Modeling Language Usage and Listener Engagement in Podcasts

TL;DR

This study analyzes how linguistic features like vocabulary, emotion, and syntax in podcasts relate to listener engagement, using data-driven models to identify highly predictive stylistic factors.

Contribution

It introduces a comprehensive analysis linking linguistic style to engagement, validating some popular beliefs and offering new insights.

Findings

Certain linguistic features strongly predict engagement

Vocabulary diversity and emotional tone are key factors

Models achieve high accuracy in predicting engagement levels

Abstract

While there is an abundance of popular writing targeted to podcast creators on how to speak in ways that engage their listeners, there has been little data-driven analysis of podcasts that relates linguistic style with listener engagement. In this paper, we investigate how various factors -- vocabulary diversity, distinctiveness, emotion, and syntax, among others -- correlate with engagement, based on analysis of the creators' written descriptions and transcripts of the audio. We build models with different textual representations, and show that the identified features are highly predictive of engagement. Our analysis tests popular wisdom about stylistic elements in high-engagement podcasts, corroborating some aspects, and adding new perspectives on others.