Topic: New research: Using Time-Series and Sentiment Analysis to Detect the Determinant (Read 840 times)

Thanks for posting this, it is really interesting.  Now let me try and wrap my head around it.  OK done.  I tend to agree with odolvlobo even if the results seem conclusive.  I would like to see this tracked long term to find out if the variables do indeed lag/lead or correlate directly.

The time-series measured sentiment assuming the servers were online
A great example of when one of the main sources of information was down would make a good note but they focused on twitter so the sources focus on one area still an interesting series of relationships were illustrated in my opinion.

For the set of cointegrated variables, we estimated a VECM to identify the underlying long-run relationships. The analysis revealed that the stock of Bitcoins has a positive long-run impact on their price.

This is also a counterintuitive result, since the number of Bitcoins in circulation measures the total supply of money which would be expected to have a negative effect on Bitcoin prices.

The Standard and Poor‟s 500 index was found to have a negative impact on Bitcoin prices in the long run, implying that stocks and Bitcoins are treated as substitutes by investors.

More specifically, a decrease in the Standard and Poor‟s 500 index induces investors to sell their stocks and substitute them for Bitcoins

So like any asset it's impacted by awareness popularity and exchange rates.

Correlation does not imply causation. Q.E.D.

I'm sure google trends would also work.  I would also assume that Twitter and other markers are lagging indicators, i.e. they pick up just as or immediately after the price rises.

During the last massive rise, the news were all over bitcoin and searches skyrocketed.  I don't think the internet chat increased the price, rather the price change caused lots of internet chat.

Using Time-Series and Sentiment Analysis to Detect the Determinants of Bitcoin Prices

See http://papers.ssrn.com/sol3/Papers.cfm?abstract_id=2607167

Abstract:     
This paper uses time-series analysis to study the relationship between Bitcoin prices and fundamental economic variables, technological factors and measurements of collective mood derived from Twitter feeds. Sentiment analysis has been performed on a daily basis through the utilization of a state-of-the-art machine learning algorithm, namely Support Vector Machines (SVMs). A series of short-run regressions shows that the Twitter sentiment ratio is positively correlated with Bitcoin prices. The short-run analysis also reveals that the number of Wikipedia search queries (showing the degree of public interest in Bitcoins) and the hash rate (measuring the mining difficulty) have a positive effect on the price of Bitcoins. On the contrary, the value of Bitcoins is negatively affected by the exchange rate between the USD and the euro (which represents the general level of prices). A vector error-correction model is used to investigate the existence of long-term relationships between cointegrated variables. This kind of long-run analysis reveals that the Bitcoin price is positively associated with the number of Bitcoins in circulation (representing the total stock of money supply) and negatively associated with the Standard and Poor's 500 stock market index (which indicates the general state of the global economy).

Number of Pages in PDF File: 14

Keywords: Bitcoins, error correction, machine learning, sentiment analysis