icon/x Created with Sketch.

Splunk Cookie Policy

We use our own and third-party cookies to provide you with a great online experience. We also use these cookies to improve our products and services, support our marketing campaigns, and advertise to you on our website and other websites. Some cookies may continue to collect information after you have left our website. Learn more (including how to update your settings) here.
Accept Cookie Policy

Accept License Agreements

This app is provided by a third party and your right to use the app is in accordance with the license provided by that third-party licensor. Splunk is not responsible for any third-party apps and does not provide any warranty or support. If you have any questions, complaints or claims with respect to this app, please contact the licensor directly.

Thank You

Downloading Sentiment Analysis
SHA256 checksum (sentiment-analysis_13.tgz) ccc7a6569c08b9d483a370d3854c6c2759215ec6972565f01404599e59e72b53 SHA256 checksum (sentiment-analysis_12.tgz) 877df6192fc149a4f59b3bd26998a2cbeb6b3752037d94d39210585f317fff5b SHA256 checksum (sentiment-analysis_11.tgz) 41831a9916884e69c1142c7f769d824f18b87e0b98224cebd0a60138a79746f8 SHA256 checksum (sentiment-analysis_10.tgz) b944c76d0875e341abcf2bb3bda508ac365570d2851ace3826b3f1db5cf9e602 SHA256 checksum (sentiment-analysis_094a.tgz) 4c74fe73454d641e55df8c89d387cf48f977ffd5b30f9d355384b2d7e5b9330b SHA256 checksum (sentiment-analysis_093a.tgz) 9729c78d91eb6f0db42e6748a7f24a4f38f92a83570426595af965b5a8aa48eb SHA256 checksum (sentiment-analysis_092a.tgz) 64e66dbf6f469f1c808ad34b6f74423f7684d3544f0082f09a1b83c5a2c475a1 SHA256 checksum (sentiment-analysis_091a.tgz) 8a107da3b8eef8b3f73fa3c6b80a824fe3c528090ca7d154bc1255d23733cae3 SHA256 checksum (sentiment-analysis_090a.tgz) 1a08bd7621088e12df28f73d79fdcc7a8db60910599dc9c581d5e40858ab0511 SHA256 checksum (sentiment-analysis_085a.tgz) 0bc99d3139178943b0df993d491d21460aab903275a413054ed36db2f07e6ceb SHA256 checksum (sentiment-analysis_082a.tgz) 476519dcaa11f012f3f73a03d19f36ec96b7bbbbe3b5613db514336049af8d83 SHA256 checksum (sentiment-analysis_081a.tgz) a3d981ae65a32fcf5d7a5c1b3a8f2a2c4ab8c284d77d2f70b8db7070a1bcca58 SHA256 checksum (sentiment-analysis_08a.tgz) 33c3f62b2578f8f2c89995b0bcc6994884a86ffee960074327ad184829132162
To install your download
For instructions specific to your download, click the Details tab after closing this window.

Flag As Inappropriate

Sentiment Analysis

Overview
Details
Now you can analyze user opinion, converting text into ratings. For example, how do twitter users feel about your company over time? How do people in California vs Texas feel about various issues? How is your marketing or tech support performing?

The sentiment analysis app allow you to analyze user opinion, converting text to numerical ratings.

  • How do twitter users feel about your company over time?
  • How do people in California vs Texas feel about various issues?
  • How is your marketing or tech support performing against competitors?

This app includes:

  • two trained datasets (twitter and imdb)
  • three search commands:
    • sentiment to predict user sentiment
    • language to predict what language an event is written in
    • tokens to make it easier to tokenize terms and phrases for analyzing text
    • heat to measure how emotionally charged a text is

From a command shell, you can train it on your own data. The training produces a (naive bayes classifier) model file used for the sentiment command, but training also outputs a lookup table of a few thousand terms and their expected sentiment rating, so the vocabulary can be tweaked and used with lookup commands to also do some basic sentiment analysis.

A note about accuracy: Over the twitter data, assuming 50-50 positive and negative tweets, it's about 70% accurate. Assuming the actual distribution of tweets, which seems to be about 75% positive, it's about 85% accurate. The most important part is not the accuracy on any given text but on the aggregate -- to see how sentiment trend over time or how "google" vs "apple" compare with other.

Release Notes

Version 1.3
April 28, 2014

handle non-utf-8 more gracefully

Version 1.2
March 24, 2014

Fixed bug in tokens command. Reorganized 'local' into 'default'

Version 1.1
Sept. 23, 2013

updated app so commands are exported properly to other apps

Version 1.0
Sept. 12, 2013

updated 'tokens' to not give error messages unappropriately. updated 'heat' terms to return fewer false positives of swearing and violent terms.

Version 0.94A
July 29, 2013

updated package

Version 0.93A
Nov. 2, 2012

- Added new sentiment dashboards:
----- overview,
----- basic sentiment,
----- compraison dashboard to compare two values (e.g. phoneX vs phoneY).
- Added 'heat' command to find emotionally excited text
- Recent improvements:
----- Fix a major bug where only the first batch of results (e.g., 50) were getting sentiment but all other events were empty.
----- Performance speed up.
----- Added support for distributed environments. Previously model files were not being distributed to indexers, cause an error and sentiment failing to work.
- Fixed bug preventing sentiment from finding model files.
- Added sample training data

Version 0.92A
Oct. 31, 2012

- Added new sentiment dashboard: overview, basic sentiment, and a dashboard to compare two values (e.g. phoneX vs phoneY).
- Recent improvements:
- Fix a major bug where only the first batch of results (e.g., 50) were getting sentiment but all other events were empty.
- Performance speed up.
- Added support for distributed environments. Previously model files were not being distributed to indexers, cause an error and sentiment failing to work.
- Fixed bug preventing sentiment from finding model files.
- Added sample training data

Version 0.91A
Oct. 29, 2012

- Added new sentiment dashboard
- Recent improvements:
- Fix a major bug where only the first batch of results (e.g., 50) were getting sentiment but all other events were empty.
- Performance speed up.
- Added support for distributed environments. Previously model files were not being distributed to indexers, cause an error and sentiment failing to work.
- Fixed bug preventing sentiment from finding model files.
- Added sample training data

Version 0.90A
Oct. 29, 2012

- Added new sentiment dashboard
- Recent improvements:
- Fix a major bug where only the first batch of results (e.g., 50) were getting sentiment but all other events were empty.
- Performance speed up.
- Added support for distributed environments. Previously model files were not being distributed to indexers, cause an error and sentiment failing to work.
- Fixed bug preventing sentiment from finding model files.
- Added sample training data

Version 0.85A
Oct. 26, 2012

Fix a major bug where only the first batch of results (e.g., 50) were getting sentiment but all other events were empty.

Performance speed up.

Version 0.82A
Sept. 27, 2012

Added support for distributed environments. Previously model files were not being distributed to indexers, cause an error and sentiment failing to work.

Version 0.81A
Sept. 25, 2012

- Fixed bug preventing sentiment from finding model files.
- Added sample training data

Version 0.8A
Aug. 29, 2012

115
Installs
4,128
Downloads
Share Subscribe LOGIN TO DOWNLOAD

Subscribe Share

AppInspect Tooling

Splunk AppInspect evaluates Splunk apps against a set of Splunk-defined criteria to assess the validity and security of an app package and components.

Are you a developer?

As a Splunkbase app developer, you will have access to all Splunk development resources and receive a 50GB license to build an app that will help solve use cases for customers all over the world. Splunkbase has 1000+ apps and add-ons from Splunk, our partners and our community. Find an app or add-on for most any data source and user need, or simply create your own with help from our developer portal.

Follow Us:
© 2005-2019 Splunk Inc. All rights reserved.
Splunk®, Splunk>®, Listen to Your Data®, The Engine for Machine Data®, Hunk®, Splunk Cloud™, Splunk Light™, SPL™ and Splunk MINT™ are trademarks and registered trademarks of Splunk Inc. in the United States and other countries. All other brand names, product names, or trademarks belong to their respective owners.