Connect with us

FACEBOOK

How PayPal uses Built-in NLP in Messenger

Published

2 years ago

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

Related Topics:
Continue Reading

FACEBOOK

Best Practices for Designing Great Messaging Experiences on Messenger

Published

15 hours ago

on

February 27, 2020

By

We recently reminded our community of the upcoming policy changes to the Messenger platform that will go into effect on March 4, 2020. These policy changes were designed to improve the messaging experience between people and businesses by driving timely and personally relevant conversations — prioritizing conversations started by people and related follow-up communications.

To help businesses best adapt to these new policy changes, here are some tips on the best practices to adopt when designing messenger experiences:

1. Respond quickly and set customer expectations on response times

People expect businesses to respond quickly and provide timely updates. We have found a strong correlation between responsiveness and successful business outcomes.>

2. Make it short and sweet

Make sure to communicate your key points succinctly and early on in your message. This aligns with people’s expectations for messaging as a channel and increases readability. Messages that are short and to the point can also be read clearly in message previews.

3. Leverage Messenger features to send high value messages outside the 24 hour standard messaging window

Successful businesses know the options available to send messages outside the standard messaging window and use them effectively.

  • Message tags – use tags to send personal, timely and important non-promotional messages. Businesses can use tags to send account updates, post purchase updates, confirmed event updates, and human agent responses.
  • One-Time Notification – allows a page to request a user to send one follow-up message after the 24-hour messaging window has ended. This can be used for cases such as back in stock alerts where a person has explicitly requested the business to send out a notification. Make sure that the message matches the topic the user agreed to receive the notification for and this message is fully communicated on the first attempt. You may also want to prompt people to interact with your notification in order to restart the standard messaging window.
  • Sponsored Messages – use sponsored messages for broadcast promotional updates to customers you’ve interacted with in Messenger. Sponsored messages support Facebook ads targeting and have built-in integrity controls to help us safeguard the user experience in Messenger.

4. Focus on customer value

Ensure your messages clearly communicate customer value – especially notifications sent outside the standard messaging window. Sending out low value messages makes it more likely that customers will tune out or block messages from your business altogether. Businesses using Messenger’s platform should consider adjusting push parameters for valuable messages that don’t require immediate action.

5. Provide audiences with options to choose from

Consider giving your audience additional control over the type of content they will receive via Messenger. For example, you may allow the user to select specific types of account alerts or post-purchase updates provided they comply with the Messenger platform policies.

We believe following these simple guidelines will help to ensure a businesses’ messaging efforts will be effective and drive outcomes, while providing customers with pleasant and valuable interaction experiences that encourage them to continue engaging with the business on Messenger.

Facebook Developers

Continue Reading

FACEBOOK

Two Billion Users — Connecting the World Privately

Published

2 weeks ago

on

February 12, 2020

By

We are excited to share that, as of today, WhatsApp supports more than 2 billion users around the world.

Mothers and fathers can reach their loved ones no matter where they are. Brothers and sisters can share moments that matter. Coworkers can collaborate, and businesses can grow by easily connecting with their customers.

Private conversations that once were only possible face-to-face can now take place across great distances through instant chats and video calling. There are so many significant and special moments that take place over WhatsApp and we are humbled and honored to reach this milestone.

We know that the more we connect, the more we have to protect. As we conduct more of our lives online, protecting our conversations is more important than ever.

That is why every private message sent using WhatsApp is secured with end-to-end encryption by default. Strong encryption acts like an unbreakable digital lock that keeps the information you send over WhatsApp secure, helping protect you from hackers and criminals. Messages are only kept on your phone, and no one in between can read your messages or listen to your calls, not even us. Your private conversations stay between you.

Strong encryption is a necessity in modern life. We will not compromise on security because that would make people less safe. For even more protection, we work with top security experts, employ industry leading technology to stop misuse as well as provide controls and ways to report issues — without sacrificing privacy.

WhatsApp started with the goal of creating a service that is simple, reliable and private for people to use. Today we remain as committed as when we started, to help connect the world privately and to protect the personal communication of 2 billion users all over the world.

The post Two Billion Users — Connecting the World Privately appeared first on About Facebook.

Facebook Newsroom

Continue Reading

FACEBOOK

Facebook, Instagram and YouTube: Government forcing companies to protect you online

Published

2 weeks ago

on

February 12, 2020

By

Although many of the details have still to be confirmed, it’s likely the new rules will apply to Facebook, Twitter, Whatsapp, Snapchat, and Instagram

We often talk about the risks you might find online and whether social media companies need to do more to make sure you don’t come across inappropriate content.

Well, now media regulator Ofcom is getting new powers, to make sure companies protect both adults and children from harmful content online.

The media regulator makes sure everyone in media, including the BBC, is keeping to the rules.

Harmful content refers to things like violence, terrorism, cyber-bullying and child abuse.

The new rules will likely apply to Facebook – who also own Instagram and WhatsApp – Snapchat, Twitter, YouTube and TikTok, and will include things like comments, forums and video-sharing.

Platforms will need to ensure that illegal content is removed quickly, and may also have to “minimise the risks” of it appearing at all.

These plans have been talked about for a while now.

The idea of new rules to tackle ‘online harms’ was originally set out by the Department for Digital, Culture, Media and Sport in May 2018.

The government has now decided to give Ofcom these new powers following research called the ‘Online Harms consultation’, carried out in the UK in 2019.

Plans allowing Ofcom to take control of social media were first spoken of in August last year.

The government will officially announce these new powers for Ofcom on Wednesday 12 February.

But we won’t know right away exactly what new rules will be introduced, or what will happen to tech or social media companies who break the new rules.

Children’s charity the NSPCC has welcomed the news. It says trusting companies to keep children safe online has failed.

“Too many times social media companies have said: ‘We don’t like the idea of children being abused on our sites, we’ll do something, leave it to us,'” said chief executive Peter Wanless.

“Thirteen self-regulatory attempts to keep children safe online have failed.

To enjoy the CBBC Newsround website at its best you will need to have JavaScript turned on.

Back in Feb 2018 YouTube said they were “very sorry” after Newsround found several videos not suitable for children on the YouTube Kids app

The UK government’s Digital Secretary, Baroness Nicky Morgan said: “There are many platforms who ideally would not have wanted regulation, but I think that’s changing.”

“I think they understand now that actually regulation is coming.”

In many countries, social media platforms are allowed to regulate themselves, as long as they stick to local laws on illegal material.

But some, including Germany and Australia, have introduced strict rules to force social media platforms do more to protect users online.

In Australia, social media companies have to pay big fines and bosses can even be sent to prison if they break the rules.

For more information and tips about staying safe online, go to BBC Own It, and find out how to make the internet a better place for all of us.

Read More

Continue Reading

Trending