Extract Sentiment

Sentiment analysis is one of the new branches of AI and natural language processing with the goal of understanding whether the context of a text piece is positive, negative or neutral. This has been proven helpful for businesses in detecting sentiment in the received feedback which leads to a better understanding of needs and goals.

To have an example of sentiment analysis, imagine a dataset composed of clients' feedback. A sentence such as I am tired of the delays is a negative, while I appreciate the time you spend in the support line is a positive sample.

📘

How can sentiment analysis be beneficial

Sentiment analysis focuses on the polarity of a text (positive, negative, neutral) and has been proven helpful for businesses in detecting sentiment in the received feedback which leads to a better understanding of needs and goals.

How to perform Sentiment analysis on Relevance AI's platform

Relevance AI provides you with a no-code workflow to analyse the sentiment of text fields in your dataset. This is done via complex and state-of-the-art neural networks trained and tested for this specific task.

Once you have uploaded your data, select your dataset, click on Extract Sentiment under Workflows and follow the instruction. If it is not listed in the Overview page (i.e. under "Suggested workflows for this dataset"), one easy way to access a workflow is to search for it under Browse Workflows as shown in the image below.

Clicking on "Get started" and "Continue" will activate each relevant section.
Steps are

1. specify the field(s) you want to analyse
2. Optional: review the optional settings
   1. Set up an advanced filter so the workflow only processes a subset of the data
   2. Change to No, if you do not wish to receive and email notification upon workflow completion
   3. Apply to the whole dataset by default processes all the entries that have not been processed with this workflow before.
   4. Modify the sensitivity level. Larger numbers makes the model more biased to become binary (Positive/Negative) whereas smaller numbers results in more neutrals
3. Click on "Run workflow"

After the workflow is finalised you can view the results (sentiment tag and sentiment score) under new fields that are automatically added to your dataset, on the Data view page.

Note 1: You do not need to keep the page open while the workflow is in progress. You can close the window or explore other functionalities of the platform.

Note 2: You can run multiple workflows in parallel (i.e. no need to wait for one to finalize).

Note 3: Workflow results are saved back to the dataset.

Note 4: Workflow results are independent of each other meaning they do not overwrite each other unless a workflow is run twice with the exact same workflow setup.

We will learn about the Emotion workflow on the next page.