Connect with us

FACEBOOK

How PayPal uses Built-in NLP in Messenger

Published

on

Regardless of how good a bot’s UX flow is, people sometimes send inputs that the developer hasn’t accounted for. Unexpected behavior can potentially break the flow of a bot’s experience and lead to customer frustration when the bot responds incorrectly or doesn’t respond at all.

The Messenger Platform’s built-in natural language processing (NLP) feature can be an effective way to handle these types of off-script user behaviors. To show you how this can work, let’s take a look at PayPal’s Messenger bot.

The fintech company recently integrated built-in NLP into its Messenger bot to take advantage of Wit.ai. This allows their bot to process and understand questions and commands from their customers as free-form input, including questions about their accounts, password resets, declined payments, issues with purchases, and requesting refunds.

PAYPAL BOT DESIGN APPROACH

PayPal designed their bot to have a conversational flow while combining features from the Messenger/Wit.ai platforms. Their team used Wit.ai to create a conversational bot to interact with their customers and provide help with their accounts in real time.

“We looked at a number of NLP tools before choosing Wit.ai. The fact that Wit.ai was integrated into Messenger was a big plus, but we also found that Wit.ai provided the right level of customization with an easy to use interface that allowed both technical and non-technical team members to directly contribute to the bot’s success.”
— Principal Product Manager, PayPal

In the example below, the user wants to ‘dispute a charge,’ which is recognized by built-in NLP and passed to the bot as an intent. The bot then recognizes that it is not able to handle this request with an automated response and uses the Messenger Platform’s handover protocol to seamlessly transition the conversation to a PayPal customer support agent. This design helps the team manage handoffs and conversation control without needing to store the handoff/control state for each conversation.

USING NATURAL LANGUAGE PROCESSING

For companies in industries like fintech, it can be difficult to handle free-form user inputs, since there is often not a common vernacular, and there can often be a lot of overlap in how certain terms are used. For example, if a customer send the input “payment” are they referring to the money they sent to a friend or a payment toward an account balance? Traditionally the solution for these cases is to ask a series of questions to narrow down the user’s intent. This can create additional effort and frustration for the customer, so PayPal decided to focus on simple questions and answers that provide a lot of value, while recognizing when it’s best to pass the conversation to a human.

When they built the bot, PayPal’s developers integrated built-in NLP and customized their entities via Wit.ai. This eliminated the need for separate API calls to other NLP services and reduced latency. They also used both the Wit console and the POST/sample API to provide examples of questions the bot might receive from customers, and because the Wit console is user-friendly and doesn’t require technology-specific input, they were able to quickly scale their bot. In addition, PayPal is a global company with users interacting with their bot from many different countries, so having an NLP framework that supports many languages was important for them (click here to see the languages currently supported by built-in NLP).

KEY TAKEAWAYS

PayPal’s developer team focused on simplicity and creating a bot that could respond quickly to customer needs. NLP combined with other Messenger platform tools gives their bot the ability to handle varied customer inquiries while minimizing the effort needed by the customer to complete their request. In addition, utilizing the Wit.ai platform allowed the PayPal product, design, customer support, and engineering teams to work together seamlessly to understand common questions and needs from their audience base so their bot would deliver the desired results.

Messenger Developer Blog

FACEBOOK

Helping Prevent Discrimination in Ads that Offer Housing, Employment or Credit Opportunities.

Published

on

iscrimination has no place on Facebook, and our advertising policies have long prohibited unlawful discrimination. Over the last year, our auditors have released two progress updates on Facebook’s Civil Rights Audit and we reached a historic settlement with leading civil rights organizations. As part of the settlement, we introduced a new process for how advertisers based in the US, or trying to reach audiences in the US, can buy ads that offer housing, employment or credit opportunities. These ads are known as Special Ad Categories and are restricted from using the following targeting criteria: age, gender, ZIP code, multicultural affinity or any detailed options describing or appearing to relate to protected characteristics.The Latest News from Facebook for Business

Continue Reading

FACEBOOK

Facebook Brings WhatsApp Integration to Its Revamped Crisis Response Tool

Published

on

Social network giant Facebook is adding a WhatsApp button to crisis response tool, its disaster-reporting and communications feature where a user requests or offers help during a time of emergency. The tool is being used in 300 crises in more than 80 countries presently.

The new feature will allow people in affected areas to provide real-time information related to any disaster, TechCrunch.com reported on Tuesday.

Formerly, replies to requests on Facebook’s crisis response pages could only be sent with Facebook Messenger.

The update allow the social network to provide this information to state and local officials, as well as federal relief agencies such as Direct Relief and the National Alliance for Public Safety GIS Foundation.

Facebook is also expanding its Data for Good tools, using its data to provide relief organisations with information on where to distribute supplies, based on aggregated, anonymised data.

Additionally, Facebook is also updating its disaster maps to be more accurate in collaboration with agencies such as the International Displacement Monitoring Centre.

The new features will allow for photo and video sharing within the Crisis Response centre on Facebook.

Crisis Response originally developed out of a handful of features that help family, friends and communities support one another in the wake of a disaster.

NDTV Gadgets360.com

Continue Reading

FACEBOOK

Facebook to Allow Transfer of Photos, Videos to Google, Other Rivals

Published

on

Facebook started testing a tool on Monday that lets users move their images more easily to other online services, as it faces pressure from regulators to loosen its grip on data. The social network’s new tool will allow people to transfer their photos and videos directly to competing platforms, starting with Google Photos. The company said it will first be available to people in Ireland and will be refined based on user feedback.

The tool will then be rolled out worldwide in the first half of 2020.

US and European regulators have been examining Facebook’s control of personal data such as images as they look into whether the tech giant’s dominance is stifling competition and limiting choice for consumers. Facebook CEO Mark Zuckerberg has reacted by calling for new rules to address “data portability” and other issues.

Facebook said that as it worked on a new set of data portability tools, it had discussions with policymakers, regulators, and academics in the UK, Germany, Brazil, and Singapore to learn about which data should be portable and how to protect privacy.

The company is developing products that “take into account the feedback we’ve received and will help drive data portability policies forward by giving people and experts a tool to assess,” Steve Satterfield, director of privacy and public policy, said in a blog post.

NDTV Gadgets360.com

Continue Reading

Trending