{
  "id": 19342159,
  "title": "A Word List Tied the Model",
  "url": "https://urgent.news/2026/11/10/a-word-list-tied-the-model",
  "topic": "tech",
  "section": "Tech",
  "published": "2026-11-10T14:16:00.000Z",
  "source": {
    "name": "Dev.to",
    "slug": "dev-to",
    "url": "https://dev.to/kenwalger/a-word-list-tied-the-model-213o"
  },
  "original_language": "en",
  "account": "The story focuses on the author's efforts to measure the impact of comments on their posts. Initially, they found that metrics on their dashboard did not align with what mattered to them. After realizing the importance of reader engagement, they decided to measure it instead. The author designed a system using AI to filter comments based on their importance. The system classifies comments into categories like corrections, questions, and acknowledgments, and then decides whether to surface, queue, or collapse them. The author tested the system using a word list as a baseline and found that the AI model performed better in classifying consequential comments. The system was built as a local Python tool that reads posts and comments from the DEV API and stores them in a local SQLite database. The author labeled all 544 of their historical comments by hand, which took a significant amount of time but provided valuable insights into their comment engagement.",
  "summary": "I tried to find out which of my comments mattered. The answer was not the one I built for. A few weeks ago I pulled nine years of my own DEV data out of the API, mostly to chart which posts had moved my follower count. The numbers were not what I expected. The follow-up, Views Measure Views , was about what they taught me: the metrics on my dashboard were measuring almost nothing I cared about.…",
  "key_points": [
    "Author designed AI system to filter comments based on importance",
    "Word list used as baseline for AI model classification testing",
    "Local Python tool stored comments in SQLite database for analysis"
  ],
  "editors_take": null,
  "illustration": null,
  "coverage": {
    "outlets": 1,
    "also_reported_by": []
  },
  "ai_generated": true,
  "disclaimer": "Summaries, key points and the editor’s take are written by software from other outlets’ reporting and may contain errors — always check the linked original."
}