Logistic Regression for Twitter Data Scraping

[gerry888]

HI there, 

I am trying to do a logistic regression for data i have scraped from a twitter advanced search, but it comes up with error everytime i run it, i believe this is due to the the fact that my all my value types come up as Char (character) and it needs to be Num (numbers) but my variables are 

 Variables in Creation Order# Variable Type Len Format Informat12345678

Field1	Char	87	$87.	$87.
TwitterHandle	Char	77	$77.	$77.
Username	Char	41	$41.	$41.
DateofTweet	Char	104	$104.	$104.
InResponseTo	Char	10	$10.	$10.
Tweet	Char	12	$12.	$12.
Comments	Char	1	$1.	$1.
Retweets	Char	1	$1.	$1.

how should i go about changing this or am i not using an appropriate statistical technique for this type of data 

[PGStats]

What is your logistic regression model for this data?

[gerry888]

What do you mean by that. 

I'll say it about the volume of tweets produced by the user, level of traction (replies, retweets and comments) and time produced. 

Also is logistic regression the current method of statistical technique to use for what I need?

[PGStats]

Logistic regression is a powerful statistical estimation technique that is not appropriate for your goal. Look it up.

You seem to want to calculate summary statistics such as totals and means. First, you will need to translate those character fields into dates and numbers . The function to do that with SAS is INPUT. Then you should formulate your needs in mathematical terms, as precicely as possible. We can help you from there, if needed.

[gerry888]

how would i go about doing that, could you give me a step by step instructions

[miriam93]

Logistic regression is definitely not what you need. It models the likelihood of an outcome of a dichotomous variable (yes/no) based on a bunch of predictor variables. So, for instance, the odds of a tweet being longer than 20 characters based on time of posting, language used etc.

As already pointed out by PGStats, you need to specifiy what it is that you want to do with your data. Then we might be able to help out.