T&S #2: A Rationale for Uncaught Spam in UGVC

Published: 2025 June 25
Disclaimer: The following is an educational analysis based on the author's interpretation of publicly available data using the frameworks, methodologies and/or approaches written about in this post. It constitutes the author's opinion and is not a definitive assertion of fact.

Why Write This Blogpost?

Previously, this blogpost focused on the spam on 3 platforms that best deliver delightful experiences in the UGVC space: YouTube, Instagram and TikTok. The blogpost reviewed an example of two comment threads which looked like-near duplicates. Following that review, one may begin to look through comment threads in other videos and begin to wonder, “Why are there 'so many'1 uncaught cases of spam?”. To address this question, this blogpost presents a rationale on why there may be uncaught spam.

Who Are The UGVC Ecosystem’s Participants?

For a UGVC ecosystem to operate, the ecosystem requires the presence of these 4 participants:

  1. Video platform providers
  2. Content producers
  3. Content consumers
  4. Advertisers

In addition, these other participants may become involved:

  1. Regulators
  2. Software/Hardware Service Providers
  3. Creative Process Service Providers

To date, spammers have participated in the ecosystem as “Content producers”, "Consumers” and/or “Advertisers”.

Why Is Not All Spam Caught?

Video platform providers work tirelessly and valiantly to execute highly effective computer-program-driven (e.g. classifiers) and/or people-driven approaches (e.g. investigations) to detect and enforce on spam activities. Unfortunately, less than 100% of spam activities are prevented and/or stopped. Some reasons for this reality are presented in the following table.

Rationale for Uncaught Spam2

Rationale Category Reason
Computer-program-driven Approach Reasons The current models are trained on irrelevant data.
The current models are run on insufficiently frequent schedules.
The current models have computational resource constraints.
The current models made tradeoffs in recall and precision.
The latest models have not yet been deployed.
People-driven Approach Reasons3 The team has insufficient confidence that something is spam.
The team has deprioritized mitigation for this type of spam.
The team’s tools may need enhanced and/or new capabilities.
The team has not yet executed its mitigation approach.
Spammer-driven Approach Reasons The spammer community and thus activities have grown.
The spammer has developed novel, adversarial approaches.
The spammer has identified grey areas in a platform's policies.

What comes next after this blogpost?

For the next blogpost, expect T&S #3: A Person-driven Evaluation Framework for UGVC Spam.

Disclosures
  1. I worked in the Trust & Safety for 7 years. In 0 of those years, I worked on the 3 UGVC platforms listed in this blogpost.
  2. I interview for open roles and positions, occasionally, with the companies written about in this blogpost and/or their parent companies.
  3. I own equity in some of the companies written about in this blogpost and/or their parent companies.

Footnotes
  1. "So many" is a subjective term. To some, one case of spam satisfies the threshold. To others, several cases of spam satisfies the threshold. To all others, even more cases of spam satisfy the threshold.
  2. This should not be considered comprehensive.
  3. There is at least one more reason in this category, however I must write it as a footnote due to the cynical nature of the reason. This reason is that the team has at least one person excessively focused on performance reviews or promotion candidacy. As a result, at least one person may be incentivized to find a “high impact opportunity” to work on and deliver those “high impact” results. To be clear, this behavior is exercised by a minority of folks. Unfortunately, the behavior exists.