Automate your work using Customer Sentiments

Updated 8 months ago by Charles Jacquet

Facial expression, tone of voice or body language are all clues that improve oral communication but are lacking in online interactions. Yet, knowing how a customer feels could greatly improve the quality of your customer service.

If you're not familiar with the basics on Rules in Gorgias check out the articles below before you get started: Automate your work with Rules

How it works

The good news is, Gorgias automatically detects your customers' sentiment! Is the customer angry, in a rush or simply grateful for the service? Here's how you can figure all of that in a single glance using customer sentiments through rules.

This is also great to rapidly filter through Instagram or Facebook comments.

List of customer sentiments

Gorgias currently handles the following sentiments. Stay in touch as more may come!

Name

Description

positive

Customer is satisfied about the product, the service, or shows positive feelings about something you posted on social media.

Example: "Okay that's perfect, thank you!", "That looks gorgeous!"

promoter

Customer shows intense satisfaction about the product, the service or the brand

Example: "I LOVE IT SO MUCH!!!!!! This is utter perfection, thank you thank you! I've been telling all my friends about your products"

negative

Customer shows general dissatisfaction about a product or the service.

Example: "I just received the package and I'm very disappointed."

threatening

Customer is threatening take legal action, buy elsewhere or post a negative review.

Example: "Refund me now or I will sue you."

urgent

Customer shows impatience (multiple unsuccessful contacts) or mentions an urgent need (cancel or change an order before it ships, ....) .

Example: "Ordered the wrong item. Need to cancel ASAP!"

offensive

The message contains offensive language or inappropriate adult suggestions.

As per the screenshot below, more than one sentiment can occur at the same time:

Setup instructions

Tagging tickets with customer sentiments

The recommended way to benefit from the feature is to apply specific tags to the tickets so that you can figure out easily if some tickets require that extra attention. Here's how to create a simple rule to tag tickets using customer sentiments.

  1. In Settings, go to Rules and click Create new rule
  2. Select WHEN new message in ticket and/or ticket created as a trigger
  3. Click on THEN, and select an IF statement
  4. Select message -> sentiments -> contains one of -> "negative"
  5. Click on following THEN, select Add tag as an action, and type "negative"
  6. Click Save
  7. Don't forget to activate the rule!

Negative tickets

This example shows a simple rule tagging negative tickets using both the "negative", "threatening" and "offensive" sentiments.

Urgent tickets

You can set up a rule to auto-tag the ticket if the customer is showing impatience or mentions an urgent need. Example: "Ordered the wrong item. Need to cancel ASAP!"

To go further...

Here are some other rules ideas:

  • Tag negative/positive feedback for one product line (use the sentiment crossed with keyword)
  • Auto-hide negative comments on social media
  • Auto-like/close positive comments on social media
  • Flag promoter customer to retarget them in the future
  • Modulate your auto-response depending on sentiment (if sentiment is urgent or negative, don't auto-respond)

You can also combine customer sentiments with customer intents! See our other article: Automating your work using customer intents.

FAQs

Can customer sentiments recognize emojis as well?

Yes, the sentiments detection model can recognize emojis

Can a message be positive and negative at the same time?

No, the model will highlight the "main" sentiment of the message.

For example, if the message is "I like the shirt but it started losing its color after 2 washes, I am so disappointed...", the detected sentiment will be negative

Supported languages

Intent detection works in a number of most commonly spoken languages which is a huge advantage! The feature supports 16 most commonly spoken languages, so even if the customer is writing over to you in another language, we can detect the keywords and trigger the rule.

The currently supported languages are:

  1. Arabic (ar)
  2. Chinese (PRC) (zh)
  3. Chinese (Taiwan) (zh-tw)
  4. Dutch (nl)
  5. English (en)
  6. German (de)
  7. French (fr)
  8. Italian (it)
  9. Portuguese (pt)
  10. Spanish (es)
  11. Japanese (ja)
  12. Korean (ko)
  13. Russian (ru)
  14. Polish (pl)
  15. Thai (th)
  16. Turkish (tr)

What do you think? Yay or Nay?