EA Forum: Data analysis and deep learningpost by anishazaveri · 2020-05-12T17:39:41.884Z · EA · GW · 3 comments
1. Scraping 2. Exploratory Data Analysis Number of yearly posts Posts with the most comments Posts with the most karma Authors with the most posts Authors with the highest mean karma 3. Word Clouds 4. GPT2 None 3 comments
(Cross-posted from my blog)
Here's a fun project I undertook this month:
- Scrape all posts from the Effective Altruism (EA) Forum
- Explore overall trends in the data i.e. posts with the greatest number of comments, authors with the greatest number of posts etc.
- Build a wordcloud to visualize the most used words
- Fine-tune GPT2 on the EA Forum text corpus and generate text. Here's a preview of the text GPT2 produced:
GITC's Vaccination Prevention Research Project This is the first post of a three part series on the development of effective vaccines. This series will start with a list of possible vaccines that can be developed by the GPI team
Code and data for this project are available at this GitHib repo
- Manually loaded yearly links from
/allPosts(this required manually clicking each year followed by "Load More")
- Used a link extractor in Chrome to extract links from the page into a .csv file
- Used Scrapy to scrape the following fields from each link: 'date', 'author', 'title', 'number of comments', 'number of karma', and 'content'. I extracted data for posts published between 01-01-2013 and 05-04-2020. Posts with low karma (below -10) were ignored.
I cleaned the data and restricted subsequent analyses on posts published between 01-01-2013 to 04-15-2020, since recent posts were unlikely to have accumulated comments.
2. Exploratory Data Analysis
2.1 Number of yearly posts
2.2 Posts with the most comments
2.3 Posts with the most karma
2.4 Authors with the most posts
|Aaron Gertler [EA · GW]||87|
|Milan_Griffes [EA · GW]||83|
|Peter_Hurford [EA · GW]||74|
|RyanCarey [EA · GW]||66|
|Tom_Ash [EA · GW]||58|
2.5 Authors with the highest mean karma
Authors with <2 posts were excluded
|Buck [EA · GW]||92.2|
|Jonas Vollmer [EA · GW]||77.0|
|Luisa_Rodriguez [EA · GW]||74.7|
|saulius [EA · GW]||73.5|
|sbehmer [EA · GW]||73.0|
3. Word Clouds
My next goal was to make a word cloud representing the most commonly used words in the EA Forum. I preprocessed the post content as follows:
- Tokenized words
- Expanded word contractions e.g. 'don't' -> 'do not'
- Converted all words to lowercase
- Removed tokens that were only punctuation
- Filtered out stop words using nltk
- Removed any tokens containing numbers
- Removed any tokens containing 'http' or 'www'
The resulting word cloud was built using the Python word_cloud package on ~2.6 million tokens:
The most common words appeared to be 'one' and 'work'. I thought it would be instructive to see if these were over-represented in the EA Forum specifically, or are generally over-represented in other blogs/forums. To generate a control, I scraped all posts from Slate Star Codex (SSC) and performed identical text preprocessing to generate ~1.4 million tokens.
Using R's wordcloud package I built a "comparative" word cloud showing words over-represented in the EA Forum versus SSC and vice-versa.
What about words that were common between the EA Forum and SSC?
Finally, I used the text corpus from the EA Forum to fine-tune GPT2. GPT2 is a text-generating language model trained on 8 million web pages on the internet. You can play around with it on Talk to Transformer where the model completes the sentence given a prompt.
For fine-tuning I used this very convenient template Colab notebook made with gpt2-simple. I fine-tuned both the "small" (124 M parameters) and "medium" (355 M parameters) GPT2 models and tried a few temperature settings for text generation.
GPT2 can work with or without a prompt, and typically produces "good" text in 1/25 tries. I've cherry picked some outputs I obtained from the fine-tuned models:
Without a prompt:
What is Rationality in AI? Background Rationality is an ideology of AI, a belief system based on the belief that humans are naturally sentient. It argues that all human actions are responsible for the wellbeing of all sentient beings. This view is based on a large body of evidence. It is not a new, classicist theory of AI. Instead it is a mixture of old and new philosophy.
TL;DR's for the EA Forum/Welcome: ”Effective altruists are trying to figure out how to build a more effective AI, using paperclips, but we're not really sure how it's possible to do so.
GITC's Vaccination Prevention Research Project This is the first post of a three part series on the development of effective vaccines. This series will start with a list of possible vaccines that can be developed by the GPI team, ending with a brief overview of the science behind vaccine development. We will then address a variety of questions in the areas of biosecurity, biosecurity technologies and improved vaccine safety.This is a work in progress and we hope to get back to you soon.
With a prompt - 'Introduction to effective altruism':
Introduction to effective altruism [ edit ] The most basic assumption about effective altruism is that we must act rationally. It follows from this that you should maximize the benefit of the action you’re taking. The absolute value of a given intervention is the number of lives saved or improved. If the total benefit of the intervention is too small, you should not take it.
Introduction to effective altruism as a means to furthering one's life, many people I have spoken with who are currently living on less than $10,000 per year have completed some EA-related training. The basic idea of effective altruism is that one should donate your money to the most effective charities. In practice, many people who are involved with EA don't do this, and they will only use other methods to do it.
Comments sorted by top scores.