From Interaction to Intent: Inferring User Objectives from Provenance Logs

2026-07-05

AI Summary

This study addresses the challenge of automatically inferring users’ high-level analytical intents from fine-grained interaction logs during exploratory data analysis to enable intelligent assistance. By collecting provenance logs of interactions within multidimensional visualizations, the authors construct sequential behavior models that incorporate temporal context and employ embedding-based representation learning coupled with classification techniques for intent recognition. The work provides the first empirical validation that low-level interactions encode discernible patterns corresponding to high-level analytical intents. It successfully identifies distinctive interaction signatures associated with tasks such as clustering and anomaly detection, and demonstrates robust generalization of intent prediction across different datasets and dimensionality reduction methods with high accuracy.

Abstract

The ability to automatically infer analytic intent from user interaction histories could enable interactive AI systems to proactively assist users during exploratory data analysis. In this paper, we examine whether provenance logs -- detailed records capturing sequences and timing of user interactions -- can be used to classify user intentions in visual exploration tasks. To investigate this, we record how participants interact with multiple multidimensional data projections across a range of analytic tasks, capturing fine-grained mouse interaction data throughout each session. We find that distinct behavioral signatures emerge across different analytic objectives. For instance, users examining properties of specific clusters exhibit markedly different interaction patterns compared to those searching for outliers. More importantly, we show that embedding contextual information into interaction provenance enables classifiers to predict user objectives that generalize across datasets and projection methods. These findings demonstrate that low-level interaction data can serve as a practical bridge to high-level analytic intent, contributing to the development of intent-aware visualization systems.

Problem

• analytic intent
• provenance logs
• user interaction
• visual exploration
• intent inference

Innovation

• analytic intent inference
• interaction provenance
• behavioral signatures
• intent-aware visualization
• cross-dataset generalization