Predicting Audio Advertisement Quality

TL;DR

This paper introduces a deep learning approach to automatically predict the quality of online audio ads based on acoustic features, aiming to enhance ad ranking and creation for better user engagement.

Contribution

It presents the first large-scale study on audio ad quality prediction using raw waveform features and a novel deep learning model outperforming traditional methods.

Findings

Deep learning model outperforms models with hand-crafted features

Acoustic features like harmony, rhythm, and timbre relate to ad quality

Proposed proxy metric LCR effectively measures ad engagement

Abstract

Online audio advertising is a particular form of advertising used abundantly in online music streaming services. In these platforms, which tend to host tens of thousands of unique audio advertisements (ads), providing high quality ads ensures a better user experience and results in longer user engagement. Therefore, the automatic assessment of these ads is an important step toward audio ads ranking and better audio ads creation. In this paper we propose one way to measure the quality of the audio ads using a proxy metric called Long Click Rate (LCR), which is defined by the amount of time a user engages with the follow-up display ad (that is shown while the audio ad is playing) divided by the impressions. We later focus on predicting the audio ad quality using only acoustic features such as harmony, rhythm, and timbre of the audio, extracted from the raw waveform. We discuss how the characteristics of the sound can be connected to concepts such as the clarity of the audio ad message, its trustworthiness, etc. Finally, we propose a new deep learning model for audio ad quality prediction, which outperforms the other discussed models trained on hand-crafted features. To the best of our knowledge, this is the first large-scale audio ad quality prediction study.