Showing papers on "Intelligent tutoring system published in 2015"

Examining self-efficacy during learning: variability and relations to behavior, performance, and learning

Abstract: Self-regulated learning (SRL) theorists propose that learners' motivations and cognitive and metacognitive processes interact dynamically during learning, yet researchers typically measure motivational constructs as stable factors. In this study, self-efficacy was assessed frequently to observe its variability during learning and how learners' efficacy related to their problem-solving performance and behavior. Students responded to self-efficacy prompts after every fourth problem of an algebra unit completed in an intelligent tutoring system. The software logged students' problem-solving behaviors and performance. The results of stability and change, path, and correlational analyses indicate that learners' feelings of efficacy varied reliably over the learning task. Their prior performance (i.e., accuracy) predicted subsequent self-efficacy judgments, but this relationship diminished over time as judgments were decreasingly informed by accuracy and increasingly informed by fluency. Controlling for prior achievement and self-efficacy, increases in efficacy during one problem- solving period predicted help-seeking behavior, performance, and learning in the next period. Findings suggest that self-efficacy varies during learning, that students consider multiple aspects of performance to inform their efficacy judgments, and that changes in efficacy influence self-regulated learning processes and outcomes.

AttentiveLearner: Improving Mobile MOOC Learning via Implicit Heart Rate Tracking

Abstract: We present AttentiveLearner, an intelligent mobile learning system optimized for consuming lecture videos in both Massive Open Online Courses (MOOCs) and flipped classrooms. AttentiveLearner uses on-lens finger gestures as an intuitive control channel for video playback. More importantly, AttentiveLearner implicitly extracts learners’ heart rates and infers their attention by analyzing learners’ fingertip transparency changes during learning on today’s unmodified smart phones. In a 24-participant study, we found heart rates extracted from noisy image frames via mobile cameras can be used to predict both learners’ “mind wandering” events in MOOC sessions and their performance in follow-up quizzes. The prediction performance of AttentiveLearner (accuracy = 71.22%, kappa = 0.22) is comparable with existing research using dedicated sensors. AttentiveLearner has the potential to improve mobile learning by reducing the sensing equipment required by many state-of-the-art intelligent tutoring algorithms.

A flowchart-based intelligent tutoring system for improving problem-solving skills of novice programmers

Abstract: Intelligent tutoring and personalization are considered as the two most important factors in the research of learning systems and environments An effective tool that can be used to improve problem-solving ability is an Intelligent Tutoring System which is capable of mimicking a human tutor's actions in implementing a one-to-one personalized and adaptive teaching In this paper, a novel Flowchart-based Intelligent Tutoring System FITS is proposed benefiting from Bayesian networks for the process of decision making so as to aid students in problem-solving activities and learning computer programming FITS not only takes full advantage of Bayesian networks, but also benefits from a multi-agent system using an automatic text-to-flowchart conversion approach for engaging novice programmers in flowchart development with the aim of improving their problem-solving skills In the end, in order to investigate the efficacy of FITS in problem-solving ability acquisition, a quasi-experimental design was adopted by this research According to the results, students in the FITS group experienced better improvement in their problem-solving abilities than those in the control group Moreover, with regard to the improvement of a user's problem-solving ability, FITS has shown to be considerably effective for students with different levels of prior knowledge, especially for those with a lower level of prior knowledge

TECH8 intelligent and adaptive e-learning system

Abstract: E-materials and various e-learning systems have become regular features in lower secondary schools in Slovenia and around the world. Many different systems and materials have been created for students, but only a few offer the same amount of individualisation that is present in traditional one to one teaching (one teacher to one student). The purpose of this research is to demonstrate the design and evaluation of an adaptive, intelligent and, most important, an individualised intelligent tutoring system (ITS) based on the cognitive characteristics of the individual learner. The TECH8 model presented is designed modularly, based on a system for collecting a range of metadata and variables that are vital for the teaching process. Prepared in such a way, the proposed system supports individualization and differentiation; because of this, it can be adapted to each individual's level of knowledge and understanding of the subject matter.This TECH8 system was evaluated in a real learning environment. The evaluation sample of the study consists of 117 students from five schools (suburban and urban). Qualitative and quantitative data was gathered with a system for collecting metadata and variables. The assembled data was analysed and statistically processed using descriptive analysis. This data was also compared to data from national assessments of knowledge, which encompassed the entire student population (approx. 5000) in the years 2008, 2010 and 2013. The study and the comparisons indicated that appropriately created TECH8 e-learning material, yields results that are better than those from traditional teaching but not better than one to one teaching. With the help of the collected metadata, optimisation, evaluation and an upgrade of the TECH8 itself will be carried out. In addition, such individualized e-learning systems can reinforce knowledge gained through traditional classroom education. Research question: Is it possible to replace a human teacher with a virtual one?The presented modified version of ITS includes hybrid model TECH8.TECH8 can adapt the learning process to the needs of an individual student.TECH8 does not only symbolise the learning process, but also the social environment.Cybernetic pedagogy and presented model TECH8 can lead to the progress of ITS.

Program Synthesis using Natural Language

Abstract: Interacting with computers is a ubiquitous activity for millions of people. Repetitive or specialized tasks often require creation of small, often one-off, programs. End-users struggle with learning and using the myriad of domain-specific languages (DSLs) to effectively accomplish these tasks. We present a general framework for constructing program synthesizers that take natural language (NL) inputs and produce expressions in a target DSL. The framework takes as input a DSL definition and training data consisting of NL/DSL pairs. From these it constructs a synthesizer by learning optimal weights and classifiers (using NLP features) that rank the outputs of a keyword-programming based translation. We applied our framework to three domains: repetitive text editing, an intelligent tutoring system, and flight information queries. On 1200+ English descriptions, the respective synthesizers rank the desired program as the top-1 and top-3 for 80% and 90% descriptions respectively.

A Review of Emotion Regulation in Intelligent Tutoring Systems.

Abstract: Introduction A common view of emotions is that they are generated as a results of human's judgment about the world and initiated by individual's appraisal in response to and interaction with stimulus, such as material that the individual is learning (Desmet, 2002; Lazarus, 1991). Recent findings in neuroscience and psychology found that emotions are widely related to cognition, influencing various behavioural and cognitive processes, such as attention, long-term memorizing, decision-making, and so on (Ahn & Picard, 2005). Researches on emotion and learning suggest that positive emotions (affects) have a vital influence on various cognitive processes relevant for learning, such as information processing, communication processing, decision-making processing, negotiation processing, category sorting tasks, and creative problem-solving processes (Erez & Isen, 2002). Positive emotions promote higher cognitive flexibility and allow the learner to discover new ideas and possibilities. In addition, as a function of positive emotion, cognitive processes may be more flexible that result in greater creativity and improved problemsolving (Isen et al., 1987). Emotion also influences memory, where positive emotional state improved recall and it served as effective retrieval cues for long-term memory in many experiments (Isen et al., 1978). Reciprocally, negative emotional states like boredom and frustration have been linked with less use of self-regulation and cognitive strategies for learning as well as increases in disengaged and disturbing behavior during learning in the class (Isen, 2001). Thus, emotions, governed by proper attention, self-regulation and motivational strategies result in positive effects on learning, and lead to better achievement among the learners (Pekrun, Goetz, Titz, & Perry, 2002). In traditional learning environment, a teacher maintains a sympathetic relationship with learners to facilitate the development of positive emotions. For instance, students who feel happy generally perform better than students who feel sad, angry, or scared (Connor & Davidson, 2003). This relationship also exists in a computerized learning environments and researchers of computer science in education field had studied techniques of artificial intelligence to make the educational systems more customized to the emotional state (affective states) of students (Jaques & Vicari, 2007). Intelligent tutoring system (ITS) is a computer-based educational system that provides individualised instructions similar to like a human tutor. Typical ITSs determine how and what to teach a student based on the learner's pedagogical state to enhance learning. As experienced human tutor manages the emotional states of a learner to motivate him or her and to improve the learning process, researchers also have augment the learner model structure in ITSs to determine the emotional state of learners (Neji, Ben Ammar, Alimi, & Gouarderes, 2008). Researchers endow ITSs with the ability to detect learners' unpleasant emotional states (e.g., confusion, frustration, etc.), respond to these states, and generate appropriate tutoring strategies as well as emotional expressions by embodied pedagogical agents. These emotion-sensitive ITSs aspire to narrow the interaction bandwidth between computer tutors and human tutors with the hope that this will lead to an improved user experience and enhanced learning gains (Aghaei Pour, Hussain, AlZoubi, D'Mello, & Calvo, 2010; Klein, Moon, & Picard, 2002). In embedding emotional state reasoning into ITSs and intelligent learning environments, there are two main issues that are faced by the developers. First is determining the emotional states of the target learners, and second is determining factors that causes those states as well as how to respond and regulate negative emotional state (Avramides & Du Boulay, 2009; Du Boulay, Rebolledo Mendez, Luckin, & Martinez-Miron, 2007). …

Connection making between multiple graphical representations

Abstract: Making connections between graphical representations is integral to learning in science, technology, engineering, and mathematical (STEM) fields. However, students often fail to make these connections spontaneously. Intelligent tutoring systems (ITSs) are suitable educational technologies to support connection making. Yet, when designing an ITS for connection making, we need to investigate what concepts and learning processes play a role within the specific domain. We describe a multi-methods approach for grounding ITS design in the specific requirements of the target domain. Specifically, we applied this approach to an ITS for connection making in chemistry. We used a theoretical framework that describes potential target learning processes and conducted a series of four empirical studies to investigate what role graphical representations play in chemistry knowledge and to investigate which learning processes related to connection making play a role in students' learning about chemistry. These studies combined multiple methods, including knowledge testing, eye tracking, interviews, and log data analysis. We illustrate how our findings inform the design of an ITS for chemistry: Chem Tutor. Results from two pilot studies done in the lab and in the field with altogether 99 undergraduates suggest that Chem Tutor leads to significant and large learning gains on chemistry knowledge. Students' benefit from multiple graphical representations depends on connection making.Connection making support needs to align with the requirements of the specific target domain.We describe a multi-methods approach to ground the design of an intelligent tutoring system in the chemistry domain.The system supports sense-making and fluency-building processes.Two pilot studies demonstrate significant and large learning gains.

A problem solving oriented intelligent tutoring system to improve students' acquisition of basic computer skills

Abstract: Personalization and intelligent tutor are two key factors in the research on learning environment. Intelligent tutoring system (ITS), which can imitate the human teachers' actions to implement one-to-one personalized teaching to some extent, is an effective tool for training the ability of problem solving. This research firstly discusses the concepts and methods of designing problem solving oriented ITS, and then develops the current iTutor based on the extended model of ITS. At last, the research adopts a quasi-experimental design to investigate the effectiveness of iTutor in skills acquisition. The results indicate that students in iTutor group experience better learning effectiveness than those in the control group. iTutor is found to be effective in improving the learning effectiveness of students with low-level prior knowledge. We model a problem solving oriented ITS architecture.We develop iTutor to support skills acquisition in real-life problem situation.A quasi-experimental was designed to investigate the effectiveness of iTutor.iTutor can better facilitate skills acquisition.iTutor can improve the skill learning effect of low-level prior knowledge.

Are you reading my mind?: modeling students' reading comprehension skills with natural language processing techniques

Abstract: This study builds upon previous work aimed at developing a student model of reading comprehension ability within the intelligent tutoring system, iSTART. Currently, the system evaluates students' self-explanation performance using a local, sentence-level algorithm and does not adapt content based on reading ability. The current study leverages natural language processing tools to build models of students' comprehension ability from the linguistic properties of their self-explanations. Students (n = 126) interacted with iSTART across eight training sessions where they self-explained target sentences from complex science texts. Coh-Metrix was then used to calculate the linguistic properties of their aggregated self-explanations. The results of this study indicated that the linguistic indices were predictive of students' reading comprehension ability, over and above the current system algorithms. These results suggest that natural language processing techniques can inform stealth assessments and ultimately improve student models within intelligent tutoring systems.

Are You Reading My Mind? Modeling Students' Reading Comprehension Skills with Natural Language Processing Techniques.

Abstract: This study builds upon previous work aimed at developing a student model of reading comprehension ability within the intelligent tutoring system, iSTART. Currently, the system evaluates students' self-explanation performance using a local, sentence-level algorithm and does not adapt content based on reading ability. The current study leverages natural language processing tools to build models of students' comprehension ability from the linguistic properties of their self-explanations. Students (n = 126) interacted with iSTART across eight training sessions where they self-explained target sentences from complex science texts. Coh-Metrix was then used to calculate the linguistic properties of their aggregated self-explanations. The results of this study indicated that the linguistic indices were predictive of students' reading comprehension ability, over and above the current system algorithms. These results suggest that natural language processing techniques can inform stealth assessments and ultimately improve student models within intelligent tutoring systems.

Multi-relational Factorization Models for Student Modeling in Intelligent Tutoring Systems

Abstract: Student Modeling is an important part of an Intelligent Tutoring System. The student model tracks information of individual student (e.g., Time spent on problems, hints requested, correct answers, etc). One of the important tasks in student modeling is predicting student performance, where the system can provide the students early feedbacks to help them improving their study results. In this work, we propose using multi-relational factorization approach, which has been successfully applied in recommender systems area, for student modeling in the Intelligent Tutoring Systems. Experiments on large real world data sets show that the proposed approach can improve the prediction results and could be used for student modeling.

JavaTutor: An Intelligent Tutoring System that Adapts to Cognitive and Affective States during Computer Programming

Abstract: Introductory computer science courses cultivate the next generation of computer scientists. The impressions students take away from these courses are crucial, setting the tone for the rest of the students' computer science education. It is known that students struggle with many concepts central to computer science, struggles that could be alleviated in part through hands-on practice and individualized instruction. However, even the best existing instructional practices do not facilitate individualized hands-on support for students at large. We have built JavaTutor, an intelligent tutoring system for introductory computer science, which works alongside students to support them through both cognitive (skills and knowledge) and affective (emotion-based) feedback. JavaTutor aims to make advances in interactive, scalable student support. JavaTutor's behaviors were developed within a novel framework that leverages machine learning to acquire tutorial strategies from data collected within tutorial sessions between novice students and experienced human tutors. This demo presents an overview of the data-driven development of JavaTutor and shows how JavaTutor assesses and responds to students' contextualized needs. It is hoped that JavaTutor will help to usher in a new generation of tutorial systems for computer science education that adapt to individual students based not only on incoming student knowledge, but on a broad range of other student characteristics.

Enhancing undergraduate chemistry learning by helping students make connections among multiple graphical representations

Abstract: Multiple representations are ubiquitous in chemistry education. To benefit from multiple representations, students have to make connections between them. However, connection making is a difficult task for students. Prior research shows that supporting connection making enhances students' learning in math and science domains. Most prior research has focused on supporting one type of connection-making process: conceptually making sense of connections among representations. Yet, recent research suggests that a second type of connection-making process plays a role in students' learning: perceptual fluency in translating among representations. I hypothesized that combining support for both conceptual sense making of connections and for perceptual fluency in connection making leads to higher learning gains in general chemistry among undergraduate students. I tested this hypothesis in two experiments with altogether N = 158 undergraduate students using an intelligent tutoring system for chemistry atomic structure and bonding. Results suggest that the combination of conceptual sense-making support and perceptual fluency-building support for connection making is effective for students with low prior knowledge, whereas students with high prior knowledge benefit most from receiving perceptual fluency-building support alone. This finding suggests that students' learning in chemistry can be enhanced if instruction provides support for connection making among multiple representations in a way that tailors to their specific learning needs.

MENTOR: A Physiologically Controlled Tutoring System

Abstract: In this paper we present a tutoring system that automatically sequences the learning content according to the learners’ mental states. The system draws on techniques from Brain Computer Interface and educational psychology to automatically adapt to changes in the learners’ mental states such as attention and workload using electroencephalogram (EEG) signals. The objective of this system is to maintain the learner in a positive mental state throughout the tutoring session by selecting the next pedagogical activity that fits the best to his current state. An experimental evaluation of our approach involving two groups of learners showed that the group who interacted with the mental state-based adaptive version of the system obtained higher learning outcomes and had a better learning experience than the group who interacted with a non-adaptive version.

DeepTutor: an effective, online intelligent tutoring system that promotes deep learning

Abstract: We present in this paper an innovative solution to the challenge of building effective educational technologies that offer tailored instruction to each individual learner. The proposed solution in the form of a conversational intelligent tutoring system, called DeepTutor, has been developed as a web application that is accessible 24/7 through a browser from any device connected to the Internet. The success of several large scale experiments with high-school students using DeepTutor is a solid proof that conversational intelligent tutoring at scale over the web is possible.

Empathy for Artificial Agents

Abstract: The paper has three goals. First, it introduces into different notions of empathy and related capacities such as emotional contagion, affective empathy, cognitive empathy, and sympathy. Second, it presents a case in point of an intelligent tutoring system, Affective AutoTutor, whose affect-sensitive behavior seems to further and enhance the outcome of its interactions with its students. Affective AutoTutor appears to behave empathically within a well defined learning environment. Third, attention is directed towards the requirements to be met by artificial empathizers to be judged as empathizers tout court by their social interactants, even when acting in unspecified social situations. To be a convincing empathizer, the artificial agent would not only need to grasp the emotional states of its interaction partners and understand their situation with respect to an adequate world model, but also communicate its own affective states. Eventually, an artificial empathizer should be ready to react appropriately to its interaction partner’s reciprocal empathy.

Spendency: Students' Propensity to Use System Currency.

Abstract: Using students’ process data from the game-based Intelligent Tutoring System (ITS) iSTART-ME, the current study examines students’ propensity to use system currency to unlock game-based features, (i.e., referred to here as spendency). This study examines how spendency relates to students’ interaction preferences, in-system performance, and learning outcomes (i.e., self-explanation quality, comprehension). A group of 40 high school students interacted with iSTART-ME as part of an 11-session experiment (pretest, eight training sessions, posttest, and a delayed retention test). Students’ spendency was negatively related to the frequency of their use of personalizable features. In addition, students’ spendency was negatively related to their in-system achievements, daily learning outcomes, and performance on a transfer comprehension task, even after factoring out prior ability. The findings from this study indicate that increases in students’ spendency are systematically related to their selection choices and may have a negative effect on in-system performance, immediate learning outcomes, and skill transfer outcomes. The results have particular relevance to game-based systems that incorporate currency to unlock features within games as well as to the differential tradeoffs of game features on motivation and learning.

The Mars and Venus Effect: The Influence of User Gender on the Effectiveness of Adaptive Task Support

Abstract: Providing adaptive support to users engaged in learning tasks is the central focus of intelligent tutoring systems. There is evidence that female and male users may benefit differently from adaptive support, yet it is not understood how to most effectively adapt task support to gender. This paper reports on a study with four versions of an intelligent tutoring system for introductory computer programming offering different levels of cognitive (conceptual and problem-solving) and affective (motivational and engagement) support. The results show that female users reported significantly more engagement and less frustration with the affective support system than with other versions. In a human tutorial dialogue condition used for comparison, a consistent difference was observed between females and males. These results suggest the presence of the Mars and Venus Effect, a systematic difference in how female and male users benefit from cognitive and affective adaptive support. The findings point toward design principles to guide the development of gender-adaptive intelligent tutoring systems.

Partial Verbal Redundancy in Multimedia Presentations for Writing Strategy Instruction

Abstract: Summary Multimedia instructional materials require learners to select, organize, and integrate information across multiple modalities. To facilitate these comprehension processes, a variety of multimedia design principles have been proposed. This study further explores the redundancy principle by manipulating the degree of partial redundancy between written and narrated content. Ninety high school students learned about cohesion via animated lesson videos from the Writing Pal intelligent tutoring system. Videos were crafted such that narrated and onscreen written content overlapped by 10%, 26%, or 50%. Across conditions, students gained significantly in their knowledge of cohesion-building strategies and the effects of cohesion on writing quality. However, degree of redundancy did not influence learning gains. Additionally, although more-skilled readers outperformed less-skilled readers, reading skill did not interact with the degree of redundancy. These results provide evidence that a broad range of partially redundant multimedia materials may be viable instructional tools that benefit diverse learners. Copyright © 2015 John Wiley & Sons, Ltd.

Usability evaluation of intelligent tutoring system: ITS from a usability perspective

Abstract: Face-to-face and one-to-one human tutoring is the best tutoring field. Human tutors are not always and everywhere available and that’s why computer based tutoring is developed. Intelligent Tutoring...

Mind wandering during learning with an intelligent tutoring system

Abstract: Mind wandering (zoning out) can be detrimental to learning outcomes in a host of educational activities, from reading to watching video lectures, yet it has received little attention in the field of intelligent tutoring systems (ITS). In the current study, participants self-reported mind wandering during a learning session with Guru, a dialogue-based ITS for biology. On average, participants interacted with Guru for 22 minutes and reported an average of 11.5 instances of mind wandering, or one instance every two minutes. The frequency of mind wandering was compared across five different phases of Guru (Common-Ground-Building Instruction, Intermittent Summary, Concept Map, Scaffolded Dialogue, and Cloze task), each requiring different learning strategies. The rate of mind wandering per minute was highest during the Common-Ground-Building Instruction and Scaffolded Dialogue phases of Guru. Importantly, there was significant negative correlation between mind wandering and learning, highlighting the need to address this phenomena during learning with ITSs.

Intensive scaffolding in an intelligent tutoring system for the learning of algebraic word problem solving

Abstract: The term intensive scaffolding refers to any set of conceptual scaffolding strategies that always allow the user to find the solution to a problem. Despite the many benefits of scaffolding, some negative effects have also been reported. These are mainly related to the possibility that a student solves the problems without actually engaging in their content. In this paper, we have used an intelligent tutoring system ( ITS) to analyze the effect that intensive scaffolding has on the learning of algebraic word problem solving ( AWPS). Two different versions of the ITS, which differ in the amount of scaffolding that they provide, have been created. These two versions were used by two groups of students in Secondary Education, in a quasi-experimental study. The comparison of pre- and posttest scores shows a significant increase of the competence in AWPS in the group that used the ITS with intensive scaffolding. [ABSTRACT FROM AUTHOR]

A hybrid cognitive assessment based on ontology knowledge map and skills

Abstract: An intelligent tutoring system plays vital role in education and its importance is constantly increasing, meanwhile the key challenge in the teaching learning process is assessing students' learning efficiently. In this paper, a hybrid assessment based-on ACT-R cognitive learning theory, combining ontology knowledge map with skills is proposed. In order to assess how well students master knowledge structure, an ontology knowledge map is constructed to describe declarative knowledge; and in order to assess how well students master knowledge skills, a problem solving process is constructed to describe procedural knowledge based on ACT-R. Finally, a student's mastery of knowledge is assessed through both the knowledge map and skills in the problem solving process, as well as auxiliary indicators like time usage, prior knowledge level, self-assessment, etc. This method is implemented in a geometric intelligent assessment system and is evaluated in a junior high school. Experiments show that the assessment results are consistent with students' actual learning levels. The hybrid cognitive assessment method can not only obtain the score of students' mastery of knowledge points and the structure through knowledge map, but also assess the learning skills in problem solving process through exercises quantitatively.

Cognitive Demand of Model Tracing Tutor Tasks: Conceptualizing and Predicting How Deeply Students Engage

Abstract: Model tracing tutors represent a technology designed to mimic key elements of one-on-one human tutoring. We examine the situations in which such supportive computer technologies may devolve into mindless student work with little conceptual understanding or student development. To analyze the support of student intellectual work in the model tracing tutor case, we adapt a cognitive demand framework that has been previously applied with success to teacher-guided mathematics classrooms. This framework is then tested against think-aloud data from students using a model tracing tutor designed to teach proportional reasoning skills in the context of robotics movement planning problems. Individual tutor tasks are coded for designed level of cognitive demand and compared to students’ enacted level of cognitive demand. In general, designed levels predicted how students enacted the tasks. However, just as in classrooms, student enactment was often at lower levels of demand than designed. Several contextual design features were associated with this decline. Implications for intelligent tutoring system design and research are discussed.