arXiv subjects

Thomas Lancaster

Publications and source records attributed to Thomas Lancaster.

4 recordsLinked to original sources

arXiv2024

The Gig's Up: How ChatGPT Stacks Up Against Quora on Gig Economy Insights

Generative AI is changing the way in which humans seek to find answers to questions in different fields including on the gig economy and labour markets, but there is limited information available about closely ChatGPT simulated output matches that obtainable from existing question and answer platforms. This paper uses ChatGPT as a research assistant to explore how far ChatGPT can replicate Quora question and answers, using data from the gig economy as an indicative case study. The results from content analysis suggest that Quora is likely to be asked questions from users looking to make money and answers are likely to include personal experiences and examples. ChatGPT simulated versions are less personal and more concept-based, including considerations on employment implications and labour rights. It appears therefore that generative AI simulates only part of what a human would want in their answers relating to the gig economy. The paper proposes that a similar comparative methodology would also be useful across other research fields to help in establishing the best real world uses of generative AI.

cs.CY↗

arXiv2024

A Large Language Model Supported Synthesis of Contemporary Academic Integrity Research Trends

This paper reports on qualitative content analysis undertaken using ChatGPT, a Large Language Model (LLM), to identify primary research themes in current academic integrity research as well as the methodologies used to explore these areas. The analysis by the LLM identified 7 research themes and 13 key areas for exploration. The outcomes from the analysis suggest that much contemporary research in the academic integrity field is guided by technology. Technology is often explored as potential way of preventing academic misconduct, but this could also be a limiting factor when aiming to promote a culture of academic integrity. The findings underscore that LLM led research may be option in the academic integrity field, but that there is also a need for continued traditional research. The findings also indicate that researchers and educational providers should continue to develop policy and operational frameworks for academic integrity. This will help to ensure that academic standards are maintained across the wide range of settings that are present in modern education.

cs.CY↗

arXiv2023

Classification of Major Depressive Disorder Using Vertex-Wise Brain Sulcal Depth, Curvature, and Thickness with a Deep and a Shallow Learning Model

Major depressive disorder (MDD) is a complex psychiatric disorder that affects the lives of hundreds of millions of individuals around the globe. Even today, researchers debate if morphological alterations in the brain are linked to MDD, likely due to the heterogeneity of this disorder. The application of deep learning tools to neuroimaging data, capable of capturing complex non-linear patterns, has the potential to provide diagnostic and predictive biomarkers for MDD. However, previous attempts to demarcate MDD patients and healthy controls (HC) based on segmented cortical features via linear machine learning approaches have reported low accuracies. Here, we used globally representative data from the ENIGMA-MDD working group containing 7,012 participants from 30 sites (N=2,772 MDD and N=4,240 HC), which allows a comprehensive analysis with generalizable results. Based on the hypothesis that integration of vertex-wise cortical features can improve classification performance, we evaluated the classification of a DenseNet and a Support Vector Machine (SVM), with the expectation that the former would outperform the latter. We found that both classifiers exhibited close to chance performance (balanced accuracy DenseNet: 51%; SVM: 53%), when estimated on unseen sites. Slightly higher classification performance (balanced accuracy DenseNet: 58%; SVM: 55%) was found when the cross-validation folds contained subjects from all sites, indicating site effect. In conclusion, the integration of vertex-wise morphometric features and the use of the non-linear classifier did not lead to the differentiability between MDD and HC. Our results support the notion that MDD classification on this combination of such features and classifiers is unfeasible. Perhaps more sophisticated integration of multimodal information may lead to a higher performance in this diagnostic task.

q-bio.QM↗

arXiv2022

Multi-site benchmark classification of major depressive disorder using machine learning on cortical and subcortical measures

Machine learning (ML) techniques have gained popularity in the neuroimaging field due to their potential for classifying neuropsychiatric disorders. However, the diagnostic predictive power of the existing algorithms has been limited by small sample sizes, lack of representativeness, data leakage, and/or overfitting. Here, we overcome these limitations with the largest multi-site sample size to date (n=5,356) to provide a generalizable ML classification benchmark of major depressive disorder (MDD). Using brain measures from standardized ENIGMA analysis pipelines in FreeSurfer, we were able to classify MDD vs healthy controls (HC) with around 62% balanced accuracy, but when harmonizing the data using ComBat balanced accuracy dropped to approximately 52%. Similar results were observed in stratified groups according to age of onset, antidepressant use, number of episodes and sex. Future studies incorporating higher dimensional brain imaging/phenotype features, and/or using more advanced machine and deep learning methods may achieve more encouraging prospects.

q-bio.QM↗