Pattern VS spaCy

There’s some old work [1] that conceptualized sentiment as an interplay between subjectivity and sentiment. The more subjective a statement, the more “range” sentiment gets. I think this is what you are getting at.

I don’t think it ever gained traction, probably because people aren’t interested in creating an actual theory of sentiment that matches the real world.

[1]: https://github.com/clips/pattern/wiki/pattern-en#sentiment

if you're curious about the nitty gritty, the parsing module's documentation is well written and doesn't require a comp sci or linguistics degree to get the gist of what's happening.

Spacy. If you have time, explore nltk (the NLTK book is actually a really good place to start). I'm kind of fond of the https://github.com/clips/pattern -- it doesn't get the appreciation it deserves

Is this just using LLM to be cool? How does pure LLM with simple "In the scale between 0-10"" stack up against traditional, battle-tested sentiment analysis tools?

Gemini suggests NLTK and spaCy

https://www.nltk.org/

https://spacy.io/

Hi Community, In this article, I will demonstrate below steps to create your own chatbot by using spaCy (spaCy is an open-source software library for advanced natural language processing, written in the programming languages Python and Cython):

SpaCy: An open-source library providing tools for advanced NLP tasks like tokenization, entity recognition, and part-of-speech tagging.

spaCy https://spacy.io/

In this article, I'm going to walk through a sentiment analysis project from start to finish, using open-source Amazon product reviews. However, using the same approach, you can easily implement mass sentiment analysis on your own products. We'll explore an approach to sentiment analysis with one of the most popular Python NLP packages: spaCy.

Spacy [0] is a state-of-art / easy-to-use NLP library from the pre-LLM era. This post is the Spacy founder's thoughts on how to integrate LLMs with the kind of problems that "traditional" NLP is used for right now. It's an advertisement for Prodigy [1], their paid tool for using LLMs to assist data labeling. That said, I think I largely agree with the premise, and it's worth reading the entire post.

The steps described in "LLM pragmatism" are basically what I see my data science friends doing — it's hard to justify the cost (money and latency) in using LLMs directly for all tasks, and even if you want to you'll need a baseline model to compare against, so why not use LLMs for dataset creation or augmentation in order to train a classic supervised model?

[0] https://spacy.io/

[1] https://prodi.gy/