Analyzing User Engagement with TikTok's Short Format Video Recommendations using Data Donations

Savvas Zannettou; Olivia Nemes-Nemeth; Oshrat Ayalon; Angelica Goetzen; Krishna P. Gummadi; Elissa M. Redmiles; Franziska Roesner

doi:10.1145/3613904.3642433

Analyzing User Engagement with TikTok's Short Format Video Recommendations using Data Donations

Savvas Zannettou, Olivia Nemes-Nemeth, Oshrat Ayalon, Angelica Goetzen, Krishna P. Gummadi, Elissa M. Redmiles, Franziska Roesner

Organisation & Governance

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

107 Downloads (Pure)

Abstract

Short-format videos have exploded on platforms like TikTok, Instagram, and YouTube. Despite this, the research community lacks large-scale empirical studies into how people engage with short-format videos and the role of recommendation systems that offer endless streams of such content. In this work, we analyze user engagement on TikTok using data we collect via a data donation system that allows TikTok users to donate their data. We recruited 347 TikTok users and collected 9.2M TikTok video recommendations they received. By analyzing user engagement, we find that the average daily usage time increases over the users’ lifetime while the user attention remains stable at around 45%. We also find that users like more videos uploaded by people they follow than those recommended by people they do not follow. Our study offers valuable insights into how users engage with short-format videos on TikTok and lessons learned from designing a data donation system.

Original language	English
Title of host publication	CHI '24: Proceedings of the CHI Conference on Human Factors in Computing Systems
Editors	Florian Floyd Mueller, Penny Kyburz, Julie R. Williamson, Corina Sas, Max L. Wilson, Phoebe Toups Dugas, Irina Shklovski
Publisher	Association for Computing Machinery (ACM)
Number of pages	16
ISBN (Electronic)	979-8-4007-0330-0
DOIs	https://doi.org/10.1145/3613904.3642433
Publication status	Published - 2024
Event	2024 CHI Conference on Human Factors in Computing Sytems, CHI 2024 - Hybrid, Honolulu, United States Duration: 11 May 2024 → 16 May 2024

Conference

Conference	2024 CHI Conference on Human Factors in Computing Sytems, CHI 2024
Country/Territory	United States
City	Hybrid, Honolulu
Period	11/05/24 → 16/05/24

Keywords

Data Donation
Recommendation Algorithm
TikTok
User Engagement

Access to Document

10.1145/3613904.3642433

3613904.3642433Final published version, 839 KBLicence: CC BY

Cite this

Zannettou, S., Nemes-Nemeth, O., Ayalon, O., Goetzen, A., Gummadi, K. P., Redmiles, E. M., & Roesner, F. (2024). Analyzing User Engagement with TikTok's Short Format Video Recommendations using Data Donations. In F. F. Mueller, P. Kyburz, J. R. Williamson, C. Sas, M. L. Wilson, P. Toups Dugas, & I. Shklovski (Eds.), CHI '24: Proceedings of the CHI Conference on Human Factors in Computing Systems Article 731 Association for Computing Machinery (ACM). https://doi.org/10.1145/3613904.3642433

Zannettou, Savvas ; Nemes-Nemeth, Olivia ; Ayalon, Oshrat et al. / Analyzing User Engagement with TikTok's Short Format Video Recommendations using Data Donations. CHI '24: Proceedings of the CHI Conference on Human Factors in Computing Systems. editor / Florian Floyd Mueller ; Penny Kyburz ; Julie R. Williamson ; Corina Sas ; Max L. Wilson ; Phoebe Toups Dugas ; Irina Shklovski. Association for Computing Machinery (ACM), 2024.

@inproceedings{56e979efe24945158a9076342e8ce7e5,

title = "Analyzing User Engagement with TikTok's Short Format Video Recommendations using Data Donations",

abstract = "Short-format videos have exploded on platforms like TikTok, Instagram, and YouTube. Despite this, the research community lacks large-scale empirical studies into how people engage with short-format videos and the role of recommendation systems that offer endless streams of such content. In this work, we analyze user engagement on TikTok using data we collect via a data donation system that allows TikTok users to donate their data. We recruited 347 TikTok users and collected 9.2M TikTok video recommendations they received. By analyzing user engagement, we find that the average daily usage time increases over the users{\textquoteright} lifetime while the user attention remains stable at around 45%. We also find that users like more videos uploaded by people they follow than those recommended by people they do not follow. Our study offers valuable insights into how users engage with short-format videos on TikTok and lessons learned from designing a data donation system.",

keywords = "Data Donation, Recommendation Algorithm, TikTok, User Engagement",

author = "Savvas Zannettou and Olivia Nemes-Nemeth and Oshrat Ayalon and Angelica Goetzen and Gummadi, {Krishna P.} and Redmiles, {Elissa M.} and Franziska Roesner",

year = "2024",

doi = "10.1145/3613904.3642433",

language = "English",

editor = "Mueller, {Florian Floyd} and Penny Kyburz and Williamson, {Julie R.} and Corina Sas and Wilson, {Max L.} and {Toups Dugas}, Phoebe and Irina Shklovski",

booktitle = "CHI '24: Proceedings of the CHI Conference on Human Factors in Computing Systems",

publisher = "Association for Computing Machinery (ACM)",

address = "United States",

note = "2024 CHI Conference on Human Factors in Computing Sytems, CHI 2024 ; Conference date: 11-05-2024 Through 16-05-2024",

}

Zannettou, S, Nemes-Nemeth, O, Ayalon, O, Goetzen, A, Gummadi, KP, Redmiles, EM & Roesner, F 2024, Analyzing User Engagement with TikTok's Short Format Video Recommendations using Data Donations. in FF Mueller, P Kyburz, JR Williamson, C Sas, ML Wilson, P Toups Dugas & I Shklovski (eds), CHI '24: Proceedings of the CHI Conference on Human Factors in Computing Systems., 731, Association for Computing Machinery (ACM), 2024 CHI Conference on Human Factors in Computing Sytems, CHI 2024, Hybrid, Honolulu, United States, 11/05/24. https://doi.org/10.1145/3613904.3642433

Analyzing User Engagement with TikTok's Short Format Video Recommendations using Data Donations. / Zannettou, Savvas; Nemes-Nemeth, Olivia; Ayalon, Oshrat et al.
CHI '24: Proceedings of the CHI Conference on Human Factors in Computing Systems. ed. / Florian Floyd Mueller; Penny Kyburz; Julie R. Williamson; Corina Sas; Max L. Wilson; Phoebe Toups Dugas; Irina Shklovski. Association for Computing Machinery (ACM), 2024. 731.

Research output: Chapter in Book/Conference proceedings/Edited volume › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Analyzing User Engagement with TikTok's Short Format Video Recommendations using Data Donations

AU - Zannettou, Savvas

AU - Nemes-Nemeth, Olivia

AU - Ayalon, Oshrat

AU - Goetzen, Angelica

AU - Gummadi, Krishna P.

AU - Redmiles, Elissa M.

AU - Roesner, Franziska

PY - 2024

Y1 - 2024

N2 - Short-format videos have exploded on platforms like TikTok, Instagram, and YouTube. Despite this, the research community lacks large-scale empirical studies into how people engage with short-format videos and the role of recommendation systems that offer endless streams of such content. In this work, we analyze user engagement on TikTok using data we collect via a data donation system that allows TikTok users to donate their data. We recruited 347 TikTok users and collected 9.2M TikTok video recommendations they received. By analyzing user engagement, we find that the average daily usage time increases over the users’ lifetime while the user attention remains stable at around 45%. We also find that users like more videos uploaded by people they follow than those recommended by people they do not follow. Our study offers valuable insights into how users engage with short-format videos on TikTok and lessons learned from designing a data donation system.

AB - Short-format videos have exploded on platforms like TikTok, Instagram, and YouTube. Despite this, the research community lacks large-scale empirical studies into how people engage with short-format videos and the role of recommendation systems that offer endless streams of such content. In this work, we analyze user engagement on TikTok using data we collect via a data donation system that allows TikTok users to donate their data. We recruited 347 TikTok users and collected 9.2M TikTok video recommendations they received. By analyzing user engagement, we find that the average daily usage time increases over the users’ lifetime while the user attention remains stable at around 45%. We also find that users like more videos uploaded by people they follow than those recommended by people they do not follow. Our study offers valuable insights into how users engage with short-format videos on TikTok and lessons learned from designing a data donation system.

KW - Data Donation

KW - Recommendation Algorithm

KW - TikTok

KW - User Engagement

UR - http://www.scopus.com/inward/record.url?scp=85194882371&partnerID=8YFLogxK

U2 - 10.1145/3613904.3642433

DO - 10.1145/3613904.3642433

M3 - Conference contribution

AN - SCOPUS:85194882371

BT - CHI '24: Proceedings of the CHI Conference on Human Factors in Computing Systems

A2 - Mueller, Florian Floyd

A2 - Kyburz, Penny

A2 - Williamson, Julie R.

A2 - Sas, Corina

A2 - Wilson, Max L.

A2 - Toups Dugas, Phoebe

A2 - Shklovski, Irina

PB - Association for Computing Machinery (ACM)

T2 - 2024 CHI Conference on Human Factors in Computing Sytems, CHI 2024

Y2 - 11 May 2024 through 16 May 2024

ER -

Zannettou S, Nemes-Nemeth O, Ayalon O, Goetzen A, Gummadi KP, Redmiles EM et al. Analyzing User Engagement with TikTok's Short Format Video Recommendations using Data Donations. In Mueller FF, Kyburz P, Williamson JR, Sas C, Wilson ML, Toups Dugas P, Shklovski I, editors, CHI '24: Proceedings of the CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery (ACM). 2024. 731 doi: 10.1145/3613904.3642433

Analyzing User Engagement with TikTok's Short Format Video Recommendations using Data Donations

Abstract

Conference

Keywords

Access to Document

Other files and links

Fingerprint

Cite this