Dr Math is a math tutoring service implemented on the chat application Mxit. The service allows school learners to use their mobile phones to discuss mathematicsrelated topics with human tutors. Using the broad user-base provided by Mxit, the Dr Math service has grown to consist of tens of thousands of registered school learners. The tutors on the service are all volunteers and the learners far outnumber the available tutors at any given time. School learners on the service use a shorthand language-form called microtext, to phrase their queries. Microtext is an informal form of language which consists of a variety of misspellings and symbolic representations, which emerge spontaneously as a result of the idiosyncrasies of a learner. The specific form of microtext found on the Dr Math service contains mathematical questions and example equations, pertaining to the tutoring process. Deciphering the queries, to discover their embedded mathematical content, slows down the tutoring process. This wastes time that could have been spent addressing more learner queries. The microtext language thus creates an unnecessary burden on the tutors. This study describes the development of an automated process for the translation of Dr Math microtext queries into mathematical equations. Using the design science research paradigm as a guide, three artefacts are developed. These artefacts take the form of a construct, a model and an instantiation. The construct represents the creation of new knowledge as it provides greater insight into the contents and structure of the language found on a mobile mathematics tutoring service. The construct serves as the basis for the creation of a model for the translation of microtext queries into mathematical equations, formatted for display in an electronic medium. No such technique currently exists and therefore, the model contributes new knowledge. To validate the model, an instantiation was created to serve as a proof-of-concept. The instantiation applies various concepts and techniques, such as those related to natural language processing, to the learner queries on the Dr Math service. These techniques are employed in order to translate an input microtext statement into a mathematical equation, structured by using mark-up language. The creation of the instantiation thus constitutes a knowledge contribution, as most of these techniques have never been applied to the problem of translating microtext into mathematical equations. For the automated process to have utility, it should perform on a level comparable to that of a human performing a similar translation task. To determine how closely related the results from the automated process are to those of a human, three human participants were asked to perform coding and translation tasks. The results of the human participants were compared to the results of the automated process, across a variety of metrics, including agreement, correlation, precision, recall and others. The results from the human participants served as the baseline values for comparison. The baseline results from the human participants were compared with those of the automated process. Krippendorff’s α was used to determine the level of agreement and Pearson’s correlation coefficient to determine the level of correlation between the results. The agreement between the human participants and the automated process was calculated at a level deemed satisfactory for exploratory research and the level of correlation was calculated as moderate. These values correspond with the calculations made as the human baseline. Furthermore, the automated process was able to meet or improve on all of the human baseline metrics. These results serve to validate that the automated process is able to perform the translation at a level comparable to that of a human. The automated process is available for integration into any requesting application, by means of a publicly accessible web service.

C³TO (Chatter Call Centre/Tutoring Online) is a scalable architecture to support mobile online tutoring using chat protocols over cell phones. It is the scalability of this architecture which is the primary focus of this dissertation. Much has been written lamenting the state of mathematics education in South Africa. It is not a pretty story. In order to help solve this mathematical crisis, the “Dr Math” research project was started in January, 2007. “Dr Math” strove to assist school pupils with their mathematics homework by providing access to tutors from a nearby university to help them. The school pupils used MXit on their cell phones and the tutors used normal computer workstations. The original “Dr Math” research project expected no more than twenty to thirty school pupils to participate. Unexpectedly thousands of school pupils started asking “Dr Math” to assist them with their mathematics homework. The original software could not scale. The original software could not cater for the thousands of pupils needing help. The scalability problems which existed in the original “Dr Math” project included: hardware scalability issues, software scalability problems, lack of physical office space for tutors, and tutor time being wasted by trivial questions. C³TO tackled these scalability concerns using an innovative three level approach by implementing a technological feature level, a tactical feature level, and a strategic feature level in the C³TO architecture. The technological level included specific components, utilities, and platforms which promoted scalability. The technological level provided the basic building blocks with which to construct a scalable architecture. The tactical level arranged the basic building blocks of the technological level into a scalable architecture. The tactical level provided short term solutions to scalability concerns by providing easy configurability and decision making. The strategic level attempted to answer the pupils questions before they actually arrived at the tutor thereby reducing the load on the human tutors. C³TO was extensively tested and evaluated. C³TO supported thousands of school pupils with their mathematics homework over a period of ten months. C³TO was used to support a small conference. C³TO was used to encourage people to volunteer their time in participation of Mandela Day. C³TO was used to support “Winter School” during the winter school holiday. In all these cases, C³TO proved itself to be scalable.

The purpose of this dissertation is to examine the impact of domain and methodological tutorials on the attitude and performance of end-users who are neither well-versed in the domain area nor well-versed with an expert system which is designed to assist them in solving software selection tasks. With respect to these tasks and the mechanism for accomplishing them, the end-users can be categorized as "non-technical users." The design of this experiment was a 2 x 2 full factorial laboratory experiment employing eighty novice users as subjects. Each of the experimental subjects was randomly assigned to one of the four treatment groups corresponding to receipt or lack of receipt of tutorials concerning the problem domain and methodology employed by an expert system. The results of this research indicate that there is a significant interaction between receiving the application and expert system tutorial videos; better performance in terms of correct categorization of problems was observed in subjects who saw either both or neither video whereas worse performance was observed in subjects who saw only one video. In general, the video treatments were unrelated to a variety of attitude measures applied to the subjects. However, it was found that prior attitudes towards the use of computers were significantly related to the majority of the (posttest) attitude measures. Further, the general pattern was for attitudes towards computers to improve as a result of undergoing the experimental process with the viewing of the expert system video to be significant in the level of improvement.

Intelligent Tutoring Systems are notoriously costly to construct, and require PhD level experience in cognitive science and rule based programming. The purpose of this research was to ease the development process for building pseudo-tutors. Pseudo-tutors are ITS constructs that mimic cognitive tutors but are limited in that they only apply to a single problem. The Assistment Builder is a tool designed to rapidly create, test, and deploy simple pseudo-tutors. These tutors provide a simplified cognitive model based upon a state graph designed for a specific problem. These tutors offer many of the features of rule-based tutors, but with shorter creation time. The system simplifies the process of tutor creation to allow users with little or no ITS experience to develop content. The system provides a web-based interface as a means to build and store these simple tutors we have called Assistments. This paper describes our attempt to make the process of developing, testing, and deploying content easy for teachers. We present data to suggest that users can develop a tutor that can be released to students in approximately an hour.

A major issue in Intelligent Tutoring Systems is off-task student behavior, especially performance-based gaming, where students systematically exploit tutor behavior in order to advance through a curriculum quickly and easily, with as little active thought directed at the educational content as possible. The goal of this research was to explore the phenomena of off-task gaming behavior within the Assistments system, as well as to develop a passive visual indicator to deter and prevent off-task gaming behavior without active intervention via graphical feedback to the student and teachers. Traditional active intervention approaches were also constructed for comparison purposes, and machine-learned gaming-detection models were developed as a potential invocation and evaluation mechanism. Passive graphical interventions have been well received by teachers, and results are suggestive that they are effective at reducing off-task gaming behavior.

Detection and prevention of off-task student behavior in an Intelligent Tutoring System (ITS) has gained a significant amount of attention in recent years. Previous work in these areas have shown some success and improvement. However, the research has largely ignored the incorporation of the expert on student behavior in the classroom: the teacher. Our research re-evaluates the subjects of off-task behavior detection and prevention by developing metrics for student engagement in an ITS using teacher observations of student behavior in the classroom. We present an exploratory analysis of such metrics and the data gathered from the teachers. For off-task prevention we developed a visual reporting tool that displays a representation of a student's activity in an ITS as they progress and gives a valuable immediate report for the instructor.

The Common Tutor Object Platform (CTOP) was designed as a lightweight component framework for creating and deploying applications relating to Intelligent Tutoring Systems. The CTOP supports a runtime for intelligent tutoring system content deployment, a content development environment, an extensive reporting tool, and other smaller applications. The CTOP was designed with future development in mind, allowing easy specification of new base objects and extension points for future development. It has been used as the foundation of the Assistments Project, a wide scale server based ITS deployment. This thesis documents the software engineering aspects of the project. The Assistments Project is capable of supporting a quarter of targeted students in Massachusetts, and optimistically scalable to the entire state and beyond.

The need to give educators the ability to enter a particular teaching strategy of their choice into an Intelligent Tutoring System (ITS) and have the ITS respond appropriately to each student has been stated by many researchers. For example, an educator could tell the ITS to keep students within a certain help level ratio (how much help they request), or to introduce a new topic in a particular manner and the ITS simply carries this out at each learning point of interest. Educators could then try new strategies, ones that unaided are impossible to try out in class (such as keeping a student within a help-seeking range) or difficult within an ITS (as the ITS would have to be specially programmed in that way). Current ITSs provide adaptivity to the student at the domain level but not necessarily at the pedagogical level. While a variety of pedagogical strategies have been implemented (e.g. apprenticeship, socratic, practice), there is no system that offers parts or all of these strategies with the ability to choose between them dynamically. In this project, we designed a new framework for an ITS to include multiple, potentially adaptable pedagogical strategies. This was done by breaking up the pedagogical module into separate components. The Pedagogical Strategy Set (PSS) contains all the strategies, written as constraints. The Pedagogical Student Model (PSM) keeps track of which pedagogical strategies were used by each student. Within the ITS, there is still a smaller, separate pedagogical module to deal with domain-specific strategies. The Pedagogical Control Centre (PCC) contains the logic of when and how to use the pedagogical strategies. It gathers its information from the other modules and uses decision logic to trigger strategies. We implemented and evaluated this framework within the context of SQL-Tutor and found that the framework could be used to enter pedagogical strategies, which in turn compared favourably to the original SQL-Tutor. This proof of concept opens up the possibility of the logic and algorithms that could be implemented (e.g. in the PCC) in future ITSs. The PSS is a separate module, written in a different language, independent of ITSs. This could lead to sharing of pedagogical strategies between tutors. Furthermore, students learn differently to each other; this framework allows them to do so.

The goal of this study was to evaluate whether Electroencephalography (EEG) estimates of attention and cognitive workload captured as students solved math problems could be used to predict success or failure at solving the problems. Students solved a series of SAT math problems while wearing an EEG headset that generated estimates of sustained attention and cognitive workload each second. Students also reported on their level of frustration and the perceived difficulty of each problem. Results from a Support Vector Machine (SVM) training indicated that problem outcomes could be correctly predicted from the combination of attention and workload signals at rates better than chance. The EEG data was also correlated with students' self-report of problem difficulty. Findings suggest that relatively non-intrusive EEG technologies could be used to improve the efficacy of tutoring systems.

The aim of this PhD thesis is to develop a framework for adaptive intelligent tutoring systems (ITS) in the domain of Modern Standard Arabic language. This framework will comprise of a new approach to using a fuzzy inference mechanism and generic rules in guiding the learning process. In addition, the framework will demonstrate another contribution in which the system can be adapted to be used in the teaching of different languages. A prototype system will be developed to demonstrate these features. This system is targeted at adult English-speaking casual learners with no pre-knowledge of the Arabic language. It will consist of two parts: an ITS for learners to use and a teachers‘ tool for configuring and customising the teaching rules and artificial intelligence components among other configuration operations. The system also provides a diverse teaching-strategies‘ environment based on multiple instructional strategies. This approach is based on general rules that provide means to a reconfigurable prediction. The ITS determines the learner‘s learning characteristics using multiple fuzzy inferences. It has a reconfigurable design that can be altered by the teacher at runtime via a teacher-interface. A framework for an independent domain (i.e. pluggable-domain) for foreign language tutoring systems is introduced in this research. This approach allows the system to adapt to the teaching of a different language with little changes required. Such a feature has the advantages of reducing the time and cost required for building intelligent language tutoring systems. To evaluate the proposed system, two experiments are conducted with two versions of the software: the ITS and a cut down version with no artificial intelligence components. The learners used the ITS had shown an increase in scores between the post-test and the pre-test with learning gain of 35% compared to 25% of the learners from the cut down version.