Natural Language Processing and Conversational Shopping

Natural language processing (NLP) plays a critical role in human-machine communication. Billions of gigabytes of data are being created by users around the world every day. Most of this content is created in unstructured formats, making it unusable using regular programming techniques. With NLP, this unstructured data can be interpreted by machines without the requirements of strict data structures. To learn more about data and data structures.

In the fashion industry, natural language processing has been used in applications like conversational commerce, chatbots, AI-based stylists, image and trend classification, and micro-moment shopping.

Finding garments you like on the Internet can be really hard, requiring sifting through tens, hundreds, even thousands of listings. One of the most pervasive concepts to gain traction in fashion retail is conversational commerce, which took hold in late 2017. By integrating product information into a chat interface, brands are able to reduce friction during product discovery and provide highly personalized experiences to consumers searching for products, information, and customer service.

This article gives context for the emergence of conversational commerce and natural language processing, the technology that enables it.

Natural Language Processing

Language Processing

Natural language processing has been studied by computer scientists since the 1950s. Computer scientist Alan Turing thought the ability to use human language to be an important determinant of intelligence in machines. He later created the Turing test as a measure of machine intelligence. A machine passes the Turing test if it can fool people into believing it is a human. At that time and throughout the 1960s, the first chatterbots were created, exemplifying the power of natural language–based interfaces.


What makes you think I am entitled to my own opinion? —ELIZA, chatbot.

One of the most famous examples during this time was ELIZA. ELIZA was one of the first programs to pass a restricted version of the Turing test. Simulating a Rogerian psychotherapist, the program processed user inputs, saving them in memory and recalling them during conversation.

ELIZA was originally created by Joseph Weizenbaum at the MIT Artificial Intelligence Laboratory.

The ELIZA bot consists of a long list of possible responses and complex rules to determine which responses are used in conversation. In the 1980s, the architecture of these bots all changed because of machine learning.

Chatbots today are capable of more complex interactions because of the algorithms that control them.



Most chatbots can be placed into two basic categories: scripted and artificially intelligent. Scripted chatbots can follow only a predefined set of rules. This set of rules means the kinds of questions the chatbot can answer and the responses it can create are limited to the scripts it was programmed with. Artificially intelligent chatbots are built to interpret natural language used by humans and are capable of coming up with relevant responses to inputs that are not exactly pre-defined.

More recently, chatbots can use images as part of a conversation in addition to text.

Specialized Chatbots

Although numerous companies create general-use chatbots, some companies create chatbots specifically for retail applications. These chatbot services are more likely to help fashion retailers because a general-­purpose chatbot may get confused when discussing fashion or retail with a customer.

Companies like bake in style preference as well as size and fit preference. Another feature some of these companies are working on is integrating cross-brand size correlations to make it easier for consumers to know what size to buy in the moment that they’re considering purchasing.

In the end, it seems like these specialized chatbot services will become a one-stop shop for fashion brands looking for AI-assisted product discovery, product care, and customer service.

Conversational Commerce

I don’t know anyone who likes calling a business. And no one wants to have to install a new app for every business or service that they interact with. We think you should be able to mes-sage a business, in the same way you would message a friend —Mark Zuckerberg at F8 in 2016.

Conversational interfaces aren’t new. Although they have been around since the introduction of chatterbots like ELIZA in the 1960s, their traction today is likely explained by the rise in popularity of messaging apps. According to Business Insider, in 2015, messaging apps outpaced social media apps in growth. Messaging apps, which did not have widespread adoption until recent years, make for a natural interface for chatbot conversations.

Natural Language Queries

The main idea behind conversational commerce is to reduce the number of clicks that a user has to go through to reach a desired product. Rather than selecting a half dozen filters, a user can type what they’re looking for in a natural language query. Could be replaced with the simple input Find Women’s Sandals with 3-4˝ Heels in Black under $100.