Nicheloom

Market intelligence for builders — see what's gaining traction before it's crowded.

HN Sentiment API

I ranked tech CEOs by how much you hate them

Details

External ID
46345330
Source
HN
Company
—
Product
HN Sentiment API
Website domain
hnpulse.com
Launched
Dec. 21, 2025
Cohort
—
Upvotes
27
Upvotes percentile
0.708969465648855
Tags
—
Fetched at
Sept. 7, 2026, 9:25 p.m.
Updated at
Sept. 7, 2026, 9:25 p.m.

Description

I built an API that extracts entities from Hacker News comments and classifies sentiment towards them as positive, negative, or neutral. It also classifies overall comment sentiment and assigns each entity a label (person, location, date, technology, organization, other).505k+ comments, Oct 31 - Present.Here's the leaderboard:LOVED:- Steve Jobs: 44% positive, 7% negative- Linus Torvalds: 43% positive, 5% negative- Gabe Newell: 34% positive, 8% negativeMID:- Bill Gates: 22% positive, 8% negative- Tim Cook: 15% positive, 30% negative- Bezos: 12% positive, 18% negativeHATED:- Zuckerberg: 4% positive, 35% negative- Sam Altman: 8% positive, 38% negative- Musk: 5% positive, 45% negativeTry it yourself:# Who does HN talk about the most?curl "https://api.hnpulse.com/entities?label=person&sort=mentions"# What are people saying about remote work?curl "https://api.hnpulse.com/comments?entity=remote work&limit=3"# Is OpenAI's reputation getting worse?curl "https://api.hnpulse.com/trends?entity=openai&bucket=day"# What technology gets mentioned alongside SF?curl "https://api.hnpulse.com/entities?co-occur=SF&label=technolog..."Stack: Go, PostgreSQL, GPT-4o mini for entity extractionDocs: https://docs.hnpulse.com API: https://api.hnpulse.com

Enrichment

Theme
Hacker News clients, datasets, and tools
Vertical
Horizontal
Function
Analytics & BI
Audience
B2C
AI stance
AI feature
Project type
Hobby / open-source project
Normalized one-liner
sentiment analysis of tech ceos on hacker news
Manually corrected
False

Could you build this?

Yes The product extracts entities and sentiment from public comments via standard batch processing or off-the-shelf NER/sentiment models (or LLM API calls) and serves the results over a REST API.

Discussion

9 comments analyzed.

Concerns raised: Cost is high - $238.21 and 663M tokens for analysis, Binary sentiment analysis loses nuance between different types of criticism, Data collection and annotation effort required for personal datasets

Feature requests: AI nudging for better communication patterns in personal comments, More granular sentiment analysis beyond binary positive/negative, Easier personal data collection from Chrome bookmarks and social posts

Competitors

Other products that read as similar to this one — 81 launches clear the similarity bar, closest 8 shown.

Attention rank: #32 of 82 (itself plus its competitors, highest first — normalized so YC and Product Hunt are compared fairly).

Launched 52 days after the earliest competitor.

Other launches for this product

Same idea, different domain

Nobody's really built a analytics & bi tool for Legal yet.