Twitter Sentiment Analysis of CryptoCoins

Andy Boyan, Ph.D.
Jul 28, 2017 · 2 min read

I’ve been learning data analysis tools for a variety of new research projects. My main platform as of now is R. In order to learn R I decided to try to run sentiment analysis on groups of tweets.

I chose cryptocurrencies & digital assets because they are fun and interesting, and they should vary every day (or minute these days).

These analyses are from the most recent 500 tweets (at time of analysis) mentioning four major digital assets: Bitcoin, Ethereum, Litecoin, and Tezos. The sentiment analysis mines the tweets for trigger words that indicate general positive and negative sentiment.

Here are distributions of the scores for each:

Here are the overall averages for each digital asset:

We can also learn about the extreme sentiment values to see who has the most positive and negative mentions:

This analysis is, of course, very limited in sample (size and method). I just grabbed the @ mentions for four digital assets, not anything about any of the major movers, core devs, founders, or exchanges.

Could be interesting though…

Andy Boyan, Ph.D.

Written by

i like loud music. dad, phd, msu, wazzu, dlt. product vp research & innovation @urban_ft. Blockchain, crypto, & technosocial game theory on the side.

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade