Today’s Social Web allows people in a community of practice to post their own experiences in a diversity of content repositories such as blogs, forums, Q&A websites, etc. However, today there is no real support in finding and reusing these rich collections of personal experience. Current search functions available merely consider experience as text to be indexed as any other text and searched and found as any other document.
The objective of the project cluster Extraction and Case-Based Processing of Experiential Knowledge from Internet Communities is the analysis, the development, and the experimental application and evaluation of new knowledge-based methods, particularly from case-based reasoning (CBR), information extraction, and machine learning to extract and process experiences in Internet communities.
The project 'EVER - Extraction and Processing of Procedural Experience Knowledge in Workflows' focuses on procedural experiential knowledge, which describes how to do a certain thing or to achieve a certain goal through a sequence of steps. In this project we deal with the representation of such knowledge in the form of workflows and aim at improving the CBR methodology by enabling the reasoning with workflow cases extracted from a semi-structured representation (as they occur in Internet Communities).
The project was funded in a first funding period by the 'Deutsche Forschungsgemeinschaft' (DFG) from 2011 to 2016 and was executed at the Universities of Trier and Frankfurt. The second funding period ran from 2016 to 2021.
- M.Sc. Christian Zeyen (from 2016)
- M.Sc. Gilbert Müller (until 2016)
- Dipl.-Inf. Pol Schumacher (until 2016)
A summary of the project results can be found here.
Best phd student paper award on the 22nd International Conference on Case-Based Reasoning (ICCBR 2014) Conference in Cork, Ireland for the paper "Workflow Streams: A Means for Compositional Adaptation in Process-Oriented CBR" by Gilbert Müller and Ralph Bergmann (paper details).
A list of publications of the project can be found here.
CookingCake is a demo for the generation of sandwich recipes based on recipes represented as workflows. CookingCake makes use of the methods developed as part of the EVER project.
We used our Workflow Maker to automatically generate workflows in a manually defined domain using a planer. Here you can find two example repositories of pizza and pasta workflows.
Another workflow repository is available via the EVER page of the Goethe University of Frankfurt.