How to extract keywords from Zendesk Support Tickets & Chats using generative AI
How to extract keywords from Zendesk Support Tickets & Chats using generative AI
There are golden insights in the conversations your support team has with customers. However, to comb through each support ticket would be wildly impractical and inefficient. Fortunately there is an easy, cost-effective way to identify important insights from your Zendesk support tickets using AI. In this post, we’ll show you how to use generative AI to automatically extract keywords from Zendesk support tickets and chats.
What is Keyword Extraction?
Keyword extraction is a natural language processing (NLP) technique that involves identifying the most important or relevant words or phrases in a piece of text. You can use it to extract key information and themes from text has many applications, such as search engine optimization (SEO), content analysis, and topic modeling.
Keyword extraction can be performed manually, but it can also be automated using machine learning algorithms. These algorithms learn to recognize patterns and features in the text that are associated with important words or phrases, and can be trained on a labeled dataset of text.
You can use keyword extraction to analyze and summarize large amounts of text data to quickly identify the most important information and themes.
Example Use Cases
Use cases for extracting keywords from Zendesk support tickets and chats include:
- Categorizing and prioritizing support tickets
- Identifying common issues and trends
- Improving response times
- Personalizing customer interactions
- Identifying areas for training and improvement
Teams that might find these use cases helpful include: customer support, customer success, product, marketing, and operations.
Finding your input data and identifying preliminary keywords
You first need to identify the data that you want to work with. Here, we are looking at Zendesk support tickets and chats. You can extract this data using the Zendesk API, export it in CSV format, query a list of tickets from your data warehouse or BI tool, or copy and paste with an example ticket.
For more information on the Zendesk API see here: https://developer.zendesk.com/api-reference/
Next, it can be helpful (but not necessary) to identify common keywords that you may want to extract from your support tickets. Generative AI tools can be used to both identify and measure frequency of keywords but also to suggest additional keywords you may not have been aware to look for. For example - you might find that recurring customer inquiries around billing may provide insights into product improvement opportunities non-obvious to the initial support inquiry.
Once you have your data and preliminary keywords identified, you can use generative AI to automatically assess the sentiment of your Zendesk support tickets and chats. This will help you improve the quality and consistency of your customer support. This can help you both reduce churn and improve the efficiency of your support team.