A Wizard of Oz Study Simulating API Usage Dialogues with a Virtual Assistant

TL;DR

This paper presents Wizard of Oz experiments to create a dataset simulating API usage dialogues with a virtual assistant, aiming to improve AI support for programmers in software engineering tasks.

Contribution

It introduces a novel dataset of simulated API assistance dialogues collected through Wizard of Oz experiments with professional programmers.

Findings

Diverse interaction patterns observed in dialogues

Annotated dialogue acts along multiple dimensions

Dataset facilitates development of API-focused virtual assistants

Abstract

Virtual Assistant technology is rapidly proliferating to improve productivity in a variety of tasks. While several virtual assistants for everyday tasks are well-known (e.g., Siri, Cortana, Alexa), assistants for specialty tasks such as software engineering are rarer. One key reason software engineering assistants are rare is that very few experimental datasets are available and suitable for training the AI that is the bedrock of current virtual assistants. In this paper, we present a set of Wizard of Oz experiments that we designed to build a dataset for creating a virtual assistant. Our target is a hypothetical virtual assistant for helping programmers use APIs. In our experiments, we recruited 30 professional programmers to complete programming tasks using two APIs. The programmers interacted with a simulated virtual assistant for help - the programmers were not aware that the assistant was actually operated by human experts. We then annotated the dialogue acts in the corpus along four dimensions: illocutionary intent, API information type(s), backward-facing function, and traceability to specific API components. We observed a diverse range of interactions that will facilitate the development of dialogue strategies for virtual assistants for API usage.