| Issue |
ITM Web Conf.
Volume 88, 2026
The 2026 International Conference on Artificial Intelligence, Big Data and Computer Science (AIBDCS 2026)
|
|
|---|---|---|
| Article Number | 01007 | |
| Number of page(s) | 5 | |
| Section | Artificial Intelligence, Big Data and Computer Science | |
| DOI | https://doi.org/10.1051/itmconf/20268801007 | |
| Published online | 27 July 2026 | |
Influence Analysis of High-Follower Social Media Influencers
Faculty of Science and Technology, Beijing Normal-Hong Kong Baptist University, Zhuhai, China
* Corresponding author: This email address is being protected from spambots. You need JavaScript enabled to view it.
Abstract
As social media continues to reshape consumer behavior, gauging the true reach of digital influencers has emerged as a pressing concern for scholars and industry professionals alike. Drawing upon data harvested from TikTok and Instagram in September 2022, this investigation probes the often-assumed link between audience size and content resonance. The TikTok corpus encompasses 1,000 profiles, tracking metrics from follower tallies to interaction patterns—views, likes, comments, and shares. Complementing this, the Instagram sample comprises 200 accounts, each profiled through proprietary influence scores and two-month engagement trajectories. Statistical scrutiny via correlation and regression modeling yields a nuanced picture: follower numbers correlate only moderately with engagement indicators (r = 0.36-0.46), and surprisingly, account for a mere 12.5% of variation in like counts. The platform divide proves equally striking—TikTok creators command engagement rates roughly threefold those on Instagram (7.2% versus 2.3%). For brands navigating the influencer landscape, these results underscore a pivotal insight: raw follower statistics tell only part of the story; engagement caliber and platform dynamics warrant equal, if not greater, attention.
© The Authors, published by EDP Sciences, 2026
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.

