Where do I start, how do I create a red thread through my argumentation, and which building blocks must not be missing in a good written response in the field of economics? The path from a good answer in one's head to a good answer on paper is often long. Especially with open-ended questions, which are common in economics, it can be challenging to structure one's thoughts sensibly and build arguments effectively. This is where the econArgueNiser can support students in a professional manner.
With the econArgueNiser, students do not write a complete answer to an open question, but instead, they write individual free-text responses to predefined argumentative building blocks. For this purpose, a specific argumentation structure for economics was developed as part of the DeepWrite research project, based on the Toulmin model, and consisting of four building blocks: Claim, Preferences, Limitations, and Conclusion. After students have written a text for each of these building blocks, they receive individual feedback from an AI that highlights strengths and areas for improvement in each element. Through the econArgueNiser, students not only learn an important argumentation structure for their discipline but also have the opportunity to specifically train their weaknesses.
The econArgueNiser can be used both interactively in synchronous lectures in the classroom and for asynchronous learning. The online tool is integrated into the audience-response system classEx. To use the econArgueNiser, students only need a computer or a mobile device like a smartphone or tablet.
The most important tool for a lawyer is language. This is learned in law studies through the legal writing style and the associated argumentative skills. Acquiring this somewhat unusual form of knowledge presentation can initially pose challenges for students. The legal writing style is not an end in itself, but rather structures thoughts. This is where the legalArgueNiser comes in: The AI-based application presents a brief factual scenario, which students then need to solve in the legal writing style. The structure is already technically predefined: divided into introduction, definition, subsumption, and conclusion, with each section having its own text field where students insert their response elements.
Afterwards, students receive individual AI-based feedback for each of the four elements. This feedback takes into account both content-related and argumentative strengths and weaknesses.
The legalArgueNiser is also integrated into the audience-response system classEx and can be used both in the lecture hall and from home.
Would you like to try out the Jura ArgueNiser? Then you can do so here.
The Annotation Parser Tool, provided by the Data Science team, automates the extraction of annotated structured data from complex legal documents in .docx format, particularly suitable for annotations in Gutachtenstil with detailed classes and properties. This tool effectively identifies and represents hierarchical relationships within anntotations, making it useful for documents with complex legal arguments. It uses robust parsing techniques for accurate and efficient extraction. The extracted annotations are conveniently available for download in JSON and CSV formats.
Interested? Then you can test a demo version of the Annotation Parser Tool here!
