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

TL;DR

pysentimiento is an open-source Python toolkit that simplifies opinion mining and social NLP tasks across multiple languages, offering state-of-the-art models and comprehensive performance evaluation.

Contribution

It introduces a multilingual, user-friendly Python library with integrated models for opinion mining, addressing accessibility and language limitations of existing tools.

Findings

High performance across multiple languages and tasks

Evaluation of fairness in social NLP models

Open-source tool enhances accessibility for researchers

Abstract

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.