Stuck? No worries!: Task-aware Command Recommendation and Proactive Help for Analysts

TL;DR

This paper introduces a task-aware command recommendation and help prediction system for data analytics software, using topic modeling and neural networks to assist users in real-time, improving usability and support.

Contribution

It presents a novel neural model that combines task awareness and proactive help prediction to enhance command recommendation in analytics tools.

Findings

Neural models outperform baseline methods in command recommendation accuracy.

Proactive help prediction effectively identifies users in need of assistance.

Task-aware recommendations improve user experience in data analytics applications.

Abstract

Data analytics software applications have become an integral part of the decision-making process of analysts. Users of such a software face challenges due to insufficient product and domain knowledge, and find themselves in need of help. To alleviate this, we propose a task-aware command recommendation system, to guide the user on what commands could be executed next. We rely on topic modeling techniques to incorporate information about user's task into our models. We also present a help prediction model to detect if a user is in need of help, in which case the system proactively provides the aforementioned command recommendations. We leverage the log data of a web-based analytics software to quantify the superior performance of our neural models, in comparison to competitive baselines.