Process mining has been successfully used in automatic knowledge discovery and in providing guidance or support. The known process mining approaches rely on processes being executed with the help of information systems thus enabling the automatic capture of process traces as event logs. However, there are many other fields such as Humanities, Social Sciences and Medicine where workers follow processes and log their execution manually in textual forms instead. The problem we tackle in this paper is mining process instance models from unstructured, text-based process traces. Using natural language processing with a focus on the verb semantics, we created a novel unsupervised technique TextProcessMiner that discovers process instance models in two steps: 1.ActivityMiner mines the process activities; 2.ActivityRelationshipMiner mines the sequence, parallelism and mutual exclusion relationships between activities. We employed technical action research through which we validated and preliminarily evaluated our proposed technique in an Archaeology case. The results are very satisfactory with 88% correctly discovered activities in the log and a process instance model that adequately reflected the original process. Moreover, the technique we created emerged as domain independent.

Research in the digital humanities often involves vague information, either because our objects of study lack clearly defined boundaries, or because our knowledge about them is incomplete or hypothetical, which is especially true in disciplines about our past (such as history, archaeology, and classical studies). Most techniques used to represent data vagueness emerged from natural sciences, and lack the expressiveness that would be ideal for humanistic contexts. Building on previous work, we present here a conceptual framework based on the ConML modelling language for the expression of information vagueness in digital humanities. In addition, we propose an implementation on non-relational data stores, which are becoming popular within the digital humanities. Having clear implementation guidelines allow us to employ search engines or big data systems (commonly implemented using non-relational approaches) to handle the vague aspects of information. The proposed implementation guidelines have been validated in practice, and show how we can query a vagueness-aware system without a large penalty in analytical and processing power.