This is the code that was used for our approach on predicting judgments (whether a person or a group agrees or disagrees) with an assertion. The paper can be found here: http://www.aclweb.org/anthology/S18-2026
If you want to use the code, please cite:
@inproceedings{wojatzki2018agree,
title={Agree or Disagree: Predicting Judgments on Nuanced Assertions},
author={Wojatzki, Michael and Zesch, Torsten and Mohammad, Saif M. and Kiritchenko, Svetlana},
booktitle={Proceedings of the Seventh Joint Conference on Lexical and Computational Semantics},
pages={214--224},
year={2018}
}
This work is part of a larger project on understanding controversial issues. See: https://sites.google.com/view/you-on-issues/about or http://www.lrec-conf.org/proceedings/lrec2018/pdf/321.pdf If you are interested in the data, you can access it on the project's website. In that case, please cite:
@inproceedings{wojatzki2018qqd,
title={Quantifying Qualitative Data for Understanding Controversial Issues},
author={Wojatzki, Michael and Mohammad, Saif and Zesch, Torsten and Kiritchenko, Svetlana},
booktitle={Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018)},
pages={1405--1418},
year={2018}
}
For the machine learning approaches we rely on the machine learning framework DKPro TC (https://dkpro.github.io/dkpro-tc/), so the code is mostly written in java (except for the tensorflow experiments, that are written in python). The project uses Java 1.8. You need to set a DKPRO_HOME variable as described here https://zoidberg.ukp.informatik.tu-darmstadt.de/jenkins/job/DKPro%20TC%20Documentation%20(GitHub)/org.dkpro.tc%24dkpro-tc-doc/doclinks/1/#QuickStart
If you have any questions on the set-up please message me!
License
This work is licensed under Attribution-NonCommercial 2.0 Generic license (CC BY-NC 2.0) (https://creativecommons.org/licenses/by-nc/2.0/)
You are free to:
-
Share — copy and redistribute the material in any medium or format
-
Adapt — remix, transform, and build upon the material
Under the following terms:
-
Attribution — You must give appropriate credit, provide a link to the license, and indicate if changes were made. You may do so in any reasonable manner, but not in any way that suggests the licensor endorses you or your use.
-
NonCommercial — You may not use the material for commercial purposes.