ChatGPT Label: Comparing the Quality of Human-Generated and LLM-Generated Annotations in Low-resource Language NLP Tasks

AH Nasution, A Onan - IEEE Access, 2024 - ieeexplore.ieee.org
This research paper presents a comprehensive comparative study assessing the quality of
annotations in Turkish, Indonesian, and Minangkabau Natural Language Processing (NLP) …

GameVibe: a multimodal affective game corpus

M Barthet, M Kaselimi, K Pinitas, K Makantasis… - Scientific Data, 2024 - nature.com
As online video and streaming platforms continue to grow, affective computing research has
undergone a shift towards more complex studies involving multiple modalities. However …

Across-game engagement modelling via few-shot learning

K Pinitas, K Makantasis, GN Yannakakis - arxiv preprint arxiv:2409.13002, 2024 - arxiv.org
Domain generalisation involves learning artificial intelligence (AI) models that can maintain
high performance across diverse domains within a specific task. In video games, for …

[PDF][PDF] Varying the context to advance affect modelling: A study on game engagement prediction

K Pinitas, N Rasajski, M Barthet… - Proceedings of the …, 2024 - antoniosliapis.com
Affective computing faces a pressing challenge: the limited ability of affect models to
generalise amidst varying contextual factors within the same task. While well recognised …

Deep Learning Methods for Affect and Schizophrenia Symptom Estimation

N Foteinopoulou - 2024 - qmro.qmul.ac.uk
Human communication encompasses a rich mixture of verbal and non-verbal cues,
significantly contributing to conveying emotion and mental state. While humans instinctively …