Master's Thesis

Artificial Intelligence trend analysis using speech-to-text data from healthcare podcasts


Philipp Dumbach (M.Sc.), Leo Schwinn (M.Sc.), Prof. Dr. B. Eskofier




Artificial intelligence (AI), Machine Learning (ML), Deep Learning (DL) – since the start of the
Fourth Industrial Revolution, these buzzwords have been trending and sometimes falsely used as
synonyms for each other [1, 2]. The technologies associated with AI are mainly responsible for
advances in many fields like image and speech recognition. Since AI technologies can be applied
to a wide range of fields including medical and education fields, many efforts have been actively
given to identify the current technology trends and analyze development directions of it. [3, 4, 5].
Podcasting has emerged as an important information technology tool for health professionals and
consumers around the world [6]. An initial literature research indicated, that there is a lack of
research using podcasts as a data set for trend analysis.
The goal of this thesis is to review the major research trend on the topics of AI, ML and DL using
trend analysis on health-care podcasts. A representative amount of trending health-care podcasts
will be screened and selected. All their podcasts will be downloaded and transcribed to text using
a Speech-to-Text API. The resulting text data will be used for quantitative trend analysis and to
research how the buzzwords around AI and its subsets have evolved over time.



[1] Kuehl N. et al.: Machine Learning in Artificial Intelligence: Towards a Common Understanding.
arXiv:2004.04686, 2020.
[2] Bini, S.: Artificial Intelligence, Machine Learning, Deep Learning, and Cognitive Computing:
What Do These Terms Mean and How Will They Impact Health Care? . The Journal
of Arthroplasty, vol. 33, 2358-2361, 2018.
[3] Chong, J. et al.: A Study on the Development Trend of Artificial Intelligence Using Text
Mining Technique: Focused on Open Source Software Projects on Github . Journal of
Intelligence and Information Systems, vol. 25 no. 1, 1-19, 2019.
[4] Fujii, H., Managi, S.: Trends and priority shifts in artificial intelligence technology invention:
A global patent analysis . Economic Analysis and Policy, vol. 58, 60-69, 2018.
[5] Holzinger, A. et al.: Current Advances, Trends and Challenges of Machine Learning and
Knowledge Extraction: From Machine Learning to Explainable AI . Machine Learning and
Knowledge Extraction, CD-MAKE 2018, 1-8, 2018.
[6] Johnson L., Grayden S.: Podcasts–an emerging form of digital publishing.. International
Journal of Computerized Dentistry 9(3), 205-218, 2006.
[7] Rohrbeck R.: Trend Scanning, Scouting and Foresight Techniques. Management of the
Fuzzy Front End of Innovation, 59-73, 2013.
[8] Duncker, C, Schuette, L.: Trendbasiertes Innovationsmanagement: Ein Modell fuer markenbasiertes
Produktmanagement. Springer-Verlag, 2017.
[9] Duncker, C, Schuette, L.: Ein erweitertes Modell fuer trendbasiertes Innovationsmanagement.
Springer Gabler, 33-42, 2018.