘MyEnglishTeacher’ environment (eq. 2).

wA,B0=(1: teacher’s selection; 0.5: system’s generation; 0: rest; (1)

wA,B t+tconst = ( wA,B t + f1(no. of times connection A,B activated[1]) +

+ f2(no. of times connection A,B was accepted, when

proposed in relation to unknown subject) +

+ f3(no. of times connection A,B was accepted, when

proposed in relation to query) +

+ f4(no. of times tests related to connection A,B were

solved satisfactorily or not)[2]; (2)

where: (((0,1): forgetting rate; f1~f4: linear functions;

wA,B>0[3]: weight between subjects A and B;

t: time; tconst: period for weight update[4];

It is easy to see from these connections, that related subjects will form cluster-type formations. However, within these clusters, weights expressing the relative relatedness of the cluster components also appear.

The PA of each student makes its own copy of the subject link database, and modifies it for its student, according to his/her independent behavior. These modifications are, just like the modifications of the GlA’s subject database, of evolutionary and adaptive nature.

The PA has to check from time to time with the GlA, in order to decide on possible updates of its own subject database, as the GlA is adaptively reflecting the current average trend in the global subject database.

The PA generates the ‘next learning steps’ (the current index) and the ‘review suggestions’, in two separate windows. The latter contains suggestions to consult lessons and texts, which are connected to the errors which appeared in the student’s current and previous tests.

The PA generates the current index following the normal learning flow set by the priority order. Going in the opposite direction can happen only when the student cannot answer some tests or quizzes satisfactorily. In that case, the review suggestion window activates, as explained, connections to previous subjects, to direct the student to where he/she can fill the gaps in his/her knowledge.

The PA also has to choose between two or more priority links. The usual procedure is to present all of them to the student in their relatedness connection weight order. If no such connections exist, than a random order is assumed. However, the current user’s choices will be recorded by the PA, reported also to the GlA and be reflected in the new connections. That means that the current user’s choices might be recommended to the next user. The ignored, non-related links will appear next time lower on the list.

5.3 Resuming the agents’ structure

From the described interactions between agents and databases, and between the agents themselves, it is clear that the agents of the system work in two ways. The first way is based on the embedded rule/knowledge systems, which try to foresee, prevent and solve conflicting situations. The second way is as evolutionary, learning objects, which can adaptively change their representation of the subject space, by creating and deleting links and changing weights.

A next step in the system’s agents design will be focused on adaptive problem, quiz and test generation. In short, this design is made necessary by the fact that a student, after failing to pass a test, has to be presented, after some more learning is done, with a new test, of similar difficulty and contents. As it is difficult for the teachers to generate as many tests as would be necessary for such repeated situations, this task is to be passed to the system’s agents.

A very important task of each of the agents is also to keep the consistency of the subject link database. The agents inform the teacher(s) if some subjects form loops (determined by the priority connections set by the teacher(s)), if some subjects become inaccessible, etc. Ultimately, when a teacher is not available, they make corrections by themselves, and decide from the student-user(s) feedback about the appropriateness of those changes.

Other Learning environment functioning details

When entering the system for the first time, the student user must register. Figure 3 shows part of the registering interface. To ensure confidentiality, the user must choose a pseudonym (username) and a password, in order to access his/her own profile stored in the system.

The stored data have multiple uses (e.g., to help the GlA and the PA in their decisions, as explained below), but it is mainly used at the moment for identification purposes. If the user forgets his/her username and password, the system can retrieve them, by requesting some of the information provided in this form, e.g., name, e-mail, and birthday.

The information obtained on the user is collected with the purpose of applying the adaptive, evolutionary advising method. Users are not only different at start from one-another, but they also evolve differently in time, their knowledge changes (this being the actual purpose of the teaching system), so the personal user model has to evolve together with its user. This is the job of the personal agent.

After registering, or after confirmation of username and password (in the following sessions), the user can continue his/her study from where he/she stopped last time, as shown in figures 4, 5. The download links (plug-ins), as well as a variety of free, on-line dictionary links (as the ones mentioned in the introduction, and many more), ready to open in a separate window, and to be always handy during learning, are available to the user, presented in a user-friendly interface, as can be seen in the left frame of fig. 4,5.

In addition, for users with little space on their system for a multimedia display, a simplified text-only version is available, which has less capabilities and options but allows a brief overview, not shown here due to lack of space.

In figure 5, the way of combining text with video / sound is shown. The cues that are used in the videos are completely reproduced as texts, for an easy understanding, and for easy search purposes. However, listening-only tests and lessons are possible.

In the following, the role of the TEST POINTS mentioned in section 4.5 is explained. If the student wants to jump one or more subjects, he/she can proceed with only one test, made of a random combination of tests from the previous TEST POINTS, in a proportional relation. If the student fails, another test is generated similarly a number of times (e.g., only one time). If he/she fails again, he/she is given pointers where to return to study, and cannot proceed until the requests are satisfied.

This is because the PA represents a personalized tutor, and, as a tutor, it cannot allow the student to pass any level without taking the respective exams. Therefore, the system is aimed mainly as a learning, and less as a referencing environment (although referencing can be done, assuming the referenced material was previously studied and belongs to the current level, or the levels before). This system behavior was decided due to the complains from teachers and educators that now-a-days systems allow the student too much freedom (unlike the situation in a real classroom), and by trying to be over-flexible, actually have as a result that learning is superficial, and the learner soon gets lost in the presented material.

Next to these obligatory tests, set by the tutor, there are also a number of optional tests available, to help the student evaluate him/her-self. The results of the optional tests are also recorded by the agents, but only to be able to guide the students and detect his/her error patterns.

Beside of the interactions with the user described above, the system also allows the user to leave messages each time it enters the system (so not only in the initial registration phase).

Discussion, conclusions and future research

In this paper we have proposed an Evolutionary, Web-based, Academic English Teaching Environment, called “MyEnglishTeacher”. Moreover, we have described the rationale, the design and implementation of our system. Next, we have showed the modules, which the system should have, in order to function properly: an authoring environment for the teacher user(s), which is generating the lessons, and a learning environment for the student user(s). We have further on presented each of these modules in more details. In particular, the learning environment is based on two intelligent agents, interacting with each other and the student user, in order to guide the student through a new course for academic English, which is under development in our laboratory. We have also explained in which sense our agents evolve and present intelligence. Our agents build and modify student models with the help of a double graph: a non-weighted, directional priority graph, and a weighted, non-directional, relatedness graph.

In addition, we have explained how, from the authoring system courseware design requirements, we enforce the generation of structured content databases, to serve as a basis to the rule/knowledge bases, which will be used and added to by the two agents. Moreover, we have shown the computation and implementation of the weight update function for the relatedness links, and explained its usage. We have shown how, with the priority graph built by the teacher, and the relatedness graph automatically built by the system, the student guidance, direction and orientation inside the multimedia web courseware is made possible. Further on, we have presented some functioning examples of the “MyEnglishTeacher” environment. We have made some preliminary tests of the prototype system, of registration, identification, data processing and automatic course index generation for each user, also some tests of access from within the laboratory and from abroad. Our colleague researching the optimal courseware for the purpose of study of academic English has designed some preliminary lessons, mainly for test purposes. In addition, she has designed a questionnaire for our Japanese colleagues, in order to find out what the main difficulties are, when faced with expressing oneself in English in an academic environment. According to the results of this questionnaire, we intend to further develop the system. Our system is still evolving, and for the next steps, we will focus on the items described below.

· Design tests for our system with real-world situations and real students.

· Extend and implement other AI-related, as well as non-related agent capabilities (for instance, the automatic, intelligent quiz generator, which was just mentioned shortly previously).

· At keyword searches, the PA should also search the web for appropriate patterns - preferably together with the keywords of the student's research interests - to show a "real life" example usage of that pattern, opened in a separate window.

We believe that with our system we are addressing more than one current need: the need of an English tutor for academics, which should also be easily accessible – i.e., on-line –, free, adaptive and user-friendly.

references

Aspera PrivaTeacher,

, Great books on-line,

Chen, J., Okamoto, T. and Li, L. (1999) “The Theoretical Framework for CALL Courseware Development”, Frontiers in Artificial Intelligence and Applications Series, “Advanced Research In Computers And Communications In Education, New Human Abilities for the Networked Society”, Eds. Cumming, G., Okamoto, T., Gomez, L., IOS Press Ohmsha, 723-726.

Collins, A. and Michalski, R. (1989) “The logic of plausible reasoning: A core theory”, Cognitive Science, Vol. 13, 1-49.

Collis, B. (1999) “Design, Development and Implementation of a WWW-Based Course-Support System”, Frontiers in Artificial Intelligence and Applications Series, “Advanced Research In Computers And Communications In Education, New Human Abilities for the Networked Society”, Eds. Cumming, G., Okamoto, T., Gomez, L., IOS Press Ohmsha, 11-18.

Cristea, A., Chen, J. and Okamoto, T. (2000) “An Intelligent language teaching tool for the Web”, Proc. of ISSEI 2000, Bergen, Norway (to appear).

Di Lascio, L., Fischetti, E. and Gisolfi, A. (1999) “A Fuzzy-Based Approach to Stereotype Selection in Hypermedia”, User Modeling and User-Adaptive Interaction, Vol. 9, No.4, Kluwer Academic Publishers, 285-320.

Dictionary,

Ekdahl, B., Astor, E. and Davidsson, P. (1995) “Towards Anticipatory Agents”, Woolridge, M., Jennings, N.R. (Eds.), Theories, Architectures, and Languages, Lecture Notes in Artificial Intelligence, Springer Verlag, 191-202.

Elliot, A.J., McGregor, H.A. and Gable, S. (1999) “Achievement Goals, Study Strategies, and Exam Performance: A Mediator Analysis”, Journal of Educational Psychology, Vol. 91, No.3, 549-563.

EnglishLearner,

Jeffrey’s Japanese-English ó English-Japanese on-line dictionary.

Jennings, N.R. and Wooldridge, M. (1998) “Applications of Intelligent Agents”, Agent Technology Foundations, Applications, and Markets, Springer-Verlag.

Sa, W.C., West, R.F. and Stanovich, K.E. (1999) “The Domain Specificity and Generality of Belief Bias; Searching for a Generalizable Critical Thinking Skill”, Journal of Educational Psychology, Vol. 91, No.3, 497-510.

Levy, M. (1997) “Computer-Assisted Language Learning”, Oxford Claredon Press.

Maes, P. et al. (1993) “Learning Interface Agents”, Proc. of the 11th Nat. Conf. On Artificial Intelligence, AAAI, MIT/AAAI Press.

Tomek, I. (1999) “Virtual Environments in Education”, Frontiers in Artificial Intelligence and Applications Series, “Advanced Research In Computers And Communications In Education, New Human Abilities for the Networked Society”, Eds. Cumming, G., Okamoto, T., Gomez, L., IOS Press Ohmsha, 3-10.

Virvou, M., Du Boulay, B. (1999) “Human Plausible Reasoning for Intelligent Help”, User Modeling and User-Adaptive Interaction, Vol. 9, No.4, Kluwer Academic Publishers, 321-275.

Weiss, G. And Sen, S. (Eds.) (1996) “Adaptation and Learning in Multi-Agent Systems”, Springer Verlag, Lecture Notes in Artificial Intelligence, Vol. 1042.

Fig. 1: The system modules and their interaction

Fig. 2: The subject link database

Fig. 3: A partial view of the registration interface

Fig. 4: The learning environment interface

Fig. 5: A personalized text and corresponding movie

-----------------------

[1] by the user or by other users, depending if it is a weight in the global model or the personal one;

[2] can be positive or negative

[3] if wA,B = 0, the relatedness connection dissapears

[4] the weights are not updated at every move, otherwise computation becomes too time-consuming

-----------------------

- Link DB

...

- Audio DB

- Story DB

- private

student DBs

- general

student DB

- Video DB

- Graphics DB

- Expression DB DBLink datDB

Student user

Teacher user

Learning

Environment

+display

Story Editor

Environment

+display

PA

GlA

Test point

w

Priority

connections

Relatedness

connections

2

1

New Lesson

Text 1

Text 2

...

Text i

...

Text n

Lesson

Text 1

Text 2

...

Text i

...

Text n

Lesson

Text 1

Text 2

...

Text i

...

Text n

Lesson

Text 1

Text 2

...

Text i

...

Text n

Lesson

Text 1

Text 2

...

Text i

...

Text n

................
................

In order to avoid copyright disputes, this page is only a partial summary.

Google Online Preview   Download