Try TextBlob for Sentiment Analysis

November 19, 2013

Sad to say, we have heard rumblings about severe disappointment with Attensity-type and Lexalytics-type sentiment applications. If you want to kick some tires in this interesting search niche, look instead to the open source application TextBlob. OpenShift points out this resource in, “Day 9: TextBlog—Finding Sentiments in Text.” The article is one in an ambitious series by writer Shekhar Gulati, who challenged himself to master one technology a day for a month. Very admirable, sir!

Gulati begins with his experience with sentiment analysis:

“My interest in sentiment analysis is few years old when I wanted to write an application which will process a stream of tweets about a movie, and then output the overall sentiment about the movie. Having this information would help me decide if I wanted to watch a particular movie or not.

“I googled around, and found that Naive Bayes classifier can be used to solve this problem. The only programming language that I knew at the time was Java, so I wrote a custom implementation and used the application for some time. I was lazy to commit the code, so when my machine crashed, I lost the code and application. Now I commit all my code to github, and I have close to 200 public repositories 🙂

“In this blog, I will talk about a Python package called TextBlob which can help developers solve this problem. We will first cover some basics, and then we will develop a simple Flask application which will use the TextBlob API.”

The post does indeed cover the basics, including the installation of Python and virtualenv before we can get going with TextBlob. It then takes us through writing an example application and deploying to the cloud. As he notes above, Gulati has his code safe and sound at Github; the code for this example are posted here, and the js and css files can be found here.

Cynthia Murrell, November 19, 2013

Sponsored by ArnoldIT.com, developer of Augmentext

Comments

One Response to “Try TextBlob for Sentiment Analysis”

  1. Stanford researchers open source sentiment analysis project | Knowledge Strategies & Bioscience on December 25th, 2013 11:45 am

    […] Try TextBlob for Sentiment Analysis (arnoldit.com) […]

  • Archives

  • Recent Posts

  • Meta