LEARN MORE...

Text Mining Edd

Content type

User Generated

Subject

Statistics

School

Northeastern University

Type

Homework

Uploaded By

znlaneqgbby059

Pages

Showing Page:

1/9

Running head: TEXT MINING 1

Text Mining: Trump Tweets

Student Name:

Course Name:

Professor Name:

Date of Submission:

Showing Page:

2/9

TEXT MINING 2

Introduction

The evolution of data sharing and communication platforms such as Twitter, Facebook,

Instagram, and emails has resulted in the massive production of data. Generated data can be analyzed

and used to improve the value of a business. For example, Amazon can assess data from different e-

commerce users across the globe with the aim of building a proper framework for extracting and

analyzing useful information. AS such, the reliance on data analysis to improve business value has

supported the importance of text mining. This approach entails deriving meaningful information from

a natural text language. R programming offers interesting insights into the organization and analysis

of data. The text mining (TM) package in R is an essential component of text analysis (Feinerer,

2013). This paper presents the workflow involved text mining of Trump tweets in Rstudio.

Steps involved in the R Session and Explanation

Installing Packages

The first step involved in this framework is the installation of packages. The packages required

and installed for this session include; “SnowballCC", "RColorBrewer", "ggplot2", "wordcloud",

"biclust", "cluster", "igraph", and “fpc”. With the acquisition of these new packages, the power of the

R program is improved from basic functionalities. Without this step, the process of text analysis would

be impossible. As such, installing all the recommended R packages fall as part of the first line of text

analysis in R.

Loading Texts and Corpus Manipulation

The second step in text mining is the importing data. In this session, 11 documents saved in txt

format were downloaded and saved in the “texts” folder. The data can be imported using the import

feature in Rstudio. Besides, the data can be imported by executing code in the script file. This step

plays an essential in the text mining process. Ideally, the downloaded texts are made accessible in the

Rstudio for analysis. Without data importation, text mining cannot be performed. The code presented

in loading the text is presented below;

cname <- file.path("~", "Documents", "texts")

Showing Page:

3/9

End of Preview - Want to read all 9 pages?

Access Now

Unformatted Attachment Preview

Running head: TEXT MINING 1 Text Mining: Trump Tweets Student Name: Course Name: Professor Name: Date of Submission: TEXT MINING 2 Introduction The evolution of data sharing and communication platforms such as Twitter, Facebook, Instagram, and emails has resulted in the massive production of data. Generated data can be analyzed and used to improve the value of a business. For example, Amazon can assess data from different ecommerce users across the globe with the aim of building a proper framework for extracting and analyzing useful information. AS such, the reliance on data analysis to improve business value has supported the importance of text mining. This approach entails deriving meaningful information from a natural text language. R programming offers interesting insights into the organization and analysis of data. The text mining (TM) package in R is an essential component of text analysis (Feinerer, 2013). This paper presents the workflow involved text mining of Trump tweets in Rstudio. Steps involved in the R Session and Explanation Installing Packages The first step involved in this framework is the installation of packages. The packages required and installed for this session include; “SnowballCC", "RColorBrewer", "ggplot2", "wordcloud", "biclust", "cluster", "igraph", and “fpc”. With the acquisition of these new packages, the power of the R program is improved from basic functionalities. Without this step, the process of text analysis would be impossibl ...
Purchase document to see full attachment

Tags: data sharing communication platforms value of a business massive production of data analyzing useful information