The augmented social scientist: Using sequential transfer learning to annotate millions of texts with human-level accuracy

S Do, É Ollion, R Shen - Sociological Methods & Research, 2024‏ - journals.sagepub.com
The last decade witnessed a spectacular rise in the volume of available textual data. With
this new abundance came the question of how to analyze it. In the social sciences, scholars …

QuaPy: A Python-based framework for quantification

A Moreo, A Esuli, F Sebastiani - Proceedings of the 30th ACM …, 2021‏ - dl.acm.org
QuaPy is an open-source framework for performing quantification (aka supervised
prevalence estimation), written in Python. Quantification is the task of training quantifiers via …

[كتاب][B] Learning to quantify

A Esuli, A Fabris, A Moreo, F Sebastiani - 2023‏ - library.oapen.org
This open access book provides an introduction and an overview of learning to quantify (aka
“quantification”), ie the task of training estimators of class proportions in unlabeled data by …

Tweet sentiment quantification: An experimental re-evaluation

A Moreo, F Sebastiani - PLoS One, 2022‏ - journals.plos.org
Sentiment quantification is the task of training, by means of supervised learning, estimators
of the relative frequency (also called “prevalence”) of sentiment-related classes (such as …

A survey of recent machine learning techniques for stock prediction methodologies

VK Vishwakarma, NP Bhosale - Neural Computing and Applications, 2024‏ - Springer
The prime purpose of the research is to investigate stock price prediction techniques and
their shortcomings concerning particular characteristics and performance measures. The …

MC-SQ: A highly accurate ensemble for multi-class quantification

Z Donyavi, A Serapio, G Batista - Proceedings of the 2023 SIAM International …, 2023‏ - SIAM
Quantification research proposes methods to estimate the class distribution in an
independent sample. Many areas, such as epidemiology, sentiment analysis, political …

[PDF][PDF] Pitfalls in quantification assessment

W Hassan, AG Maletzke, GEAPA Batista - Proceedings, 2021‏ - repositorio.usp.br
Quantification is a research area that develops methods that estimate the class attribute
prevalence in an independent sample. Like the other fields in Machine Learning …

Quantification using permutation-invariant networks based on histograms

O Pérez-Mon, A Moreo, JJ Coz, P González - Neural Computing and …, 2024‏ - Springer
Quantification, also known as class prevalence estimation, is the supervised learning task in
which a model is trained to predict the prevalence of each class in a given bag of examples …

Multi-label quantification

A Moreo, M Francisco, F Sebastiani - ACM Transactions on Knowledge …, 2023‏ - dl.acm.org
Quantification, variously called supervised prevalence estimation or learning to quantify, is
the supervised learning task of generating predictors of the relative frequencies (aka …

Accurate and Well-Calibrated ICD Code Assignment Through Attention Over Diverse Label Embeddings

G Gomes, I Coutinho, B Martins - arxiv preprint arxiv:2402.03172, 2024‏ - arxiv.org
Although the International Classification of Diseases (ICD) has been adopted worldwide,
manually assigning ICD codes to clinical text is time-consuming, error-prone, and …