Coding-based assessment is essential not only for evaluating students' programming skills but also for assessing their ability to apply theoretical concepts to real-world scenarios. Jupyter Notebooks constitute a unique platform to assess coding-based pieces of work. Using a Jupyter Notebook, students can write, execute and visualise code while documenting their pro-cess through explanations, equations, and multimedia elements. However, identifying cases of plagiarism and collusion in Jupyter Notebooks can be challenging. Since Jupyter Notebooks cannot be processed by traditional text-based plagiarism detection tools, the ability to identify plagiarism largely relies on manual approaches. Hence, to fully benefit from Jupyter Notebooks as an assessment platform, automatic approaches that can contribute to identifying plagiarism and collusion are needed. In this paper, we introduce a new tool - JBEval, that identifies similar code and text blocks in a collection of Jupyter Notebooks and provides similarity scores for overall code and text individually. JBEval also provides a visual comparison of any two Jupyter Notebooks, allowing to trace identical blocks for further investigation and reporting. Our similarity detection algorithm is parameterized for controlling the aggressiveness of the similarity-based detection process, which makes it adaptable to a wide diversity of courses. This fast and reliable tool will be made widely accessible by sharing it in the public domain, enabling educators across diverse disciplines to integrate it into their assessment workflows.

Competition-Based Learning (CBL) provides an engaging educational approach by combining collaboration with competition. However, learners often struggle with illstructured problems, particularly in fields like Big Data Analytics. This study investigates how Generative AI, specifically ChatGPT, can support CBL through distributed scaffolding, combining both structural and problem-based approaches to enhance learning. Implemented in an undergraduate Big Data Analytics course, the scaffolding utilized Kaggle for practical problem-solving projects. ChatGPT provided personalized feedback, helping students navigate complex tasks and enhance critical thinking. A mixedmethod evaluation involving surveys and interviews showed that the ChatGPT-supported scaffolding significantly improved knowledge construction, problem-solving skills, and student engagement. These findings highlight the potential of integrating AI-driven scaffolding in CBL environments to address learning challenges, ultimately fostering more effective educational experiences.

Mixed Reality (MR) is a hybrid technology that blends digital elements with the physical world, enabling interaction across both worlds. The integration of typical video games into MR headsets can be challenging due to device limitations, user comfort, limited hardware capability, and interaction modalities. This research investigates two types of MR games, with a focus on spatial aspects, player experience, and players’ brain activity analysis. We analyzed design considerations and interaction patterns suitable for MR environments. For our study, we developed two games: a high-intensity action game and a low-intensity puzzle-solving game, and deployed them on Microsoft HoloLens 2. We conducted user studies with 14 participants using objective and subjective data collection methods. Objective data was gathered through an electroencephalogram (EEG) device, measuring players’ brain activity and emotional states. Subjective data was collected from post-test surveys that evaluated user experience, cognitive load, and emotional responses.

Detecting the elements of deception in a conversation takes years of study and experience, and it is a skill set primarily used in law-enforcement agencies. In ever-growing business opportunities, organisations employ teleoperators to provide support and services to their large customer base, which is a potential platform for fraud. With technological advancements, it is desirable to have an automated system that spots the deceptive elements in the conversation, and provides this information to the teleoperators to better support them in their interactions. We propose the Decision Engine to detect deceptive conversation based on the proximity of linguistic markers present, which produces a deception score for a conversation and highlights the potential deceptive elements of the conversation. In collaboration with behavioural experts, we have selected ten linguistic markers that potentially indicate deception. We have built a variety of models to detect the trigger terms for selected linguistic markers without ambiguity, using either regular expressions or the BERT model. The BERT model has been trained on a conversational dataset that we collated and was labelled by our behavioural experts. The proposed Decision Engine employs the BERT model and regular expressions to detect the linguistic markers and compute the proximity features to further estimate the deception score. We evaluated the proposed approach on the Columbia-SRI-Colorado (CSC) dataset and a real-world Financial Services dataset. In addition to accuracy, we have also employed the True Positive Rate metric, with a high enough threshold to avoid any false-positive cases, which we indicate as TPRF0. The Decision Engine achieves 69% accuracy and 46% TPRF0 for the CSC dataset and 72% accuracy and 60% TPRF0 for the Financial Services dataset. In contrast, a baseline model, which uses non-proximity features achieves 67% accuracy and 32% TPRF0 for the CSC dataset and 67% accuracy and 10% TPRF0 for the Financial Services dataset. Furthermore, using the Decision Engine, the impact of the proximity of markers on the deception score has been analysed by our behavioural experts to provide insight into linguistic behaviour in relation to deception.

The low-cost electroencephalogram (EEG) devices are widely used by researchers in human-computer interaction, video games, and software systems to evaluate the impact of interaction design on user emotions. However, the performance metrics of emotion states provided by a low-cost EEG device suffer several reliability and accuracy issues, which can mislead the design decisions of the developers. In this research, we combined the EEG device with three virtual reality games to investigate the reliability of performance metrics extracted from the EEG data. We conducted the experiment with 14 players using virtual reality games with ranging levels of in-game actions. Our analysis shows that there is a significant difference between performance metrics provided by the EEG device and the actual players' experience. Finally, we used ad-hoc linear models to estimate the level of players' emotion states directly from the raw EEG. We also show the different brain activity maps for individual emotions, which reveal the commonly known relation between brain activity and specific emotions.