The article "GSITK: A sentiment analysis framework for agile replication and development", by Oscar Araque, J. Fernando Sánchez-Rada, and Carlos A. Iglesias has been published in the SoftwareX journal (1.959 impact factor, JCR Q3 2020). The paper describes the GSITK software, which is a framework to perform a wide variety of sentiment analysis tasks including dataset acquisition, text preprocessing, model design, and performance evaluation.

The full paper can be openly accessed at this URL.

Abstract:

GSITK is a framework to perform a wide variety of sentiment analysis tasks, including dataset acquisition, text preprocessing, model design, and performance evaluation. The framework is oriented to both researchers and practitioners, easing the replication of previous sentiment models, as well as offering implementations of common tasks. This is achieved by building several abstractions on top of popular libraries such as scikit-learn and NLTK. In this way, GSITK allows users to implement complex sentiment pipelines using comprehensible Python code. The framework is Open Source and has been used successfully in several research projects and competitions.