python-webis: Python wrapper for the webis Twitter sentiment evaluation ensemble
This is a Python wrapper around the Java implementation of a Twitter sentiment evaluation framework presented by Hagen et al. (2015). In Zimbra et al. (2018)’s evaluation of “The State-of-the-Art in Twitter Sentiment Analysis” this approach received the highest score in classification accuracy (average across five categories of content, table 4, p5:15).
This package is available from the PyPi software repository: https://pypi.org/project/webis/
Its source code is hosted on GitLab: https://gitlab.com/christoph.fink/python-webis
Note that the attached file (version 0.3.0) is up-to-date as of April 28, 2020, and newer versions will be published on PyPi and GitLab.