Rule-based expert systems to support step-by-step guidance in algebraic problem solving: The case of the tutor PAT2Math

In order for an Intelligent Tutoring System (ITS) to correct students’ exercises, it must know how to solve the same type of problems that students do and the related knowledge components. It can, thereby, compare the desirable solution with the student’s answer. This task can be accomplished by an expert system. However, it has some drawbacks, such as an exponential complexity time, which impairs the desirable real-time response. In this paper we describe the expert system (ES) module of an Algebra ITS, called PAT2Math. The ES is responsible for correcting student steps and modeling student knowledge components during equations problem solving. Another important function of this module is to demonstrate to students how to solve a problem. In this paper, we focus mainly on the implementation of this module as a rule-based expert system. We also describe how we reduced the complexity of this module from O(n^d) to O(d), where n is the number of rules in the knowledge base, by implementing some meta-rules that aim at inferring the operations students applied in order to produce a step. We evaluated our approach through a user study with forty-three seventh grade students. The students who interacted with our tool showed statistically higher scores on equation solving tests, after solving algebra exercises with PAT2Math during an approximately two-hour session, than students who solved the same exercises using only paper and pencil.     

Why fifth- and seventh-graders submit off-task responses to a web-based reading comprehension tutor rather than expected learning responses

Research shows the students improve their reading comprehension with Intelligent Tutoring of the Structure Strategy (ITSS). One problem for ITSS is that some students are producing responses in the on-line instruction that are unrelated to learning and practicing the reading strategy. These types of disengaged responses can be referred to as system active off-task responses (“off-task”). In this study we characterize who produces off-task responses and why. Classification and Regression Trees (C&RT) and logistic regression analyses were used to answer the why question. Variables predicted to relate to gaming included reading strategy and skill variables, motivation, attitude, self-efficacy, and goal orientation variables, demographic variables, and type of computer feedback (simple versus elaborated). C&RT analysis could explain 66% of the variance in off-task responses. Students without off-task responses were higher in motivation to read and worked in ITSS to produce good main ideas. Students with higher off-task responses had low scores on work mastery goals. The highest producers of off-task responses in Grades 5 and 7 (averaging 24 off-task responses over 7 lessons) had low motivation to read and scored over 2 SD below average on recall tasks in ITSS. The logistic regression could explain 42% of the variance in off-task responses. Use of motivational scales prior to starting instruction as well as on-line performance measures could be used to flag students for early intervention to prevent system active off-task responses and increase on-line learning. The C&RT approach may be particularly helpful to designers in making software more appropriate for different types of students.     

Learning how to write effectively for academic journals: A case study investigating the design and development of a genre-based writing tutorial system

Genre-based writing instruction (GBWI) has been used for English journal paper writing both in classroom teaching and in the development of materials utilizing move analysis and corpus-based analysis. Some writing systems and tutorials have also been developed to improve the writing of non-native English speakers (NNES), as well as to assist academics and researchers for their publications. However, most of these systems had been developed for certain aspects of academic journal writing, such as organizing references, preventing plagiarism, or finding appropriate collocations. Accordingly, EJP-Write, a Chinese-interfaced writing system for English academic journal writing, was developed based on GBWI to teach and assist journal writing in a user-friendly environment.The present study aimed to investigate the perceived usefulness (content effectiveness) and perceived usability (system functionality) of EJP-Write, and identify other factors that might influence user attitudes and continued usage intention. Data was collected via questionnaire (N = 35) and structural equation modeling (SEM) was conducted for fitness estimation on the modified Technology Acceptance Model (TAM). Semi-structured interviews were also conducted to collect additional information for usefulness and usability evaluation (N = 14). Regarding perceived usefulness, the results show that participants felt the EJP-Write content was useful and effective in teaching genre and move structure because of the aid of various forms of support and examples such as phrase and paragraph templates. Additionally, the learning materials for verb tenses and citation formats were informative and practical for the participants to avoid grammatical and technical errors. However, the move structure provided was limited to the discipline of e-learning and education; thus, move analysis for different fields was suggested. Regarding perceived usability, the citation-related features in EJP-Write were particularly well-regarded. Participants also provided suggestions to improve online editing and outline developing features in the system. Factors found to influence user attitudes, and thus the intention of continued use, were usefulness and usability, while writing anxiety and personalization had less impact.Findings of the quantitative and qualitative data analysis in the study suggest that EJP-Write can play multiple roles inside or outside of the classroom, both as a platform integrating most features essential for journal paper writing, and as a teacher providing guidance and learning materials necessary for this specific genre. It is anticipated that this study will contribute to the knowledge base about both content and interface design for journal paper writing in the discipline of e-learning and education. For program designers of web-based writing tutorials, the involvement of users in the development of move structure could both strengthen various GBWI approaches and solve issues related to disciplinary differences.     

The development of an ESL OWL, or learning how to tutor writing online

This essay describes the development of an ESL OWL by grounding practices in language and literacy pedagogy theory. An initial discussion explores OWLs emulating physical writing center spaces. Two areas of concern are then addressed in meeting the needs of second language writers as they relate to practices and training for online tutoring: error correction—an area of frequent concern to second language writers—and increased interactivity—meeting second language writer expectations and creating autonomous learners. Issues of plagiarism by second language writers are discussed as related to the type of feedback OWL tutors can provide. Highlighted throughout are samples of interactions between tutors and writers that show a process of learning how to create dialogue rather than dictations from the tutor to clean up a single essay.     

Development of a reading material recommendation system based on a knowledge engineering approach

In a language curriculum, the training of reading ability is one of the most important aspects. Previous studies have shown the importance of assigning proper articles to individual students for training their reading ability; nevertheless, previous experience has also shown the challenges of this issue owing to the complexity of personal factors as well as the diverse properties of the candidate articles to be taken into consideration. This study proposes a knowledge engineering approach for developing reading material recommendation systems by eliciting domain knowledge from multiple experts. Experimental results on 29 senior high school students show that the developed system is able to provide expert-like recommendations to the students by taking preferences and knowledge levels of individual students as well as categories and traits of articles into consideration.     

eTeacher: Providing personalized assistance to e-learning students

In this paper we present eTeacher, an intelligent agent that provides personalized assistance to e-learning students. eTeacher observes a student’s behavior while he/she is taking online courses and automatically builds the student’s profile. This profile comprises the student’s learning style and information about the student’s performance, such as exercises done, topics studied, exam results. In our approach, a student’s learning style is automatically detected from the student’s actions in an e-learning system using Bayesian networks. Then, eTeacher uses the information contained in the student profile to proactively assist the student by suggesting him/her personalized courses of action that will help him/her during the learning process. eTeacher has been evaluated when assisting System Engineering students and the results obtained thus far are promising.     

Design and usability testing of a learning and plagiarism avoidance tutorial system for paraphrasing and citing in English: A case study

The prevalence of information and communication technology (ICT) has considerably converted the means of/for publication and circulation, as well as transforming academia and English pedagogy. However, with the availability and convenience of online resources, one of the critical issues emerged is that non-native English speakers are constantly accused of committing textual plagiarism: either intentionally or unintentionally. While many writing tools and plagiarism detectors are available to help solve the problem, none of them were customized for the great population of Chinese learners of English. Accordingly, DWright—a Chinese-interfaced online writing tutorial for paraphrasing and citing English—was developed in the hope of ensuring academic integrity through the avoidance of textual plagiarism.The purpose of this study was to evaluate the design and efficacy of DWright regarding plagiarism prevention and improvement of English writing. A questionnaire and semi-structured interview were administrated to participants to test DWright and its technology acceptance model (TAM) to identify the effect of perceived usefulness, usability and user attitudes of DWright. Results show that users of DWright were in high agreement regarding the content effectiveness of all DWright-based tasks, indicating the reading activities, multiple-choice exercises and paraphrasing practices were effective to help users enhance writing knowledge and skills to avoid plagiarism. Furthermore, perceived usefulness and system usability affected DWright user attitudes significantly and positively, which mirrors their attitudes toward continued use of DWright. In this study, DWright met its users' needs by extending their knowledge to avoid plagiarism while simultaneously enhancing their paraphrasing and writing skills. The conclusion suggests that tutorial designers, content experts and subject teachers should support effective communication to improve content usefulness, so as to help users achieve their writing goals with a research proven learning and plagiarism avoidance tutorial system.     

Computer-based tutoring of visual concepts: from novice to expert

Abstract Computer-based tutoring of visual concepts is a largely unexplored area. The ability to classify images, to identify features and to describe abnormalities is a necessary part of training in many professions, such as radiology, anatomy, botany and geology. To a lesser level it is important for developing everyday skills such as identifying birds, trees, rocks, and flowers. The aim of this paper is to show how computers might be used in visual concept teaching, to store and display large stocks of exemplar images, to carry out a tutorial dialogue with the learner, and to provide learning aids such as concept maps, feature spaces, and structural models. The paper describes well-established methods for teaching visual concepts and indicates how computers can supplement the human teacher in tutoring students with differing levels of expertise.     

Artificial intelligence approach to support statistical quality control teaching

Statistical quality control – SQC (consisting of Statistical Process Control, Process Capability Studies, Acceptance Sampling and Design of Experiments) is a very important tool to obtain, maintain and improve the Quality level of goods and services produced by an organization. Despite its importance, and the fact that it is taught in technical and college courses, as well as in companies’ training sectors, SQC has been largely misused. An inappropriate teaching approach may be the cause of such problem; therefore it has motivated the development of a model for SQC teaching, allowing its learners to correctly apply SQC techniques. After a survey regarding the concept needed to correctly apply SQC, its use and teaching/training methods, the model’s contents and methodology were defined. We also realized the opportunity of incorporating a computer environment for the model, permitting the practice of the needed SQC concepts and skills. An Artificial Intelligence approach was used to develop the computer environment, resulting in an Intelligent Tutoring System, the STCEQ. The paper discusses the main characteristics of the system, its functioning, benefits of using such a system and the results we obtained while using this system.     

Data mining for providing a personalized learning path in creativity: An application of decision trees

Customizing a learning environment to optimize personal learning has recently become a popular trend in e-learning. Because creativity has become an essential skill in the current e-learning epoch, this study aims to develop a personalized creativity learning system (PCLS) that is based on the data mining technique of decision trees to provide personalized learning paths for optimizing the performance of creativity. The PCLS includes a series of creativity tasks as well as a questionnaire regarding several key variables. Ninety-two college students were included in this study to examine the effectiveness of the PCLS. The experimental results show that, when the learning path suggested by a hybrid decision tree is employed, the learners have a 90% probability of obtaining an above-average creativity score, which suggests that the employed data mining technique can be a good vehicle for providing adaptive learning that is related to creativity. Moreover, the findings in this study shed light on what components should be accounted for when designing a personalized creativity learning system as well as how to integrate personalized learning and game-based learning into a creative learning program to maximize learner motivation and learning effects.     

Designing a smartphone app to teach English (L2) vocabulary

The researcher developed a Basic4Android smartphone app (named as Word Learning-CET6) and investigated its effectiveness as a tool in helping English as a Foreign Language college students learn English vocabulary. The app, containing 1274 English words, was designed to be installed into smartphones with Android operating system. To test the program's effectiveness, two groups of students were set up as a test group (those with Word Learning-CET6) and a control group (those without Word Learning-CET6). Knowledge of the vocabulary was tested before and after the study to assess the impact of the program. The study showed that the students using the program significantly outperformed those in the control group in acquiring new vocabulary. At the conclusion of this study, the researcher designed an app and established a pedagogical paradigm which can be followed as a way of mobile learning.     

Identifying students’ mathematical skills from a multiple-choice diagnostic test using an iterative technique to minimise false positives

There is anecdotal evidence that a significant number of students studying computing related courses at degree level have difficulty with sub-GCE mathematics. Testing of students’ skills is often performed using diagnostic tests and a number of computer-based diagnostic tests exist, which work, essentially, by testing one specific diagnostic skill at a time.     

A Tutor Assisting Novel Electronic Framework for Qualitative Analysis of a Question Bank

The traditional approach followed by tutors to assess the students is through a set of questions. The quality of a question bank has an impact on the effectiveness of evaluation in educational institutions. Determining the coverage of these questions with respect to a set of prescribed text/reference books helps in evaluating students efficiently. In this paper, we describe a Tutor Assisting e-Framework (TAeF) that enables the tutors to analyze the quality of a question bank. Initially, it clusters all individual topics of each of the input text/reference books according to their dependencies. Later, the questions are classified into these topics. The result is a set of topics, each containing the topic title and the probability by which the question is related to it. Lower the accuracy of the predicted topics, higher is the quality of the question. In other words, if question contains the topic title unaltered, it has a higher probability of being related to the topic; this degrades the quality of question. Furthermore, the congruence relation between the questions and the set of topics is found. This gives the question coverage of each topic. Finally, with this relation, the percentage of understanding the students have developed in each of these topics is computed. The Tutor Assisting e-Framework (TAeF) helps to improve the quality of a question bank, to check the topics covered by each question and the knowledge gained.     

Evaluation of a meta-tutor for constructing models of dynamic systems

Modelling is an important skill to acquire, but it is not an easy one for students to learn. Existing instructional technology has had limited success in teaching modelling. We have applied a recently developed technology, meta-tutoring, to address the important problem of teaching model construction. More specifically, we have developed and evaluated a system that has two parts, a tutor and a meta-tutor. The tutor is a simple step-based tutoring system that can give correct/incorrect feedback on student's steps and can demonstrate steps for students when asked. Because deep modelling requires difficult analyses of the quantitative relationships in a given system, we expected, and found, that students tended to avoid deep modelling by abusing the tutor's help. In order to increase the frequency of deep modelling, we added a meta-tutor that coached students to follow a learning strategy that decomposed the overall modelling problem into a series of “atomic” modelling problems. We conducted three experiments to test the effectiveness of the meta-tutor. The results indicate that students who studied with meta-tutor did indeed engage in more deep modelling practices. However, when the meta-tutor and tutor were turned off, students tended to revert to shallow modelling. Thus, the next stage of the research is to add an affective agent that will try to persuade students to persist in using the taught strategies even when the meta-tutoring and tutoring have ceased.     

Task results processing for the needs of task-oriented design environments

This paper presents learners’ task results gathered by means of an example task-oriented environment for knowledge testing and processed by EXCEL. The processing is domain- and task-independent and includes automatic calculation of several important task and session’s parameters, drawing specific graphics, generating tables, and analyzing the correlation coefficient. The intention is to design and implement a specialized tool called postprocessor for support of a common task base, learner’s model and decision making of the author and teacher by means of an environment for individually planned teaching courseware.     

Conceptual indexing and active retrieval of video for interactive learning environments

Selecting an instructive story from a video case base is an information retrieval problem, but standard indexing and retrieval techniques [1] were not developed with such applications in mind. The classical model assumes a passive retrieval system queried by interested and well-informed users. In educational situations, students cannot be expected to form appropriate queries or to identify their own ignorance. Systems that teach must, therefore, be active retrievers that formulate their own retrieval cues and reason about the appropriateness of intervention.

The Story Producer for InteractivE Learning (SPIEL) is an active retrieval system for recalling stories to tell to students who are learning social skills in a simulated environment [2, 3]. SPIEL is a component of the Guided Social Simulation (GuSS) architecture [4] used to build YELLO, a program that teaches account executives the fine points of selling Yellow Pages advertising. SPIEL uses structured, conceptual indices derived from research in case-based reasoning [5, 6]. SPIEL's manually-created indices are detailed representations of what stories are about, and they are needed to make precise assessments of stories' relevance.

SPIEL's opportunistic retrieval architecture operates in two phases. During the storage phase, the system uses its educational knowledge encapsulated in a library of “storytelling strategies” to determine, for each story, what an opportunity to tell that story would look like. During the retrieval phase, the system tries to recognize those opportunities while the student interacts with the simulation. This design is similar to “opportunistic memory” architectures proposed for opportunistic planning [7, 8].     

Using a hybrid rule-based approach in developing an intelligent tutoring system with knowledge acquisition and update capabilities

In this paper, we present the architecture and describe the functionality of an Intelligent Tutoring System (ITS), which uses an expert system to make decisions during the teaching process. The expert system uses neurules for knowledge representation of the pedagogical knowledge. Neurules are a type of hybrid rules integrating symbolic rules with neurocomputing. The expert system consists of three components: the user modelling unit, the pedagogical unit and the inference system. The pedagogical knowledge is distributed in a number of neurule bases within the user modelling and the pedagogical unit. Another important component of the ITS, for both its development and maintenance, is its knowledge management unit, which provides knowledge acquisition and knowledge update capabilities to the system, that is, offers expert knowledge authoring capabilities to the system.     

Using Co-Lab to build System Dynamics models: Students’ actions and on-line tutorial advice

Modeling offers a promising form of constructivist learning for students. By making and executing models of dynamic systems in a computer environment, students are stimulated to learn about the specific domain that is modeled as well as about the process of modeling in general. However, learning by modeling also leads to characteristic student mistakes, based on a combination of faulty domain knowledge and insufficient modeling skills. In this article, we describe a method of generating advice to students during their modeling process. The on-line advice system was informed by our observations of a teacher who gave advice via a textual communication tool to students building models with a System Dynamics model editor. The first version of the on-line advice system was evaluated in two ways: first, three teachers evaluated the advice the system generated for students’ final solutions; second, we analyzed the advice the system provided as it was used by a sample of students who were building a physics model. These evaluations showed that the overall approach, including matching a student solution to a family of reference solutions together with the other mechanisms of the advice system, is valid. However, they also highlighted the difficulty of building ‘intelligent’ support to help students to improve their models and gain modeling expertise. The article concludes with a discussion of our current efforts to improve the advice system based on the lessons learnt, which suggest extension of the range of solution representations and of the operations of the advice method.     

Applying learning behavioral Petri nets to the analysis of learning behavior in web-based learning environments

This paper proposes the learning behavioral Petri nets (LBPN) to model learning behavior in web-based environments. Fully useful records of learning behaviors must contain their expended time and corresponding contents. Therefore, the LBPN extends the colored tokens of colored Petri nets to identify learners and learning contents, and raises the time variable to represent diverse learning times for individual learners. To verify the viability of the LBPN, this paper also proposes a LBPN-based learning behavioral model to simulate a situation in which many learners participate in an e-learning course, and then to generate their behavioral patterns. The experimental results illustrated in this paper confirm that (1) the generated behavioral pattern based on the LBPN-based model is very close to actual data, (2) the time and cost spent to verify the effectiveness of an ITS is substantially reduced, (3) adequate testing data for estimating the performance and accuracy of an ITS is easily acquired, and (4) the LBPN-based model can be built to recommend appropriate learning contents and to accomplish adaptive learning.