Modeling Language Usage and Listener Engagement in Podcasts

While there is an abundance of advice 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 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 pieces of advice and adding new perspectives on others.

• Publication year

  2021

• Venue

  Annual Meeting of the Association for Computational Linguistics

• Publication date

  2021-06-11

• Fields of study

  Linguistics, Computer Science

• Identifiers
  DOI 10.18653/v1/2021.acl-long.52arXiv 2106.06605
• External record

  Open on Semantic Scholar

• Source metadata

  Semantic Scholar

• No claims are published for this paper.

• No concepts are published for this paper.

• Detecting Extraneous Content in Podcasts

  2021influential reference
• Mutual Hyperlinking Among Misinformation Peddlers

  2021cited by this paper
• Current Challenges and Future Directions in Podcast Information Access

  2021cited by this paper
• Measuring Forecasting Skill from Text

  2020influential reference
• A review of metadata fields associated with podcast RSS feeds

  2020cited by this paper
• 100,000 Podcasts: A Spoken English Document Corpus

  2020influential reference
• The Engagement-Diversity Connection: Evidence from a Field Experiment on Spotify

  2020cited by this paper
• Racial disparities in automated speech recognition

  2020cited by this paper
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

  2019influential reference
• A Neural Citation Count Prediction Model based on Peer Review Text

  2019cited by this paper
• Auditing radicalization pathways on YouTube

  2019cited by this paper
• Analyzing and Predicting News Popularity in an Instant Messaging Service

  2019cited by this paper
• FairyTED: A Fair Rating Predictor for TED Talk Data

  2019cited by this paper
• Finding Your Voice: The Linguistic Development of Mental Health Counselors

  2019cited by this paper
• Analyzing Polarization in Social Media: Method and Application to Tweets on 21 Mass Shootings

  2019cited by this paper
• More Than Just Words: Modeling Non-Textual Characteristics of Podcasts

  2019influential reference
• Letting Emotions Flow: Success Prediction by Modeling the Flow of Emotions in Books

  2018cited by this paper
• Identifying the sentiment styles of YouTube’s vloggers

  2018cited by this paper
• Awe the Audience: How the Narrative Trajectories Affect Audience Perception in Public Speaking

  2018cited by this paper
• The spread of true and false news online

  2018cited by this paper
• How algorithmic popularity bias hinders or promotes quality

  2017cited by this paper
• Gender and Dialect Bias in YouTube’s Automatic Captions

  2017cited by this paper
• A Readability Analysis of Campaign Speeches from the 2016 US Presidential Campaign

  2016cited by this paper
• Automated Analysis and Prediction of Job Interview Performance

  2015cited by this paper
• The effect of wording on message propagation: Topic- and author-controlled natural experiments on Twitter

  2014cited by this paper
• Distributed Representations of Sentences and Documents

  2014cited by this paper
• Predicting and Characterising User Impact on Twitter

  2014cited by this paper
• Success with Style: Using Writing Style to Predict the Success of Novels

  2013cited by this paper
• CROWDSOURCING A WORD–EMOTION ASSOCIATION LEXICON

  2013cited by this paper
• You Had Me at Hello: How Phrasing Affects Memorability

  2012cited by this paper
• Textual Predictors of Bill Survival in Congressional Committees

  2012cited by this paper
• Predicting a Scientific Community’s Response to an Article

  2011cited by this paper
• Cross-domain Feature Selection for Language Identification

  2011cited by this paper
• Predicting podcast preference: An analysis framework and its application

  2010influential reference
• Software Framework for Topic Modelling with Large Corpora

  2010cited by this paper
• Latent Dirichlet Allocation

  2009cited by this paper
• Thumbs up? Sentiment Classification using Machine Learning Techniques

  2002cited by this paper
• A FORMULA FOR PREDICTING READABILITY

  1948cited by this paper
• A new readability yardstick.

  1948cited by this paper

• Narrative Techniques in Romanian Podcasts: A Qualitative Case Study Analysis

  2025cites this paper
• Podcasts as an emerging register of computer-mediated communication

  2025cites this paper
• Podcast: The Dilemmas of Popularity

  2025cites this paper
• Repetition as an Effective Means of Information Conveyance and Audience Attention Retention in Concise Texts of English-Language Podcast Announcements

  2025cites this paper
• Identifying Narrative Content in Podcast Transcripts

  2024cites this paper
• Comparing ASR Systems in the Context of Speech Disfluencies

  2024cites this paper
• It’s What You Say and How You Say It: Exploring Audio and Textual Features for Podcast Data

  2023cites this paper
• Fine Grained Spoken Document Summarization Through Text Segmentation

  2023influential citation
• MedNgage: A Dataset for Understanding Engagement in Patient-Nurse Conversations

  2023cites this paper
• Podify: A Podcast Streaming Platform with Automatic Logging of User Behaviour for Academic Research

  2023cites this paper
• Audio- and text-based Podcast Retrieval and Summarization Master’s Thesis

  2022cites this paper
• What Makes a Good Podcast Summary?

  2022cites this paper
• Prediction of Listener Perception of Argumentative Speech in a Crowdsourced Dataset Using (Psycho-)Linguistic and Fluency Features

  2021cites this paper
• TU Wien at TREC DL and Podcast 2021: Simple Compression for Dense Retrieval

  2021cites this paper