Matt Dennis

Adapting Progress Feedback and Emotional Support to Learner Personality

As feedback is an important part of learning and motivation, we investigate how to adapt the feedback of a conversational agent to learner personality (as well as to learner performance, as we expect an interaction effect between personality and performance on feedback). We investigate two aspects of feedback. Firstly, we investigate whether the conversational agent should employ a slant (or bias) in its feedback on particular test scores to motivate a learner with a particular personality trait more effectively (for example, using “you are slightly below expectations” versus “you are substantially below expectations” depending on learner conscientiousness). Secondly, we investigate which emotional support messages the conversational agent should use (for example: using praise, emotional reflection, reassurance or advice) given learner personality and performance. We investigate the adaptation of this feedback to a learner personality, in particular the traits in the Five Factor Model. Five experiments were run where participants gave progress feedback and emotional support to students with different personalities and test scores. The type of emotional support given varied between different personalities (e.g. neurotic individuals with poor grades received more emotional reflection). Two algorithms were created using different methods to describe the adaptations and evaluated on how well they described the experimental data using DICE scores. A refined algorithm was created based on the results. Finally, we ran a qualitative study with teachers to investigate the algorithm’s effectiveness and further refine the algorithm.

Does Learner Conscientiousness Matter When Generating Emotional Support in Feedback

This paper describes the development of an algorithm for use by an Empathic Conversational Agent for choosing appropriate emotional support messages to a learner receiving feedback on their performance. We present a study where we employed a User as Wizard approach to explore how such statements were used by people giving feedback to a fictional learner with high or low conscientiousness and varying grades. We found that the type of emotional support employed depended primarily on the grade that had been achieved, but conscientiousness also influenced the amount of advice given. Interesting differences were found in how people combine Emotional Support messages depending on grade and level of conscientiousness, which inspired an algorithm for automatically choosing appropriate messages depending on context.

Adapting exercise selection to learner self-esteem and performance

The past years have witnessed an increased use of applied games for developing and evaluating communication skills. These skills benefit from in-terpersonal interactions. Providing feedback to students practicing communica-tion skills is difficult in a traditional class setting with one teacher and many students. This logistic challenge may be partly overcome by providing training using a simulation in which a student practices with communication scenarios. A scenario is a description of a series of interactions, where at each step the player is faced with a choice. We have developed a scenario editor that enables teachers to develop scenarios for practicing communication skills. A teacher can develop a scenario without knowledge of the implementation. This paper presents the implementation architecture for such a scenario-based simulation.This paper presents an initial evaluation of different forms of adaptation based on learning style and knowledge level, which were implemented in an adaptive e-learning system. An experiment conducted in a learning context with 174 participants produced significant results in terms of learning gain. They indicate that adaptation based on both learning style and knowledge level yields significantly better learning gain than adaptation based on learning style only, and better than adaptation based on knowledge level only.Technology Enhanced Learning (TEL) largely focuses on the retrieval and reuse of educational resources from Web platforms like Coursera. Unfortunately, Coursera does not provide educational metadata of its content. To overcome this limitation, this study proposes a data mining approach for discovering Teaching Contexts (TC) where resources have been delivered in. Such TCs can facilitate the retrieval of resources for the teaching preferences and requirements of teachers.Gamification is the use of game design elements in non-game contexts, and it has reported potential benefits for students. However, the proposals supporting teachers to create gamified ubiquitous learning situations are tied to specific activities and enactment technologies. To start addressing this issue, we propose a system to help teachers design and deploy these situations involving a variety of technologies frequently used in education.Adapting tasks to learner characteristics is essential when selecting appropriate tasks for learners [5]. This paper investigates how humans adapt exercise selection to learner self-esteem (SE) and performance, to allow a future Intelligent Tutoring System (ITS) to use these adaptations. Self esteem is an important factor in learning as it is a significant predictor of academic performance [4]. Previous research adapts task selection to other characteristics e.g. past performance [1], but little work focuses on task selection based on learner personality.

Conceptualizing a Framework for Adaptive Exercise Selection with Personality as a Major Learner Characteristic

Effective exercise selection based on learner characteristics is important for Intelligent Tutoring Systems to improve learning. Based on a literature review, we categorize learner characteristics used for adaptation in an ITS. We then present a preliminary framework of the relationship between some of these learner characteristics, with an emphasis on personality, and how they can be used by an ITS to adapt exercise selection.

Investigating the Impact of Personality and Cognitive Efficiency on the Selection of Exercises for Learners

Adapting to learner characteristics is essential when selecting exercises for learners. This paper investigates how humans adapt next exercise selection to learner personality and invested mental effort to enable a future Intelligent Tutoring System to use these adaptations. Participants were presented with validated stories of a learner`s personality at polarised levels, a validated story conveying the mental effort invested in carrying out a given task and an indication of a previous performance (just passing) at a simple arithmetic exercise. Participants were also shown a selection of validated exercises of varying difficulty levels and asked to select the exercise which they thought the learner should do next. We found that overall more difficult exercises were selected for learners who used little effort than for learners who used more effort. We found that although an exercise of slightly harder difficulty remains the most popular choice in the high and low self-esteem conditions, for low self-esteem, participants picked an exercise of lower or the same difficulty more often than in the high condition.

Encouraging students to study more: adapting feedback to personality and affective state

My PhD investigates how a conversational agent can adapt feedback to the personality and affective state of learners in order to increase learner motivation. This paper provides an overview of the research area, research questions and work to date.

Adapting exercise selection to performance, effort and self-esteem

ABSTRACT Adapting to learner characteristics is essential when selecting exercises for learners in an intelligent tutoring system. This paper investigates how humans adapt next exercise selection (in particular difficulty level) to learner personality, invested mental effort, and performance to inspire an adaptive exercise selection algorithm. First, the paper describes the investigations to produce validated materials for the main studies, namely the creation and validation of self-esteem personality stories, mental effort statements, and mathematical exercises with varying levels of difficulty. Next, through empirical studies, we investigate the impact on exercise selection of learners self-esteem (low versus high self-esteem) and effort (minimal, little, moderate, much, and all possible effort). Three studies investigate this for learners who had different performances on a previous exercise: just passing, just failing, and performed well. Participants considered a fictional learner with a certain performance, self-esteem and effort, and selected the difficulty level of the next mathematical exercise. We found that self-esteem, mental effort, and performance all impacted the difficulty level of the exercises selected for learners. Finally, using the results from the studies, we propose an algorithm that selects exercises with varying difficulty levels adapted to learner characteristics.

Computing authoring tests from competency questions: Experimental validation

This paper explores whether Authoring Tests derived from Competency Questions accurately represent the expectations of ontology authors. In earlier work we proposed that an ontology authoring interface can be improved by allowing the interface to test whether a given Competency Question (CQ) is able to be answered by the ontology at a given stage of its construction, an approach known as CQ-driven Ontology Authoring (CQOA). The experiments presented in the present paper suggest that CQOA’s understanding of CQs matches users’ understanding quite well, especially for inexperienced ontology authors.

Workshop on Interactivity in Healthcare Systems (IHS)

We are all living longer with average life expectancy increasing across the globe [1]. However, chronic conditions such as heart disease, strokes and cancer, coupled with an increasing global obesity problem still cause a growing number of premature deaths [1]. These conditions combined with an aging population cause a huge strain on healthcare provision.