Organizations generate vast amounts of unstructured textual data – a valuable source of information that frequently remains underutilized for process mining. However, textual descriptions often record exceptions and manual activities absent from structured data, and therefore, enable a better understanding of deviations from the expected business process behavior. Importantly, unstructured sources typically retain the object-centric characteristics of real-world processes – information that gets flattened or lost in case-centric event logs. Yet, existing approaches primarily target structured data sources or produce case-centric event logs. To address this gap, we present an automated approach to derive object-centric event logs directly from unstructured textual descriptions. The approach comprises two subcomponents: a collector that identifies events and objects (including their attributes and relationships), and a refiner that consolidates and cleans the extracted information. We instantiate each subcomponent in heuristic and generative implementations and create four pairwise combinations of collector and refiner instances to assess the effectiveness of heuristic natural language processing and generative artificial intelligence techniques. We compare these variants quantitatively and qualitatively in a controlled, artificial setting based on synthesized texts and demonstrate the practical utility on two naturally occurring corpora (fire status updates and a legal judgment). Our results show that the configurations with a generative collector achieve the highest extraction quality. In particular, the fully generative variant produces coherent and standardized event and object labels. Overall, this study fills a notable research gap by enabling the incorporation of textual information into process mining applications. • Proposes an approach to extract object-centric event logs from textual descriptions. • Develops the approach using the Design Science Research methodology. • Implements the approach using heuristic NLP and generative AI techniques. • Evaluates the approach on synthetic and naturalistic textual descriptions. • Confirms the approach’s practical utility on fire status updates and a legal judgment.

A fundamental requirement for the successful application of process mining are event logs of high data quality that can be constructed from structured data stored in organizations’ core information systems. However, a substantial amount of data is processed outside these core systems, particularly in organizations doing consumer business with many customer interactions per day, which generate high amounts of unstructured text data. Although Natural Language Processing (NLP) and machine learning enable the exploitation of text data, these approaches remain challenging due to the required high amount of labeled training data. Recent advances in NLP mitigate this issue by providing pre-trained and ready-to-use language models for various tasks such as Natural Language Inference (NLI). In this paper, we develop an approach that utilizes NLI to derive topics and process activities from customer service conversations and that represents them in a standardized XES event log. To this end, we compute the probability that a sentence describing the topic or the process activity can be inferred from the customer’s inquiry or the agent’s response using NLI. We evaluate our approach utilizing an existing corpus of more than 500,000 customer service conversations of three companies on Twitter. The results show that NLI helps construct event logs of high accuracy for process mining purposes, as our successful application of three different process discovery algorithms confirms.