> I expect two of the listed to have very positive sentiment, and one generally negative in 2025.
You are quite correct! Crafting Interpreters actually has the highest average sentiment score across all books with more than 10 comments.
This is the average sentiment score of all three( range being -10 to 10) :
> Would love to learn more about how this is built. I remember a similar project from 4 years ago[0] that used a classic BERT model for NER on HN comments
Yes, I saw that project pretty impressive! Hand-labeling 4000 books is definitely not an easy task, mad-respect to tracyhenry for the passion and hardwork that was required back then.
For my project, I just used the Gemini 2.5 Flash API (since I had free credits) with the following prompt:
"""You are an expert literary assistant parsing Hacker News comments.
Rules:
1. Only extract CLEARLY identifiable books.
2. Ignore generic mentions.
3. Return JSON ARRAY only.
4. If no books found, return [].
5. A score from -10 to 10 where 10 is highly recommended, -10 is very poorly recommended and 0 is neutral.
6. If the author's name is in the comment, include it; otherwise, omit the key.
JSON format:
[
{{
"title": "book title",
"sentiment": "score",
"author" : "Name of author if mentioned"
}}
]
Text:
{text}"""
It did the job quite well. It really shows how far AI has come in just 4 years.
My bad — probably should’ve added a disclaimer :)
For what it’s worth, I only added sponsored links to the top ~50 books out of ~10k total. Mostly just trying to cover the cost of a decent domain so I can keep the site running.
Specialist doctors are one of the highest paid professions in almost all countries. There are hardly any jobs more important than those of say a heart surgeon or a neurosurgeon.
reply