Get Started

Sentiment analysis

This plugin provides a recipe to perform sentiment analysis on your text data

This plugin provides a tool for performing sentiment Analysis on textual data.

The plugin comes with a single recipe that allows you to estimate the sentiment polarity (positive/negative) of a text based on it content. For instance, you could use this recipe on a dataset of user reviews or social media data (such as tweets) to know which instances are positive (1) and which are negative (0).

Estimate the sentiments from your data directly into DSS
Estimate the sentiments from your data directly into DSS.

Plugin Information

Version 1.3.0
Author Dataiku (Hicham EL BOUKKOURI)
Released 2018-07-09
Last updated 2018-07-09
License Apache Software License
Source code Github
Reporting issues Github

How To Use

First, make sure your text data is stored in a dataset, inside a text column, with one row for each document. Using the recipe is very straightforward. Just plug in your dataset, select the column containing the documents you are interested in scoring and run the recipe!

You can tick the “Output confidence scores” box to output the model’s confidence for each prediction.

This plugin uses the text classification library fastText. If you are interested in learning more about how fastText can be used for text classification, you can refer to the following Notebook tutorial.


The English model bundled with this plugin comes from fastText, which is BSD-licensed


Get the Dataiku Data Sheet

Learn everything you ever wanted to know about Dataiku (but were afraid to ask), including detailed specifications on features and integrations.

Get the Data Sheet