Papers by Beate Grawemeyer
Artificial Intelligence in Education, 2018
This paper investigates the effect of affect-aware support on learning tasks that differ in their... more This paper investigates the effect of affect-aware support on learning tasks that differ in their cognitive demands. We conducted a study with the iTalk2learn platform where students are undertaking fractions tasks of varying difficulty and assigned in one of two groups; one group used the iTalk2learn platform that included the affect-aware support, whereas in the other group the affect-aware support was switched off and support was provided based on students' performance only. We investigated the hypothesis that affect-aware support has a more pronounced effect when the cognitive demands of the tasks are higher. The results suggest that students that undertook the more challenging tasks were significantly more inflow and less confused in the group where affect-aware support was provided than students who were supported based on their performance only.
Proceedings of the Sixth International Conference on Learning Analytics & Knowledge - LAK '16, 2016
This paper describes the development and evaluation of an affect-aware intelligent support compon... more This paper describes the development and evaluation of an affect-aware intelligent support component that is part of a learning environment known as iTalk2Learn. The intelligent support component is able to tailor feedback according to a student's affective state, which is deduced both from speech and interaction. The affect prediction is used to determine which type of feedback is provided and how that feedback is presented (interruptive or non-interruptive). The system includes two Bayesian networks that were trained with data gathered in a series of ecologically-valid Wizard-of-Oz studies, where the effect of the type of feedback and the presentation of feedback on students' affective states was investigated. This paper reports results from an experiment that compared a version that provided affect-aware feedback (affect condition) with one that provided feedback based on performance only (non-affect condition). Results show that students who were in the affect condition were less bored and less off-task, with the latter being statically significant. Importantly, students in both conditions made learning gains that were statistically significant, while students in the affect condition had higher learning gains than those in the non-affect condition, although this result was not statistically significant in this study's sample. Taken all together, the results point to the potential and positive impact of affect-aware intelligent support.
User Modeling and User-Adapted Interaction, 2017
This paper describes the design and ecologically valid evaluation of a learner model that lies at... more This paper describes the design and ecologically valid evaluation of a learner model that lies at the heart of an intelligent learning environment called iTalk2Learn. A core objective of the learner model is to adapt formative feedback based on students' affective states. Types of adaptation include what type of formative feedback should be provided and how it should be presented. Two Bayesian networks trained with data gathered in a series of Wizard-of-Oz studies are used for the adaptation process. This paper reports results from a quasi-experimental evaluation, in authentic classroom settings, which compared a version of iTalk2Learn that adapted feedback based on students' affective states as they were talking aloud with the system (the affect condition) with one that provided feedback based only on the students' performance (the non-affect condition). Our results suggest that affect-aware support contributes to reducing boredom and off-task behavior, and may have an effect on learning. We discuss the internal and ecological validity of the study, in light of pedagogical considerations that informed the design of the two conditions. Overall, the results of the study have implications both for the design of educational technology and for classroom approaches to teaching, because they highlight the important role that affect-aware modelling plays in the adaptive delivery of formative feedback to support learning.
This paper describes how graph-based modelling can be used to explore interactions associated wit... more This paper describes how graph-based modelling can be used to explore interactions associated with a change in students' affective state when they are working with an exploratory learning environment (ELE). We report on a user study with an ELE that is able to detect students' affective states from their interactions and speech. The data collected during the user study was modelled, visualized and queried as a graph. We were interested in exploring if there was a difference between low- and high-performing students in the kinds of interactions that occurred during a change in their affective state. Our findings provide new insights into how students are interacting with the ELE and the effects of the system's interventions on students' affective states.
The knowledge structures and reasoning processes that underlie the use of external representation... more The knowledge structures and reasoning processes that underlie the use of external representations (ERs) in individuals with autism spectrum disorder (ASD) are not well understood. This paper compares the organisation of knowledge of ERs in young people with a diagnosis of ASD and an age-matched typically developing control group. ASD and non-ASD participants (twenty-eight in each group) were given an untimed ER card-sorting task. The ERs were based on representations used in educational software, for example graphs, charts, and text. Cluster analysis of the card sort task revealed similar clusters for both groups: maps, drawings, text, graphs and charts, and network and tree diagrams. However, comparison of the card sorts of the two different groups showed a difference in 'basic level' categories. While in the non-ASD group, maps and non-maps were the most distinctive category, analysis of the ASD cluster revealed, in addition, another 'basic level' category of textual representations. These results are discussed in relation to theories of information processing in autism. Our ultimate research aim is to develop educational software tailored to the specific needs of users with ASD. We wish to use our research results to inform requirements for the development of such educational software, in which ERs are able to support differences in information processing for individuals with ASD.
Artificial Intelligence in Education, 2017
We conducted a user study that explored the relationship between students' usage of multiple exte... more We conducted a user study that explored the relationship between students' usage of multiple external representations and their affective states during fractions learning. We use the affective states of the student as a proxy indicator for the ease of reasoning with the representation. Extending existing literature that highlights the advantages of learning with multiple external representations, our results indicate that low-performing students have difficulties in reasoning with representations that do not fully accommodate the fraction as a part-whole concept. In contrast, high-performing students were at ease with a range of representations, including the ones that vaguely involved the fraction as part-whole concept.
Proceedings of the 20th International Conference on Intelligent User Interfaces - IUI '15, 2015
Affective states play a significant role in students' learning behaviour. Positive affective stat... more Affective states play a significant role in students' learning behaviour. Positive affective states can enhance learning, whilst negative affective states can inhibit it. This paper describes a Wizard-of-Oz study which investigates whether the way feedback is presented should change according to the affective state of a student, in order to encourage affect change if that state is negative. We presented high-interruptive feedback in the form of pop-up windows in which messages were immediately viewable; or low-interruptive feedback, a glowing light bulb which students needed to click in order to access the messages. Our results show that when students are confused or frustrated high-interruptive feedback is more effective, but when students are enjoying their activity, there is no difference. Based on the results, we present guidelines for adaptively tailoring the presentation of feedback based on students' affective states when interacting with learning environments.
This paper describes how we developed an embodied pedagogical agent (EPA) with and for young peop... more This paper describes how we developed an embodied pedagogical agent (EPA) with and for young people with autism spectrum disorder (ASD). ASD is characterised by impairments in social communication, imagination, and perspective-taking, which can compromise design and collaboration. However , if an ASD preference for visual processing can be supported by providing images of design ideas as they develop, these difficulties may be overcome. We describe a methodology that successfully supports the visualisation and development of EPAs using our prototype visualisation tool (EPA DK), enabling ASD users to function as active design participants.
Emotions play a significant role in students' learning behaviour. Positive emotions can enhance l... more Emotions play a significant role in students' learning behaviour. Positive emotions can enhance learning, while negative emotions can inhibit it. This paper describes how we provide intelligent support in a learning platform based on emotions. We discuss two components: an emotion detector to perceive emotions in speech during interaction with the platform; and an emotion reasoner to provide support, which aims at aligning the learner's personal goal with the learning task to evoke positive emotions for an enhanced learning experience.
Affective states play a significant role in students' learning behaviour. Positive affective stat... more Affective states play a significant role in students' learning behaviour. Positive affective states can enhance learning, whilst negative affective states can inhibit it. This paper describes a Wizard-of-Oz study which investigates whether the way feedback is presented should change according to the af-fective state of a student, in order to encourage affect change if that state is negative. We presented high-interruptive feedback in the form of pop-up windows in which messages were immediately viewable; or low-interruptive feedback, a glowing light bulb which students needed to click in order to access the messages. Our results show that when students are confused or frustrated high-interruptive feedback is more effective , but when students are enjoying their activity, there is no difference. Based on the results, we present guidelines for adaptively tailoring the presentation of feedback based on students' affective states when interacting with learning environments .
Lecture Notes in Computer Science, 2015
This paper reports on our progress on a systematic approach to operationalizing support in Fracti... more This paper reports on our progress on a systematic approach to operationalizing support in Fractions Lab -an exploratory learning environment for learning fractions in primary education. In particular, we focus on the question of what feedback to provide and consider in detail the implementation of feedback according to two dimensions: the purpose of the feedback, depending on the task-specific needs of the student, and the level of feedback, depending on the cognitive needs of the student. We present early findings from our design-based research that includes Wizard-of-Oz studies of the intelligent feedback system and student perception questionnaires.
Affective states play a significant role in students' learning behaviour. Positive affective stat... more Affective states play a significant role in students' learning behaviour. Positive affective states can enhance learning, whilst negative affective states can inhibit it. This paper describes a Wizard-of-Oz study which investigates whether the way feedback is presented should change according to the af-fective state of a student, in order to encourage affect change if that state is negative. We presented high-interruptive feedback in the form of pop-up windows in which messages were immediately viewable; or low-interruptive feedback, a glowing light bulb which students needed to click in order to access the messages. Our results show that when students are confused or frustrated high-interruptive feedback is more effective , but when students are enjoying their activity, there is no difference. Based on the results, we present guidelines for adaptively tailoring the presentation of feedback based on students' affective states when interacting with learning environments .
Affective states play a significant role in students' learning behaviour. Positive affective stat... more Affective states play a significant role in students' learning behaviour. Positive affective states can enhance learning, while negative ones can inhibit it. This paper describes the development of an affective state reasoner that is able to adapt the feedback type according to stu-dents' affective states in order to evoke positive affective states and as such improve their learning experience. The reasoner relies on a dynamic Bayesian network trained with data gathered in a series of ecologically valid Wizard-of-Oz studies, where the effect of feedback on students' affective states was investigated.
We describe a Wizard-of-Oz study that investigates the impact of different types of feedback on s... more We describe a Wizard-of-Oz study that investigates the impact of different types of feedback on students' affective states. Our results indicate the importance of matching carefully the affective state with appropriate feedback in order to help students transition into more positive states. For example when students were confused affect boosts and specific instruction seem to be effective in helping students to be in flow again. We discuss this and other effective ways to and implications for the development of our system and the field in general.
This paper describes the development and evaluation of an affect-aware intelligent support compon... more This paper describes the development and evaluation of an affect-aware intelligent support component that is part of a learning environment known as iTalk2Learn. The intelligent support component is able to tailor feedback according to a student's affective state, which is deduced both from speech and interaction. The affect prediction is used to determine which type of feedback is provided and how that feedback is presented (interruptive or non-interruptive). The system includes two Bayesian networks that were trained with data gathered in a series of ecologically-valid Wizard-of-Oz studies , where the effect of the type of feedback and the presentation of feedback on students' affective states was investigated. This paper reports results from an experiment that compared a version that provided affect-aware feedback (affect condition) with one that provided feedback based on performance only (non-affect condition). Results show that students who were in the affect condition were less bored and less off-task, with the latter being statically significant. Importantly , students in both conditions made learning gains that were statistically significant, while students in the affect condition had higher learning gains than those in the non-affect condition, although this result was not statistically significant in this study's sample. Taken all together, the results point to the potential and positive impact of affect-aware intelligent support.
Employing Speech to Contribute to Modelling and Adapting to Students’ Affective States
Lecture Notes in Computer Science, 2014
ABSTRACT Affect plays a significant role in students’ learning behaviour. Positive affective stat... more ABSTRACT Affect plays a significant role in students’ learning behaviour. Positive affective states can enhance learning, while negative ones can inhibit it. This paper describes how we provide intelligent support in a learning platform based on affect states. We discuss two components: an affective state detector to perceive affective states in speech during interaction with the platform; and an affective state reasoner to provide support, which aims at aligning the learner’s personal goal with the learning task to evoke positive affective states for an enhanced learning experience.
Lecture Notes in Computer Science, 2015
We describe a Wizard-of-Oz study that investigates the impact of different types of feedback on s... more We describe a Wizard-of-Oz study that investigates the impact of different types of feedback on students' affective states. Our results indicate the importance of matching carefully the affective state with appropriate feedback in order to help students transition into more positive states. For example when students were confused affect boosts and specific instruction seem to be effective in helping students to be in flow again. We discuss this and other effective ways to and implications for the development of our system and the field in general.
Lecture Notes in Computer Science, 2006
This paper describes the evaluation of ERST, an adaptive system which is designed to improve its ... more This paper describes the evaluation of ERST, an adaptive system which is designed to improve its users' external representation (ER) selection accuracy on a range of database query tasks. The design of the system was informed by the results of experimental studies. Those studies examined the interactions between the participants' background knowledge-of-external representations, their preferences for selecting particular information display forms, and their performance across a range of tasks involving database queries. The paper describes how ERST's adaptation is based on predicting users' ER-to-task matching skills and performance at reasoning with ERs, via a Bayesian user model. The model drives ERST's adaptive interventions in two ways -by 1. hinting to the user that particular representations be used, and/or 2. by removing from the user the opportunity to select display forms which have been associated with prior poor performance for that user. The results show that ERST does improve an individual's ER reasoning performance. The system is able to successfully predict users' ER-to-task matching skills and their ER reasoning performance via its Bayesian user model.
… Postgraduate Workshop, University of Sussex, School …, 2001
Intelligent display systems Automatic visualization systems (AVSs) generate graphical visualizati... more Intelligent display systems Automatic visualization systems (AVSs) generate graphical visualizations intelligently depending on the particular type of information to be presented. These systems analyse the source data and produce a specific visualization that optimally represents the data. ...
Studies in Health Technology and Informatics, Feb 1, 2000
AUDIX is a knowledge-based multimedia system for auditory discrimination exercises. The aim of AU... more AUDIX is a knowledge-based multimedia system for auditory discrimination exercises. The aim of AUDIX is to provide patients with a computer-based therapy system which they can use between sessions with the human therapist, at home on an 'on-demand' basis. It is centered around computer based cognitive rehabilitation therapy whereas most existing programs in this area are only used for assessment. The auditory discrimination exercise system is designed for adult people who are speech-impaired as a result of a stroke. These people have auditory perceptual problems. The nature of the perceptual problem is an inability to perceive differences between phonemes. This requires a type of therapy called auditory discrimination training. The system provides computer-based auditory discrimination training. Through the knowledgebased design the domain dependent therapy knowledge is separated from the system core and provides a way for the therapist to add new knowledge, as new stimuli, or to create a new knowledge base to provide special exercises for an individual patient. The AUDIX architecture is described and the advantages of computerbased therapy are discussed.
Uploads
Papers by Beate Grawemeyer