Crypto markets are much more susceptible to the hype and mood of investors than e.g. stock markets. Latter is a different market as the companies value is defined by discounted cash flow valuation and is largely dependent on some observable – financial statements. Most of the time spent by financial analysis is thus on analysing financial statements and predicting revenue, net profit, cashflow, e.g. free cash flow.
In case of cryptocurrencies there is no comparable thing. This is why the value of given coin is much more dependent on the opinion of others, investors, about the coin.
This has led to an enlarged importance of opinions and sentiments about coins in terms of given altcoin or bitcoin valuation.
Bitcoin sentiment analysis can thus be an important in assessing or predicting the bitcoin price developments.
Bitcoin sentiment analysis is done by regularly collecting tweets and other social media posts about bitcoin and then determining the sentiment (positive or negative) for each social media post. This is usually done by using data science and machine learning techniques, first training machine learning model, using e.g. sklearn that is able to predict the sentiment (positive or negative, 1 or 0) for given text. And then deploying this on the stream of tweets and other social media posts.
The latter needs to be managed with some kind of data pipeline, e.g. employing spark or other libraries for this purpose.
Sentiment analysis is just one of many text classification models. Others include product categorization, news classification, product tagging and others.
Product categorization is e.g. especially important for the eCommerce ecosystem where the online stores often want to determine categories of product that they sell. They can thus allow their customers an easier search for their products.
Product tagging on the other hand is a more modern variant of the product categorization, where online stores do not assign one category to given product but rather one or more tags. This allows the user of online stores an even more refined search for their products.