How to enable Multi-Language Sentiment Analysis with R

Have you seen how easy it is to integrate sentiment analysis in your Tableau dashboard – if your text is in English?

Until now the sentiment package for R only worked with English text. Today, I released version 1.0 of the sentiment package on GitHub that features multi-language support. In order to perform sentiment analysis with German text, just add the parameter language="german" as shown in this example:

Demo showing Multi-Language Sentiment Analysis with English and German text
Demo showing Multi-Language Sentiment Analysis with English and German text

The new code allows you to add any language. So far, I started to prepare German sentiment files. French and Spanish sentiment files are on my to-do list.

How to implement Sentiment Analysis in Tableau using R

Interactive sentiment analysis with Tableau using R
Interactive sentiment analysis with Tableau using R

In my previous post I highlighted Tableau’s text mining capabilities, resulting in fancy visuals such as word clouds:

Today I’d like to follow up on this and show how to implement sentiment analysis in Tableau using Tableau’s R integration. Some of the many uses of social media analytics is sentiment analysis where we evaluate whether posts on a specific issue are positive, neutral, or negative (polarity), and which emotion in predominant.

What do customers like or dislike about your products? How do people perceive your brand compared to last year?

In order to answer such questions in Tableau, we need to install an R package that is capable of performing the sentiment analysis. In the following example we use an extended version of the sentiment package, which was initiated by Timothy P. Jurka.

The sentiment package requires the tm and Rstem packages, so make sure that they are installed properly. Execute these commands in your R console to install sentiment from GitHub (see alternative way to install at the end of this blog post):


install.packages("devtools")
library(devtools)
install_github("aloth/sentiment/sentiment")

The sentiment package offers two functions, which can be easily called from calculated fields in Tableau:

Screenshot 2016-01-31 15.25.24 crop

The function get_polarity returns „positive“, „neutral“, or „negative“:


SCRIPT_STR('
library(sentiment)
get_polarity(.arg1, algorithm = "bayes")
'
, ATTR([Tweet Text]))

The function get_emotion returns „anger“, „disgust“, „fear“, „joy“, „sadness“, „surprise“, or „NA“:


SCRIPT_STR('
library(sentiment)
get_emotion(.arg1, algorithm = "bayes")
'
, ATTR([Tweet Text]))

The sentiment package follows a lexicon based approach and comes with two files emotions_english.csv.gz (source and structure) and subjectivity_english.csv.gz (source and structure). Both files contain word lists in English and are stored in the R package library under /sentiment/data directory.

If text is incorrectly classified, you could easily fix this issue by extending these two files. If your aim is to analyze text other than English, you need to create word lists for the target language. Kindly share them in the comments!

Feel free to download the Packaged Workbook (twbx) here.

Update 11 Aug 2016: If you are having trouble with install_github, try to install directly form this website:


install.packages("Rcpp")
install.packages("http://alexloth.com/utils/sentiment/current/sentiment.zip",repos=NULL)

How to perform Text Mining at the Speed of Thought directly in Tableau

Interactive real-time text mining with Tableau Desktop 9.2
Interactive real-time text mining with Tableau Desktop

Tableau is an incredibly versatile tool, commonly known for its ability to create stunning visualizations. But did you know that with Tableau, you can also perform real-time, interactive text mining? Let’s delve into how we can harness this function to gain rapid insights from our textual data.

Previously, during text mining tasks, you might have found yourself reaching for a scripting language like R, Python, or Ruby, only to feed the results back into Tableau for visualization. This approach has Tableau serving merely as a communications tool to represent insights.

However, wouldn’t it be more convenient and efficient to perform text mining and further analysis directly in Tableau?

While Tableau has some relatively basic text processing functions that can be used for calculated fields, these often fall short when it comes to performing tasks like sentiment analysis, where text needs to be split into tokens. Even Tableau’s beloved R integration does not lend a hand in these scenarios.

The Power of Postgres for Text Mining in Tableau

Faced with these challenges, I decided to harness the power of Postgres‘ built-in string functions for text mining tasks. These functions perform much faster than most scripting languages. For example, I used the function regexp_split_to_table for word count, which takes a piece of text (like a blog post), splits it by a pattern, and returns the tokens as rows:

select
guid
, regexp_split_to_table(lower(post_content), '\s+') as word
, count(1) as word_count
from
alexblog_posts
group by
guid, word

Incorporating Custom SQL into Tableau Visualization

I joined this code snippet as a Custom SQL Query to my Tableau data source, which is connected to the database that is powering my blog:

Join with Custom SQL Query in Tableau applying the Postgres function regexp_split_to_table
Join with Custom SQL Query in Tableau applying the Postgres function regexp_split_to_table

And here we go, I was able to create an interactive word count visualization right in Tableau:

This example can be easily enhanced with data from Google Analytics, or adapted to analyze user comments, survey results, or social media feeds. The possibilities for Custom SQL in Tableau are vast and versatile. Do you have some more fancy ideas for real-time text mining with Tableau? Leave me a comment!

Update (TC Pro Tip): Identifying Twitter Hashtags in Tableau

A simple calculated field in Tableau can help identify words within tweets as hashtags or user references, eliminating the need for another regular expression via a Custom SQL Query:

CASE LEFT([Word], 1)
WHEN "#" THEN "Hash Tag"
WHEN "@" THEN "User Reference"
ELSE "Regular Content"
END

Looking for an example? Feel free to check out the Tweets featuring #tableau Dashboard on Tableau Public and download the Packaged Workbook (twbx):

Tableau dashboard that shows tweets featuring the hashtag #tableau (presented at Tableau Conference)
Tableau dashboard that shows tweets featuring the hashtag #tableau (presented at Tableau Conference)

Any more feedback, ideas, or questions? I hope this post provides you with valuable insights into how to master text mining in Tableau, and I look forward to hearing about your experiences and creative applications. You can find more tutorials like this in my new book Visual Analytics with Tableau (Amazon).

Transparency: This blog contains affiliate links. If you click on them, you will be redirected to the merchant. If you decide to make a purchase, we will receive a small commission. The price does not change for you. Affiliate links have no influence on our writing.