Reinforcement learning from human feedback improves automatic speech recognition models for ancient Thai language. [PDF]
Sci RepPopun J +4 more
europepmc +1 more source
British Journal of Educational Technology, EarlyView.Abstract Generative AI is increasingly positioned as a peer in collaborative learning, yet its effects on ethical deliberation remain unclear. We report a between‐subjects experiment with university students (N = 217) who discussed an autonomous‐vehicle dilemma in triads under three conditions: human‐only control, supportive AI teammate or contrarian ...
Yueqiao Jin +7 more
wiley +1 more source
On the interface between linguistics, computer science and psychiatry: analyzing textual key-factors affecting BERT-based classification of schizophrenia in social media texts. [PDF]
Front Artif IntellMiranda E Silva JV +2 more
europepmc +1 more source
Happy me: Asymmetric bidirectional links between the self and positivity underpin biased processing
British Journal of Psychology, EarlyView.Abstract Understanding how the self relates to emotional valence is fundamental to theories of self‐concept and cognitive bias. While separate literatures have documented advantages for information associated with the self and information of positive valence, the mechanisms and directionality of their interaction remain poorly understood.
Naomi A. Lee, Douglas Martin, Jie Sui
wiley +1 more source
Linguistic and Behavioral Mechanisms of Cyberbullying Among Chinese Social Media Users: A Scoping Review. [PDF]
Behav Sci (Basel)Deng S, Shaari AH, Shaari AAH, Gu Y.
europepmc +1 more source
Multidimensional unipolar IRT and applications to the measurement of print exposure
British Journal of Mathematical and Statistical Psychology, EarlyView.Abstract Item response theory (IRT) has been a prominent modelling framework in educational and psychological measurement. Traditional IRT models are bipolar, commonly assuming symmetric measurement link functions and symmetric trait distributions over a latent continuum unbounded at both ends. However, many measured constructs, such as print exposure,
Qi (Helen) Huang, Daniel M. Bolt
wiley +1 more source
LEXF-ATT-XLM: A hybrid lexicon-enhanced attention model for hate speech detection in low-resource language Roman Urdu. [PDF]
PLoS OneAwan JJ, Hamid M, Alshalali TAN.
europepmc +1 more source
Imagination Will Not Be Automized: On AI Image Generators and Epistemic Oppression
Constellations, EarlyView.
Sarah Abel
wiley +1 more source
UrbanClipAtlas: A Visual Analytics Framework for Event and Scene Retrieval in Urban Videos
Computer Graphics Forum, EarlyView.Abstract Extracting actionable insights from long‐duration urban videos is often labor‐intensive: analysts must manually sift through raw footage to pinpoint target events or uncover broader behavioral trends. In this work, we present UrbanClipAtlas, a visual analytics system for exploring long urban videos recorded at street intersections ...
Joel Perca +5 more
wiley +1 more source
A hybrid CNN-LSTM approach for large-scale Twitter sentiment analysis with explainable artificial intelligence. [PDF]
Sci RepKılıç Z, Aslan E, Ozupak Y.
europepmc +1 more source