In a new video learning path on O’Reilly Media, DataScience's Aaron Kramer explains how to extract valuable information from text data using natural language processing (NLP) techniques and the Python package spaCy. Because it allows for analyzing text and speech data automatically, NLP is particularly useful for business applications related to customer satisfaction, like prioritizing product development plans and building chatbots for customer support.
Optimizing Customer Satisfaction
Manually sifting through product reviews and surveys can be prohibitively time consuming, but NLP can be used to build data models that generate insights to help optimize customer satisfaction. These models automatically ingest text-based data from customer feedback and pinpoint the words and phrases most commonly used in the highest- and lowest-rated reviews. Using these insights, data-savvy companies can easily identify potential fixes that will have the greatest positive impact on user satisfaction. What’s more, the same models can be used to uncover the features customers enjoy most and promote those features accordingly.
Opinion Mining for Product Development
Sentiment analysis, also called opinion mining, combines NLP and statistics to evaluate the sentiment of text into positive, neutral, or negative categories. Each part of a phrase or sentence is assigned a score from 0 to 1 for positivity, neutrality, and negativity. These scores can then be compounded to arrive at the overall sentiment score for the text. This means companies can score feedback from existing or potential customers in terms of perceived urgency of their requests. This is essential for prioritizing the development of new features, but it can also be used for re-allocating loyalty discounts or customer support resources.
Building Chatbots for Customer Support
Many companies are successfully using customer support chatbots to streamline some of the work that would traditionally fall to representatives. Models built with NLP algorithms are the brains of these chatbots. They’re trained using text data from past conversations between your customer support agents and customers. This training allows your bot to identify the meaning of your customers’ requests using context clues and provide an answer that a human will understand. The whole process can take place almost instantaneously, so your customers never have to wait for an answer. In the meantime, the bot collects new data as it interacts with customers, so it can actually continue to learn from experience just as a human would.
These are only a few examples of the many ways NLP can be used to unlock valuable information from text data. To learn how to get started implementing these techniques in your business, don’t miss the O’Reilly video series or Aaron’s introductory guide to understanding the concepts and basic applications of NLP.