Pancakes with ICO on a python or how to measure people and projects ICO
Friends, good afternoon.
There is a clear understanding that most of the ICO projects are essentially an intangible asset. ICO project is not a Mercedes-Benz car - which rides regardless of what its who likes or dislikes. And the main influence on the ICO is the mood of the people - both the mood for the founder of the ICO, and the project itself.
It would be good to somehow measure people's attitude towards the founder of the ICO and /or the ICO project. Which was done. The report is below.
The result was a tool for collecting positive negative sentiment from the Internet, in particular from Twitter.
My environment is Windows 10 x6? I used the Python 3 language in the Spyder editor in Anaconda 5.1.? a wired connection to the network.
I'll get the mood from Twitter posts. First, I'll find out what the founder of the ICO is doing and how positively they respond to this with the example of a couple of famous personalities.
I will use the python library tweepy. To work with Twitter, you need to register as a developer, see twitter / . Get criteria for accessing Twitter. TextBlob . The library is a miracle as good.
Clever people say that she knows how:
to make a partial marking,
analyze the mood (this is useful for us below),
to make classification (naive bayes, decision tree),
translate and define the language using Google Translate,
do tokenization (break the text into words and sentences),
identify the frequency of words and phrases,
to do parsing,
do the inflection of words (pluralization and singularization) and lematization,
The library allows you to add new models or languages through extensions and has the integration of WordNet. In a word, NLP the Wunderwolf .
We have previously saved the search results in the results.xlsx file. Load it and go through it with the TextBlob library for the purposes of mood estimation:
from textblob import TextBlob
results = pd.read_excel ('results.xlsx')
polarity = 0
for i in range (? len (results.index)):
polarity + = TextBlob (results['text'].[i]) .sentiment.polarity
print (polarity /i)
Cool! A couple of lines of code and bang result.
Review of the results
It turns out that at the beginning of August 201? the "twins found on the request of" Le Minh Tam "show something that was negatively reflected in tweets with an average rating for all tweets
minus ???r3r3274. . If we look at the tweets themselves, we'll see, for example, "Crypto Mining CEO Said to Disappear With $ 35 Million In Funds Crypto Mining Firm Sky Mining's CEO Le Minh Tam has r ".
A friend of "Mike Novogratz" did something that was positively reflected in tweets with an average rating for all tweets
plus ???r3r3274. . You can interpret this in such a way that everything moves smoothly forward.
The plan of attack is
For the purposes of ICO assessment, it is worthwhile to monitor information on the founders of the ICO and on the ICO itself from several sources. For example:
https://forklog.com/ - news with reviews,
https://bitcointalk.org/ - forum, calendar and analytics, ratings,
Do this on a permanent basis, for example hourly.
The plan for monitoring one ICO:
We create a list of the names of the founders of the ICO and the ICO itself,
Create a list of resources for monitoring,
We make a robot that collects data for each row of 1 - for each resource of ? an example above,
We make a robot that evaluates each ? an example above,
We keep the results of 4 (and 3),
Repeat steps 3-5 hourly, in an automated manner, the results of the evaluation can be sent somewhere to send to save,
Automatically follow the jumps in the assessment in paragraph 6. If the jumps in the assessment occur in paragraph ? this is an occasion to conduct additional study of what is happening in an expert manner. And raise panic or vice versa.
Something like that.
P.S. Well, or buy this information, for example here thomsonreuters
It may be interesting
Situs QQ Online
Situs QQ Online