pysentimiento: A Python Toolkit for Opinion Mining and Social NLP tasks

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Pérez, Juan Manuel, Rajngewerc, Mariela, Giudici, Juan Carlos, Furman, Damián A., Luque, Franco, Alemany, Laura Alonso, Martínez, María Vanina
Format: Preprint
Published: 2021
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910525271572480
author Pérez, Juan Manuel
Rajngewerc, Mariela
Giudici, Juan Carlos
Furman, Damián A.
Luque, Franco
Alemany, Laura Alonso
Martínez, María Vanina
author_facet Pérez, Juan Manuel
Rajngewerc, Mariela
Giudici, Juan Carlos
Furman, Damián A.
Luque, Franco
Alemany, Laura Alonso
Martínez, María Vanina
contents In recent years, the extraction of opinions and information from user-generated text has attracted a lot of interest, largely due to the unprecedented volume of content in Social Media. However, social researchers face some issues in adopting cutting-edge tools for these tasks, as they are usually behind commercial APIs, unavailable for other languages than English, or very complex to use for non-experts. To address these issues, we present pysentimiento, a comprehensive multilingual Python toolkit designed for opinion mining and other Social NLP tasks. This open-source library brings state-of-the-art models for Spanish, English, Italian, and Portuguese in an easy-to-use Python library, allowing researchers to leverage these techniques. We present a comprehensive assessment of performance for several pre-trained language models across a variety of tasks, languages, and datasets, including an evaluation of fairness in the results.
format Preprint
id arxiv_https___arxiv_org_abs_2106_09462
institution arXiv
publishDate 2021
record_format arxiv
spellingShingle pysentimiento: A Python Toolkit for Opinion Mining and Social NLP tasks
Pérez, Juan Manuel
Rajngewerc, Mariela
Giudici, Juan Carlos
Furman, Damián A.
Luque, Franco
Alemany, Laura Alonso
Martínez, María Vanina
Computation and Language
In recent years, the extraction of opinions and information from user-generated text has attracted a lot of interest, largely due to the unprecedented volume of content in Social Media. However, social researchers face some issues in adopting cutting-edge tools for these tasks, as they are usually behind commercial APIs, unavailable for other languages than English, or very complex to use for non-experts. To address these issues, we present pysentimiento, a comprehensive multilingual Python toolkit designed for opinion mining and other Social NLP tasks. This open-source library brings state-of-the-art models for Spanish, English, Italian, and Portuguese in an easy-to-use Python library, allowing researchers to leverage these techniques. We present a comprehensive assessment of performance for several pre-trained language models across a variety of tasks, languages, and datasets, including an evaluation of fairness in the results.
title pysentimiento: A Python Toolkit for Opinion Mining and Social NLP tasks
topic Computation and Language
url https://arxiv.org/abs/2106.09462