Unstructured Data in Process Mining: A Systematic Literature Review

Abstract

A large proportion of available data is in unstructured form such as text, image, and video data. As data analysis methods continue to improve, it becomes easier to tap into and exploit unstructured data. Even in the process mining discipline, which is traditionally focused on structured data stored in process-aware information systems, solutions that integrate unstructured data receive increasing attention. To date, however, there is no empirical overview on how unstructured data is leveraged in process mining. This lack of insight also makes it difficult to identify the most promising avenues to advance process mining research. To address this issue, the study presents a systematic literature review, analyzing 24 primary studies selected from a total of 1,379 search results (i.e., research items) at the intersection of unstructured data and process mining. One of the main findings is that current research predominantly deals with textual data and concentrates on extracting event logs for process discovery. To guide future process mining research, the study proposes a research agenda that includes seven opportunities to address the identified research gaps.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 9 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.