Tagging tickets with customer sentiments
Updated 1 month ago
by
Victor Suo
Customer sentiments
Facial expression, tone of voice or body language are all clues that improve oral communication but are lacking in online interaction. Yet, knowing how a customer feels could greatly improve the quality of your customer service. This is also great to rapidly filter through Instagram or Facebook comments.
The good news is, Gorgias offers to automatically take a guess at the customer 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.
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.
- In Settings, go to Rules and click Create new rule
- Select WHEN new message in ticket and/or ticket created as a trigger
- Click on THEN, and select an IF statement
- Select message -> sentiments -> contains one of -> "negative"
- Click on following THEN, select Add tag as an action, and type "negative"
- Click Save
- Don't forget to activate the rule!
Negative tickets
This example shows a simple rule tagging negative tickets using both the "negative", "menacing" 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...
If you are interested in bringing your automated reply experience to another level, feel free to be creative and combine customer sentiments with customer intents. See our other article: Automating your work using customer intents.
List of customer sentiments
Gorgias currently handles six "sentiments". Stay in touch as more may come!
Name | Description |
positive | Customer is satisfied about the product or the service. Example: "Wonderful service. Highly recommend!" |
negative | Customer shows general dissatisfaction about a product, and issue or the service. Example: "I just received the package and I'm very disappointed." |
urgent | Customer is showing impatience or mentions an urgent need. Example: "Ordered the wrong item. Need to cancel ASAP!" |
menacing | Customer is menacing to buy elsewhere or take legal action. Example: "Refund me now or I will sue you." |
offensive | Ticket contains offensive language. |
need-human | Customer specifically asks to talk to an human (for example after an automated reply). |
Frequently asked questions
- Can customer sentiments recognize emojis as well?
Sentiments can recognize emojis, but not if the message contains only 1 emoji, we need at least 2 entities (2 words, 2 emojis, 1 word / 1 emoji...) in the message to return an answer from the model. Here's why:
- No data with only 1 entity in the dataset, so the accuracy is not optimal
- The emojis database is not 100% accurate and doesn't contain all of them
