As part of the Cognitive
Enterprise and also as part of the Watson Education, it is quite interesting to
know something beyond the usual ‘SIRI’ what most of us know.
What made me get interested in
Chatbots and also start my own use-cases ( Yes, I have been a Business Analyst
too!) is the urge to create the
EmpathyBots that I want to create for ‘Diversity & Inclusion’
initiatives, I can choose no better
topic than Chatbots today.
What is a Chatbot?
Chatbot is a
computer program designed to simulate
conversation with human users, especially over the Internet.
A few years
ago when chatbots were just gaining popularity, there was a lot of talk around
what a chatbot actually was. With the advent of natural language processing and
various machine learning techniques, some of the more advanced conversational
applications wanted to separate themselves from their competition. Many began
calling themselves “virtual assistants.” This implied that they were somehow
bigger or more powerful than existing chatbots, or perhaps were more
conversational or could cover a wider range of topics.
The market
did not care how powerful the bot was or about the underlying technology, so
long as it solved the right problems. So in a way, many of these different
terms for bots became more or less synonymous with each other. It didn’t matter
what you called it – you were getting something you could hold a conversation
with. We’re now at a point where we know that regardless of what you call the
bot, there are usage patterns and differentiation that make chatbots distinct.
Chatbots let
you streamline how you engage with customers, partners, and employees. Use
Watson to build robust, enterprise-grade chatbots to transform your customer
service department and more.
Conversational Solutions for your business
and social life
Whether
you're looking to build a basic bot from scratch or looking for more robust
integrations, Watson lets you build powerful chatbots that can understand your
customers, provide answers and even execute business processes. According to
the research study by Mindbowser
in association with Chatbots Journal. IBM Watson is the first choice as a bot-building platform for 61% of
businesses.
When you’ve
done your research and are at the point of beginning to build your bot, think
carefully about what problems you’re trying to solve and what functionalities
you will want to incorporate. Knowing what you want your application to solve
for and assist with will decide the type of chatbot, virtual assistant or agent
you ought to build. This will impact both your development plan and, as
importantly, your end-user experience. The following are the three main types
of chatbots I have come across, with background on their particular uses and
variations.
Three Main
Types of Chatbots
1. Support chatbots
Support
chatbots are built to master a single domain, like knowledge about a company.
Support chatbots need to have personality, multi-turn capability, and context
awareness. They should be able to walk a user through any major business
processes, and answer a wide range of FAQ-type questions. You will want to have
a short-tail and long-tail combo solution when building this type of chatbot.
At IBM Watson, we would use the Watson Conversation service for the short-tail, common
questions and processes, and Watson Discovery service for the long-tail, but there are
many potential solutions for this. Speech is an optional feature, and not a
necessity, since users typically have sat down at a desktop and are ready to
figure out their solution. The chatbot developer will want to spend the most
time making sure it is as easy as possible to navigate the bot, and ensuring it
can execute the actions that your users actually care about (for example, just
because you want to sell more credit cards doesn’t mean your customers want to
open more credit card accounts).
2. Skills chatbots
Skills
chatbots are typically more single-turn-type bots that do not require a lot of
contextual awareness. They have set commands that are intended to make life
easier: “Turn on my living room lights,” for example. Speech functionality is
recommended for this type of chatbot so the user does not need to turn on a
device or click any buttons. They should be able to follow commands quickly, so
that your users can multitask while engaging with the bot. These chatbots do
not need to worry too much about contextual awareness, unless you want to
design a particularly advanced one, as people will quickly learn what to say,
and say it appropriately. It’s a nice bonus if you can give a command, and your
bot knows – to return to our example – that you are in the kitchen and acts to
turn on the correct lights.
However,
this is not a necessary function, as users will quickly learn to give the
appropriately specific command. When building a skills bot, it is important to
focus on integration, especially when controlling a home or personalized
objects. Keep integration simple so your users can interact with the bot
without worrying about how to use .
3. Assistant chatbots
Assistant
chatbots are more or less a middle ground between the two bots above. They work
best when they know a little bit about a variety of topics. Many people
envision these bots will someday become navigators of all other bots that are
out there now. Want to pay a bill? Ask your assistant bot to talk to the
support bot for your bank. Assistant chatbots need to be conversational and
respond to just about anything, while being as entertaining as possible. Siri
is a good, current example – while she only does so much, people continually
ask her for things simply because even when she cannot perform the command, the
response she gives tends to be amusing. When building an assistant chatbot, it
is important to make it as obvious as possible how the bot is trained. The range
of questions a user might ask is large, so making sure you have adequate
coverage is going to be the most difficult factor. In many cases, when people
do not know what they should ask, they will not ask anything at all. And if you
miss the few topics they initially are willing to try, they will not come
back for more.
Even though
these are the most common types, many bots in production fall somewhere in
between two. Some are even a combination of all three. No matter what type of
bot you decide to build, it is important to give your bot some life and
personality, make it useful, and make sure it’s easy to use. People interact
with bots because they want to get something done in a more natural way than
was previously possible. Whether it’s something simple like turning on a light,
or something complex like applying for a mortgage, every pattern has specific
features that make it stand out, so be sure your bot shines brightly in what
it’s designed to do. The possibilities are endless.
Powering Social Good for Everyone with Chatbots!
These include bots that help people solve legal issues, get therapy, quit
smoking and learn to meditate.
Chatbots are
great for customer service, ordering tickets, or just giving you weather
updates, but others have nobler goals for their bots. Here are few bots,
developed using a variety of technologies and APIs, and delivered via
different interfaces, that are helping improve the world for everyone.
1. DoNotPay: Get free legal help in under 30 seconds
DoNotPay
started out as a cheeky service to help drivers get out of parking tickets.
Stanford student Joshua Browder became more interested in bots after the online
tool automatically challenged over 160,000 of them. People began contacting him
asking for help with other legal issues relating to evictions, bankruptcies,
and repossessions, so he decided to expand the capabilities of the bot to help
homeless people.
Rather than making users fill out a lengthy form, Browder
used a natural language interface to gather the data needed to fill out the
form. He then used IBM
Watson’s Conversation service which helped him improve accuracy by 30%.
Browder was only 19 years old when he created this app and Watson’s
cognitive APIs helped him build stronger AI into his app in a matter of just
weeks. He has since turned his attention to other areas of law, including
resolving landlord and travel disputes.
Browder
mined 15 years of affordable housing application data, obtained via a Freedom
of Information Act (FOIA) request. Then he programmed DoNotPay to ask users
personal questions relating to their stated problem. For example, it may ask a
resident facing eviction “do you have a right to live here?”. It might ask a
person seeking housing “are you legally homeless,” while providing them with a
legal definition. It then takes this information and creates an application
based on previous success rates, using one of seven default claim letters. His
goal with the service is to offer a replacement for what he sees as a subset of
predatory lawyers that charge heavy fees to do little more than file paperwork.
Since his
success with DoNotPay, Browder, dubbed the ‘Robin Hood of the Internet’ by the
BBC, has expanded it to give free legal aid to refugees seeking asylum in the
US, Canada and UK.
2. Woebot: Your 24×7 Chatbot Therapist
Created by a
team of Stanford psychologists and AI experts, Woebot uses short chat
conversations, sentiment and tone analysis and word games to help people who
are looking for inexpensive therapy. Wombat Labs Inc. just launched the
commercial version of the chatbot this June. The first 14 sessions with the bot
therapist are free after which they offer tiered pricing of $6 – $12 per week
depending on what plan you sign up for.
Wombat’s creators gave the bot a fun, casual and friendly
personality. For example their website says Woebot is “…ready to listen, 24/7. No couches, no meds,
no childhood stuff. Just strategies to improve your mood. And the occasional
dorky joke.“
Wombat uses a combination of natural language processing,
therapeutic expertise, personalized content, and sense of humor to “create the
experience of a therapeutic conversation for all of the people that use him.”
The company describes their service as below:
“Woebot is an automated conversational agent (chatbot) who helps
you monitor mood and learn about yourself. Drawing from a therapeutic framework
known as Cognitive Behaviour Therapy, Woebot asks people how they’re feeling
and what is going on in their lives in the format of brief daily conversations.
Woebot also talks to you about mental health and wellness and sends you videos
and other useful tools depending on your mood and needs at that moment. You can
think of Woebot as a choose-your-own-adventure self-help book that is capable
of storing all of your entries, and gets more specific to your needs over
time.”
You can sign up for Woebot directly on their website at woebot.io
3. U-Report: Your voice matters
Across the
world, young people are concerned about a variety of issues, ranging from
climate change to the economy. Unicef created its own bot, U-Report, to give
them a voice. The bot, available via Twitter and Facebook Messenger, polls its
followers (called ‘U-Reporters’) on a range of topics. The idea is to gather
opinion and experiences from these young participants, who now number over
three million, and use them to help influence public policy.
U-Report
regularly sends out polls on a variety of issues, and assesses the results
based on demographic data provided by U-Reporters when they sign up.
The pollster
bot has achieved some notable results. In Liberia, it asked 13,000 young people
if teachers at their schools were exchanging grades for sex. 86% said yes,
uncovering an endemic problem and prompting Liberia’s Minister of Education to
work with UNICEF on stamping it out.
4. Quitxt: Helping users quit smoking
It is 2017,
and despite smoking bans and punitive taxes, people still continue to light up.
Could a chatbot help people to quit smoking? Dr. Amelie G. Ramirez of the
University of Texas Health Science Center at San Antonio’s Institute for Health
Promotion Research hopes so. She created Quitxt, an SMS-based quitbot designed
to help addicted puffers deal with their cravings.
Targeting
young adults aged 18-29, the bot consistently encourages smokers to give up and
not look back. Smokers can set their quit date and embark on an 8-10 week
program, receiving between three and seven text messages per day for the first
two weeks, gradually reducing over time. In addition to encouraging words, the
bot also provides tips for managing stress and building a support network.
Participants can expect links to mobile webpages designed to help people give up
smoking.
5. MeditateBot: Creating a daily meditation habit
While some
bots exist to help you stop a habit, others want to help you start one.
Entrepreneur Eric Rems created MeditateBot as a Facebook Messenger tool to help
him remember to meditate. Meditation is a proven
health technique, and helps practitioners to remain mindful throughout the
day, reducing stress and conflict.
Developed
over a weekend, the chatbot teaches the benefits of meditation and advises on
different kinds. It also enables people to schedule daily meditation reminders.
When creating the bot, Rems focused on keeping the barrier to entry low by not
imposing too many requirements on users early on. He avoided collecting too
much information from them, so that they could begin using the bot easily
without filling out forms that would create a hurdle for them to begin using
the bot.
He enabled
them to choose when they meditate, and let them choose how long. He also
limited the available options. “I’ve seen too many apps that have an endless
amounts of options, this makes it hard to select the “right” one — which causes
frustration,” he said.
Over 500,000
users have been busy chilling out and improving their mental health using the
chatbot, so he must be doing something right.
The possibilities are endless. What type of Chatbot can you build?
References:
Source : Article: Christie Schneider
Promoting IBM Watson being a proud IBMer!
