Creator Hearts: Investigating the Impact Positive Signals from YouTube Creators in Shaping Comment Section Behavior

TL;DR

This study investigates how YouTube creator hearts—a positive endorsement signal—influence comment-section behavior and video engagement. Using a quasi-experimental design with Mahalanobis matching and Bayesian regression, the authors quantify causal effects of hearts on individual comment outcomes and on total video comments, across channels of various sizes and with different heart-timing windows. Key findings show that hearts increase comment visibility and likes, and that hearts given within the first hour after publication substantially boost subsequent engagement (about 22% at 12 hours and up to 27% at 24 hours), with effects diminishing as the initial heart timing is delayed. The work highlights how creators can curate norms and incentivize participation through positive reinforcement, and discusses implications for interface design and cross-platform extension of such signals.

Abstract

Much of the research in online moderation focuses on punitive actions. However, emerging research has shown that positive reinforcement is effective at encouraging desirable behavior on online platforms. We extend this research by studying the "creator heart" feature on YouTube, quantifying their primary effects on comments that receive hearts and on videos where hearts have been given. We find that creator hearts increased the visibility of comments, and increased the amount of positive engagement they received from other users. We also find that the presence of a creator hearted comment soon after a video is published can incentivize viewers to comment, increasing the total engagement with the video over time. We discuss the potential for creators to use hearts to shape behavior in their communities by highlighting, rewarding, and incentivizing desirable behaviors from users. We discuss avenues for extending our study to understanding positive signals from moderators on other platforms.

Figures (8)

• Figure 1: YouTube comments that have received a "heart" from a creator are displayed with a distinctive badge (top).
• Figure 2: Flowchart depicting the data collection process and subsequent analysis, with statistics of the data collected at each stage.
• Figure 3: Distribution (across channels) of the average number of creator-hearted comments (of the top 100 comments) per video. We observed at least one heart from 55.5% (6,517) of the channels in our sample, and an average 6.75 hearts per video from these channels.
• Figure 4: Distributions of the number of hearts observed from each channel, averaged across their videos.
• Figure 5: Plot of comment counts from the initial and follow-up windows ($w_{\text{init}}=1$, $w_{\text{foll}}=12$) and posterior means for treatment (dashed line) and control (dotted line) videos. The control group (n=494) consists of videos where no comments were hearted by the creator within the first hour after the video was published ($I_{\heartsuit} = 0$), and the treatment group (n=179) consists of videos where at least one comment was given a heart within the first hour ($I_{\heartsuit} = 1$). The difference in posterior means illustrates a mean 22.1% increase (HDI 6.3%-38.7%) in the number of comments after 13 hours (1 hour initial window + 12 hour follow-up window) from the presence of a creator heart within the first hour.