AI and Measurement Concerns: Dealing with Imbalanced Data in Autoscoring
Abstract Unbiasedness for proficiency estimates is important for autoscoring engines since the outcome might be used for future learning or placement. Imbalanced training data may lead to certain biases and lower the prediction accuracy for classification algorithms.
Yunting Liu +3 more
wiley +1 more source
Large language models reflect the ideology of their creators. [PDF]
Buyl M +10 more
europepmc +1 more source
Milgram's experiment in the knowledge space: individual navigation strategies. [PDF]
Zhu M, Kertész J.
europepmc +1 more source
Research citations building trust in Wikipedia: Results from a survey of published authors. [PDF]
Areia C +3 more
europepmc +1 more source
Reply to Yu et al.: Datasets, human judges, and future directions for evaluating AI-AI bias. [PDF]
Kulveit J +5 more
europepmc +1 more source
Age and gender distortion in online media and large language models. [PDF]
Guilbeault D, Delecourt S, Desikan BS.
europepmc +1 more source
LegitPhish: A large-scale annotated dataset for URL-based phishing detection. [PDF]
Potpelwar RS, Kulkarni UV, Waghmare JM.
europepmc +1 more source
Population interest in and adequacy of the information on the safety of antineoplastic agents in the Spanish edition of Wikipedia. [PDF]
Climent-Ballester S +2 more
europepmc +1 more source
The COVID-19 pandemic and the worldwide online interest in telepsychiatry: an infodemiological study from 2004 to 2022. [PDF]
Alibudbud R.
europepmc +1 more source
Correction: AI-assisted literature exploration of innovative Chinese medicine formulas. [PDF]
Chung MC, Su LJ, Chen CL, Wu LC.
europepmc +1 more source

