Interpreting Cross-Domain User Activity Sequences with LLMs

ACL ARR 2026 January Submission6161 Authors

Keywords: user activity analysis, large language models, sequence modeling

Abstract: Sequential or time‑stamped activity logs provide objective records of digital application usage, yet their granularity and noise often obscure meaningful insights into people’s work. Such insights are essential for improving digital products in ways grounded in real‑world user interactions. Prior research has applied deep learning models to cluster user actions into high-level workflow activities, but these approaches are highly sensitive to noise and struggle to generalize across applications. To address this limitation, we introduce WorkflowView, a framework that leverages large language models (LLMs) to abstract low-level action sequences into high-level workflow activities. We establish the effectiveness and generality of our approach across three distinct, challenging sequential tasks and diverse domains: (a) zero-shot task description reconstruction from browser logs (achieving high semantic similarity, $\mu_{sim} = 0.91$), (b) few-shot student dropout prediction using MOOC activity logs (reaching weighted $F_1 = 0.90$ with only five few-shot examples), and (c) anonymized, privacy-preserving analysis of AI tool integration within document workflows on a proprietary platform. Our work demonstrates that LLM-based abstraction is a robust and efficient path forward for transforming low-level behavioral data into high-level, interpretable, and actionable insights. We also discuss practical considerations for deploying LLM‑based inferences within logging infrastructures, including computational efficiency and user privacy.

Paper Type: Long

Research Area: NLP Applications

Research Area Keywords: user activity sequence inference, business NLP, data-to-text generation

Contribution Types: NLP engineering experiment

Languages Studied: English

Submission Number: 6161