Sentiment analysis - Customer Service Management (CSM)

pradeep reddy
Tera Contributor

Hello folks,

 

Have you ever wondered about knowing the mood of the customer that you are communicating with, that can be possible through the sentiment Analysis of task intelligence in customer service management.


What is Sentiment analysis?
->Sentiment analysis is the field that tries to give machines and computer software the ability to understand the emotions of the user.
->To put it another way sentiment analysis is a method that helps you analyze and understand the tone/emotion of a particular text

->Sentiment analysis has capability that could be used by customer service agents in order to better prioritize the cases by taking emotional context into consideration as well.

Configuration steps:
Required plugins:
In order to set up sentiment analysis in the instance the instance should be pre-installed with the predictive intelligence and machine learning capabilities.
-> com. glide.platform_ml_pa 
-> com. snc.csm_ml

Properties Need to be enabled:
-> com.glide.cs.enable_sentiment_analysis
-> sn_csm_ml_task.case.sentiment.ml-predictor.enabled


Once the sentiment analysis feature is installed it adds the following fields:

Field

Field Values

Original sentiment

1. Positive(1.0)

2. Neutral(0.0)

3. Negative(0.5)

Current sentiment

1. Positive(Green)

2. Neutral(Blue)

3. Negative(Red)

Sentiment over time

1. Improving

2. Neutral

3. Declining

 

We can Configure these fields for each of the following interfaces as needed:

  • CSM Configurable Workspace
  • CSM Agent Workspace
  • Core UI Platform interface

For now, will configure it for the agent workspace:

  1. Enter sys_aw_list.list in the application navigator and press Enter.
  2. Click All from the Case [sn_customerservice_case] table.
  3. Click the lock icon next to the Columns field.
  4. Select and move the sentiment fields from the Available column to the Selected column.
  5. Click the lock icon again.
  6. Click Update.

Workspace list.png

 

Use the sentiment analysis feature included with Task Intelligence for Customer Service to:

  • Evaluate email and case text.
  • Identify the current sentiment of new cases.
  • Identify the ongoing sentiment of updated cases.
  • Display this information on agents and managers.

Before the model creation:

Screenshot 2023-05-19 at 5.29.32 PM.png

 

Creating a model to predict case sentiment:

Screenshot 2023-05-19 at 5.57.33 PM.png

 

Select the case types that need the customer sentiment prediction:

Screenshot 2023-05-19 at 6.15.10 PM.png

 

Screenshot 2023-05-19 at 5.58.31 PM.png

 

Once the model is assessed we can see the sample records that were sentiment predicted:

Screenshot 2023-05-19 at 5.59.02 PM.png

 

Once you are happy with the prediction, we are ready to deploy:

Screenshot 2023-05-19 at 6.01.10 PM.png

Screenshot 2023-05-19 at 6.01.32 PM.png

 

 

 

 

 

 

 

 

After the model creation and training the Case sentiment prediction:

Screenshot 2023-05-19 at 4.38.40 PM.png

 

Advantages:
1. By incorporating sentiment analysis organizations can automate the process of analyzing customer feedback, identify patterns, and take proactive measures to address issues or improve customer experiences.

2. It allows for a better understanding and management of sentiment-related data within the ServiceNow ecosystem.
3. By applying sentiment analysis techniques, organizations can gain valuable insights into the sentiment and emotions expressed by customers on the cases raised.

 

Reference: 

1. Sentiment Analysis. 

2. Configuration 

3. Model setup 

 

Please refer to ServiceNow Docs  for more details

 

Liked the article? Hit bookmark and mark it as helpful, it would mean a lot.

 

Thanks for reading, have a great day!

12 REPLIES 12

Community Alums
Not applicable

Good one.

Thank you sharath

Vedhavrath_Kond
Tera Guru

Good One, great detail.

Thank you vedha