The paper explores stylometry as a method to distinguish between texts created by Large Language Models (LLMs) and humans, addressing issues of model attribution, intellectual property, and ethical AI use. Stylometry has been used extensively to characterise the style and attribute authorship of texts. By applying it to LLM-generated texts, we identify their emergent writing patterns. The paper involves creating a benchmark dataset based on Wikipedia, with (a) human-written term summaries, (b) texts generated purely by LLMs (GPT-3.5/4, LLaMa 2/3, Orca, and Falcon), (c) processed through multiple text summarisation methods (T5, BART, Gensim, and Sumy), and (d) rephrasing methods (Dipper, T5). The 10-sentence long texts were classified by tree-based models (decision trees and LightGBM) using human-designed (StyloMetrix) and n-gram-based (our own pipeline) stylometric features that encode lexical, grammatical, syntactic, and punctuation patterns. The cross-validated results reached a performance of up to.87 Matthews correlation coefficient in the multiclass scenario with 7 classes, and accuracy between.79 and 1. in binary classification, with the particular example of Wikipedia and GPT-4 reaching up to.98 accuracy on a balanced dataset. Shapley Additive Explanations pinpointed features characteristic of the encyclopaedic text type, individual overused words, as well as a greater grammatical standardisation of LLMs with respect to human-written texts. These results show – crucially, in the context of the increasingly sophisticated LLMs – that it is possible to distinguish machine- from human-generated texts at least for a well-defined text type

This paper explores how Bayesian Knowledge Tracing (BKT) can be integrated with a pattern-based approach to enhance the development of virtual reality (VR) based serious games and simulations. These technologies allow for the prediction of user progress and the utilization of Artificial Intelligence (AI) methods to tailor difficulty levels based on individual needs. By combining BKT, pattern-based mechanics, and affective feedback, comprehensive data on user interactions, skills, and emotional states can be collected. This data enables the estimation of learners’ knowledge levels and the prediction of their progress.

The main aims of the presented study are to verify whether the amount of textures in a virtual scene affects task performance and to test whether visual imagery changes the relationship between realism and task performance. An experimental study with three groups differed in visual realism was conducted (n=100). Participants were asked to perform a task: taking on the role of a marshaller and positioning the plane on the airport apron. Results indicate that texturing does not affect task performance. Visual imagery is a moderator of the relationship between perceived realism and task performance. A high level of imagery interferes with a high realism assessment decreasing task performance.