Below, you’ll find argument-related applications and source code from our research until early 2018. For more recent software, please check the github page of our research network Webis.
Applications and services
Argumentation-related essay scoring
An online demo that assesses four dimensions of the argumentation quality of persuasive student essays. Special thanks to Patrick Saad and Yamen Ajjour. [demo]
Review argumentation analysis
An online demo that analyzes the sentiment flow, the aspect-based sentiment, and the discourse structure of hotel reviews and scores the reviews. Developed in the BMBF research project ArguAna. [demo] [api]
Source code and feature files
Python code of papers since 2018
Most code from recent papers, particular the code in Python, can be found here: https://github.com/webis-de
COLING 2020. Argument quality assessment.
Java source code of the experiments on assessing 15 quality dimensions of arguments [zip 39mb]
ACL 2018a. Counterargument retrieval.
Java source code of the experiments on retrieving the best counterargument to an argument without prior topic knowledge. [zip 302 mb]
EMNLP 2017b. Modeling overall argumentation with tree kernels.
Java source code of the experiments on the impact of modeling overall argumentation with tree kernels on argumentation-related analysis tasks. [zip 98 mb]
ArgMining 2017b. Argument search framework.
The Java source code of an argument search framework that is build upon Apache UIMA and Apache Lucene. The argument search engine args relies on this framework. [link]
ACL 2017. Argumentation quality assessment.
Java source code of the experiments and results of the annotation study on argumentation quality assessment in theory and practice. [zip 2mb]
Java source code and Weka ARFF feature files of the experiments on argumentation-related essay scoring. [zip 244mb]
Java source code and Weka ARFF feature files of the experiments on the generality and domain robustness of sentiment flow as a model of web review argumentation. [zip 18mb]
Java source code and Weka ARFF feature files of the experiments on our approach to domain-robust sentiment analysis, which is based on a shallow model of review argumentation. [zip 47mb]