A Psychonic Approach to the Design of a Cognitive Companion Supporting Intentional Forgetting
We present the design basics of the cognitive companion Dare2Del which supports humans to temporarily ignore or permanently forget digital objects. The system infers the irrelevancy of digital objects based on a symbolic knowledge representation and white box machine learning. The logic-like knowledge base of the system is split in facts that apply to individual digital objects (data) and general rules which hold for all objects in the domain (domain theory). The irrelevancy of digital objects is inferred using explicit rules, which are learned by an inductive logic programming approach. In this paper, we focus on the knowledge base and the inference for the permanent deletion of files. First, we present relations available for data and domain theory. Then, we evaluate whether the chosen relations are suitable for inferring the irrelevancy of files. We evaluate a handcrafted irrelevancy rule on an artificial file system with 500 files. For that, we developed a generator for knowledge bases of artificial file systems. We were able to classify 97.2% of the files correctly as irrelevant or relevant.