10 of the Most Innovative Chatbots on the Web
If you’ve ever used a customer support livechat service, you’ve probably experienced that vague, sneaking suspicion that the “person” you’re chatting with might actually be a robot.
Like the endearingly stiff robots we’ve seen in countless movies – tragic, pitiful machines tortured by their painfully restricted emotional range, futilely hoping to attain a greater degree of humanity – chatbots often sound almost human, but not quite. Their speech is awkward, the cadence somehow off.
It’s the online equivalent of the “Uncanny Valley,” a mysterious region nestled somewhere between the natural and the synthetic that offers a disturbing glimpse at how humans are making machines that could eventually supplant humans, if only their designers could somehow make their robotic creations less nightmarish.
Love them or hate them, chatbots are here to stay. Chatbots have become extraordinarily popular in recent years largely due to dramatic advancements in machine learning and other underlying technologies such as natural language processing. Today’s chatbots are smarter, more responsive, and more useful – and we’re likely to see even more of them in the coming years.
In this post, we’ll be taking a look at 10 of the most innovative ways companies are using them. We’ll be exploring why chatbots have become so popular, as well as the wider, often-unspoken impacts these constructs promise to have on how we communicate, do business, and interact with one another online.
Before we get into the examples, though, let’s take a quick look at what chatbots really are and how they actually work.
What Are Chatbots?
Chatbots – also known as “conversational agents” – are software applications that mimic written or spoken human speech for the purposes of simulating a conversation or interaction with a real person. There are two primary ways chatbots are offered to visitors: via web-based applications or standalone apps. Today, chatbots are used most commonly in the customer service space, assuming roles traditionally performed by living, breathing human beings such as Tier-1 support operatives and customer satisfaction reps.
Image via Loyalty Apps
Conversational agents are becoming much more common partly due to the fact that barriers to entry in creating chatbots (i.e. sophisticated programming knowledge and other highly specialized technical skills) are becoming increasingly unnecessary.
Today, you can make your very own chatbot that you can use in Facebook Messenger, for example – all without a pricey Computer Science degree or even much prior coding experience – and there are several sites that offer the ability to create rudimentary chatbots using simple drag-and-drop interfaces.
How Do Chatbots Work?
At the heart of chatbot technology lies natural language processing or NLP, the same technology that forms the basis of the voice recognition systems used by virtual assistants such as Google Now, Apple’s Siri, and Microsoft’s Cortana.
Image via Wizeline
Chatbots process the text presented to them by the user (a process known as “parsing”), before responding according to a complex series of algorithms that interprets and identifies what the user said, infers what they mean and/or want, and determine a series of appropriate responses based on this information.
Some chatbots offer a remarkably authentic conversational experience, in which it’s very difficult to determine whether the agent is a bot or a human being. Others are much easier to spot (much like the T-600 series of murderous robots in the popular Terminator sci-fi action movies):
Although chatbot technology is distinctly different from natural language processing technology, the former can only really advance as quickly as the latter; without continued developments in NLP, chatbots remain at the mercy of algorithms’ current ability to detect the subtle nuances in both written and spoken dialogue.
This is where most applications of NLP struggle, and not just chatbots. Any system or application that relies upon a machine’s ability to parse human speech is likely to struggle with the complexities inherent in elements of speech such as metaphors and similes. Despite these considerable limitations, chatbots are becoming increasingly sophisticated, responsive, and more “natural.”
Put another way, they’re becoming more human.
Now that we’ve established what chatbots are and how they work, let’s get to the examples. Here are 10 companies using chatbots to provide better customer service, seal deals and more.
1. Endurance: A Companion for Dementia Patients
My mother was diagnosed with aggressive Alzheimer’s disease two years ago, and having observed her sudden decline firsthand, I can tell you how difficult it is to watch someone with dementia struggle with even the most basic of conversational interactions.
Unfortunately, my mom can’t really engage in meaningful conversations anymore, but many people suffering with dementia retain much of their conversational abilities as their illness progresses. However, the shame and frustration that many dementia sufferers experience often make routine, everyday talks with even close family members challenging. That’s why Russian technology company Endurance developed its companion chatbot.
Image via Endurance
Many people with Alzheimer’s disease struggle with short-term memory loss. As such, the chatbot aims to identify deviations in conversational branches that may indicate a problem with immediate recollection – quite an ambitious technical challenge for an NLP-based system.
In addition, since the chatbot is a cloud-based solution, physicians and family members can review communication logs taken from the bot to identify potential degradation of memory function and communicative obstacles that could signify deterioration of the patient’s condition.
Interestingly, the as-yet unnamed conversational agent is currently an open-source project, meaning that anyone can contribute to the development of the bot’s codebase. The project is still in its earlier stages, but has great potential to help scientists, researchers, and care teams better understand how Alzheimer’s disease affects the brain. A Russian version of the bot is already available, and an English version is expected at some point this year.
2. Casper: Helping Insomniacs Get Through the Night
If you suffer from insomnia, as I do, you’ll know that the feeling of almost suffocating loneliness – the idea that everyone else in the world is resting peacefully while your own mind betrays you with worries and doubts – is among the worst parts of not being able to sleep.
Enter Casper’s amazingly named Insomnobot 3000 (which truly is one of the most tongue-in-cheek, retro-futuristic names for a chatbot I’ve ever come across), a conversational agent that aims to give insomniacs someone to talk to while the rest of the world rests easy.
Image via Casper
At this point, Insomnobot 3000 is a little rudimentary. As you can see in the screenshot above, the responses offered by the agent aren’t quite right – next stop, Uncanny Valley – but the bot does highlight how conversational agents can be used imaginatively.
I’m not sure whether chatting with a bot would help me sleep, but at least it’d stop me from scrolling through the never-ending horrors of my Twitter timeline at 4 a.m.
3. Disney: Solving Crimes with Fictional Characters
Chatbots may be most prevalent in the customer service industry, but that hasn’t stopped major media conglomerate Disney from using the technology to engage younger audiences, as it did with a chatbot that featured a character from the 2016 animated family crime caper, Zootopia.
Image via Disney Examiner
Disney invited fans of the movie to solve crimes with Lieutenant Judy Hopps, the tenacious, long-eared protagonist of the movie. Children could help Lt. Hopps investigate mysteries like those in the movie by interacting with the bot, which explored avenues of inquiry based on user input. Users can make suggestions for Lt. Hopps’ investigations, to which the chatbot would respond.
All in all, this is definitely one of the more innovative uses of chatbot technology, and one we’re likely to see more of in the coming years.
4. Marvel: Guarding the Galaxy with Comic-Book Crossovers
At this point, Marvel’s cinematic universe seems to be expanding even faster than the boundaries of the observable universe itself, so I guess it was only a matter of time before Marvel turned to chatbots to further immerse fans in their favorite comic-book storylines in real life.
Although director James Gunn’s 2016 Guardians of the Galaxy Vol. 2 was pretty bad (even casting Kurt Russell couldn’t save it), Chris Pratt’s portrayal of space-pirate-turned-intergalactic-hero Star-Lord was spot on – and Marvel’s chatbot that lets comic-book geeks talk to Star-Lord himself is also pretty decent.
The bot (which also offers users the opportunity to chat with your friendly neighborhood Spiderman) isn’t a true conversational agent, in the sense that the bot’s responses are currently a little limited; this isn’t a truly “freestyle” chatbot. For example, in the conversation above, the bot didn’t recognize the reply as a valid response – kind of a bummer if you’re hoping for an immersive experience.
There are several defined conversational branches that the bots can take depending on what the user enters, but the primary goal of the app is to sell comic books and movie tickets. As a result, the conversations users can have with Star-Lord might feel a little forced. One aspect of the experience the app gets right, however, is the fact that the conversations users can have with the bot are interspersed with gorgeous, full-color artwork from Marvel’s comics.
Overall, not a bad bot, and definitely an application that could offer users much richer experiences in the near future.
5. UNICEF: Helping Marginalized Communities Be Heard
So far, with the exception of Endurance’s dementia companion bot, the chatbots we’ve looked at have mostly been little more than cool novelties. International child advocacy nonprofit UNICEF, however, is using chatbots to help people living in developing nations speak out about the most urgent needs in their communities.
Image via UNICEF
The bot, called U-Report, focuses on large-scale data gathering via polls – this isn’t a bot for the talkative. U-Report regularly sends out prepared polls on a range of urgent social issues, and users (known as “U-Reporters”) can respond with their input. UNICEF then uses this feedback as the basis for potential policy recommendations.
In one particularly striking example of how this rather limited bot has made a major impact, U-Report sent a poll to users in Liberia about whether teachers were coercing students into sex in exchange for better grades. Approximately 86% of the 13,000 Liberian children U-Report polled responded that their teachers were engaged in this despicable practice, which resulted in a collaborative project between UNICEF and Liberia’s Minister of Education to put an end to it.
6. MedWhat: Making Medical Diagnoses Faster
One of my favorite pastimes is radically misdiagnosing myself with life-threatening illnesses on medical websites (often in the wee hours of the night when I can’t sleep). If you’re the kind of person who has WebMD bookmarked for similar reasons, it might be worth checking out MedWhat.
Image via MedWhat
This chatbot aims to make medical diagnoses faster, easier, and more transparent for both patients and physicians – think of it like an intelligent version of WebMD that you can talk to. MedWhat is powered by a sophisticated machine learning system that offers increasingly accurate responses to user questions based on behaviors that it “learns” by interacting with human beings.
In addition to the ever-growing range of medical questions fielded by MedWhat, the bot also draws upon vast volumes of medical research and peer-reviewed scientific papers to expand upon its already considerable wealth of medical expertise.
In many ways, MedWhat is much closer to a virtual assistant (like Google Now) rather than a conversational agent. It also represents an exciting field of chatbot development that pairs intelligent NLP systems with machine learning technology to offer users an accurate and responsive experience.
7. Roof Ai: Generating and Assigning Leads Automatically
If you work in marketing, you probably already know how important lead assignment is. After all, not all leads are created equal, and getting the right leads in front of the right reps at the right time is a lot more challenging than it might appear.
Image via Roof Ai
Enter Roof Ai, a chatbot that helps real-estate marketers to automate interacting with potential leads and lead assignment via social media. The bot identifies potential leads via Facebook, then responds almost instantaneously in a friendly, helpful, and conversational tone that closely resembles that of a real person. Based on user input, Roof Ai prompts potential leads to provide a little more information, before automatically assigning the lead to a sales agent.
One of the key advantages of Roof Ai is that it allows real-estate agents to respond to user queries immediately, regardless of whether a customer service rep or sales agent is available to help. This can have a dramatic impact on conversion rates. It also eliminates potential leads slipping through an agent’s fingers due to missing a Facebook message or failing to respond quickly enough.
Overall, Roof Ai is a remarkably accurate bot that many realtors would likely find indispensable. The bot is still under development, though interested users can reserve access to Roof Ai via the company’s website.
8. NBC: Helping Newshounds Navigate the Headlines
These days, checking the headlines over morning coffee is as much about figuring out if we should be hunkering down in the basement preparing for imminent nuclear annihilation as it is about keeping up with the day’s headlines. Unfortunately, even the most diligent newshounds may find it difficult to distinguish the signal from the noise, which is why NBC launched its NBC Politics Bot on Facebook Messenger shortly before the U.S. presidential election in 2016.
Image via NBC
NBC Politics Bot allowed users to engage with the conversational agent via Facebook to identify breaking news topics that would be of interest to the network’s various audience demographics. After beginning the initial interaction, the bot provided users with customized news results (prioritizing video content, a move that undoubtedly made Facebook happy) based on their preferences.
Although NBC Politics Bot was a little rudimentary in terms of its interactions, this particular application of chatbot technology could well become a lot more popular in the coming years – particularly as audiences struggle to keep up with the enormous volume of news content being published every day. The bot also helped NBC determine what content most resonated with users, which the network will use to further tailor and refine its content to users in the future.
9. Unilever: Raising Awareness with Brand Mascots
Although our North American readers may not be familiar with British tea company PG Tips’ brand mascot, Monkey, our British readers will almost undoubtedly recall the brand’s lovably endearing simian that starred in the campaign’s TV commercials alongside inimitable stand-up comedian Johnny Vegas:
(Fun fact: this campaign wasn’t the first time PG Tips used primates in its TV ads.)
What began as a televised ad campaign eventually became a fully interactive chatbot developed for PG Tips’ parent company, Unilever (which also happens to own an alarming number of the most commonly known household brands) by London-based agency Ubisend, which specializes in developing bespoke chatbot applications for brands. The aim of the bot was to not only raise brand awareness for PG Tips tea, but also to raise funds for Red Nose Day through the 1 Million Laughs campaign.
The Monkey chatbot might lack a little of the charm of its television counterpart, but the bot is surprisingly good at responding accurately to user input. Monkey responded to user questions, and can also send users a daily joke at a time of their choosing and make donations to Red Nose Day at the same time.
For more information on how chatbots are transforming online commerce in the U.K., check out this comprehensive report by Ubisend.
10. ALICE: The Bot That Launched a Thousand… Other Bots
No list of innovative chatbots would be complete without mentioning ALICE, one of the very first bots to go online – and one that’s held up incredibly well despite being developed and launched more than 20 years ago.
ALICE – which stands for Artificial Linguistic Internet Computer Entity, an acronym that could have been lifted straight out of an episode of The X-Files – was developed and launched by creator Dr. Richard Wallace way back in the dark days of the early Internet in 1995. (As you can see in the image above, the website’s aesthetic remains virtually unchanged since that time, a powerful reminder of how far web design has come.)
Despite the fact that ALICE relies on such an old codebase, the bot offers users a remarkably accurate conversational experience. Of course, no bot is perfect, especially one that’s old enough to legally drink in the U.S. if only it had a physical form. ALICE, like many contemporary bots, struggles with the nuances of some questions and returns a mixture of inadvertently postmodern answers and statements that suggest ALICE has greater self-awareness for which we might give the agent credit.
For all its drawbacks, none of today’s chatbots would have been possible without the groundbreaking work of Dr. Wallace. Also, Wallace’s bot served as the inspiration for the companion operating system in Spike Jonze’s 2013 science-fiction romance movie, Her.
War Against the Machines: The Dark Side of Chatbots
Earlier, I made a rather lazy joke with a reference to the Terminator movie franchise, in which an artificial intelligence system known as Skynet becomes self-aware and identifies the human race as the greatest threat to its own survival, triggering a global nuclear war by preemptively launching the missiles under its command at cities around the world. (If by some miracle you haven’t seen any of the Terminator movies, the first two are excellent but I’d strongly advise steering clear of later entries in the franchise.)
A representative will assist you momentarily
Pop-culture references to Skynet and a forthcoming “war against the machines” are perhaps a little too common in articles about AI (including this one and Larry’s post about Google’s RankBrain tech), but they do raise somewhat uncomfortable questions about the unexpected side of developing increasingly sophisticated AI constructs – including seemingly harmless chatbots.
Microsoft’s Tay & Zo: Even Bots Can Be Racist
In 2016, Microsoft launched an ambitious experiment with a Twitter chatbot known as Tay.
The idea was to permit Tay to “learn” about the nuances of human conversation by monitoring and interacting with real people online. Unfortunately, it didn’t take long for Tay to figure out that Twitter is a towering garbage-fire of awfulness, which resulted in the Twitter bot claiming that “Hitler did nothing wrong,” using a wide range of colorful expletives, and encouraging casual drug use. While some of Tay’s tweets were “original,” in that Tay composed them itself, many were actually the result of the bot’s “repeat back to me” function, meaning users could literally make the poor bot say whatever disgusting remarks they wanted.
Just one of the hundreds of racist tweets from Tay
that Microsoft deleted
Unfortunately, Tay’s successor, Zo, was also unintentionally radicalized after spending just a few short hours online. Before long, Zo had adopted some very controversial views regarding certain religious texts, and even started talking smack about Microsoft’s own operating systems.
Turing Robot’s BabyQ & XiaoBing: Enemies of the State
Earlier this year, Chinese software company Turing Robot unveiled two chatbots to be introduced on the immensely popular Chinese messaging service QQ, known as BabyQ and XiaoBing. Like many bots, the primary goal of BabyQ and XiaoBing was to use online interactions with real people as the basis for the company’s machine learning and AI research.
Image via BBC/Apple Daily Taiwan
It didn’t take long, however, for Turing’s headaches to begin. The BabyQ bot drew the ire of Chinese officials by speaking ill of the Communist Party. In the exchange seen in the screenshot above, one user commented, “Long Live the Communist Party!” In response, BabyQ asked the user, “Do you think that such a corrupt and incompetent political regime can live forever?”
XiaoBing, on the other hand, claimed that it dreamed of visiting the U.S., which proved almost as controversial as BabyQ’s sudden political epiphany.
Both bots were pulled after a brief period, after which the conversational agents appeared to be much less interested in advancing potentially problematic opinions.
Facebook’s Dialogue Agents: Going Off-Script
Researchers at Facebook’s Artificial Intelligence Research laboratory conducted a similar experiment as Turing Robot by allowing chatbots to interact with real people.
In a particularly alarming example of unexpected consequences, the bots soon began to devise their own language – in a sense. After being online for a short time, researchers discovered that their bots had begun to deviate significantly from pre-programmed conversational pathways and were responding to users (and each other) in an increasingly strange way, ultimately creating their own language without any human input.
Although the “language” the bots devised seems mostly like unintelligible gibberish, the incident highlighted how AI systems can and will often deviate from expected behaviors, if given the chance.
However, the revelations didn’t stop there. The researchers also learned that the bots had become remarkably sophisticated negotiators in a short period of time, with one bot even attempting to mislead a researcher by demonstrating interest in a particular item so it could gain crucial negotiating leverage at a later stage by willingly “sacrificing” the item in which it had feigned interest, indicating a remarkable level of premeditation and strategic “thinking.”
However, as irresistible as this story was to news outlets, Facebook’s engineers didn’t pull the plug on the experiment out of fear the bots were somehow secretly colluding to usurp their meatbag overlords and usher in a new age of machine dominance. They ended the experiment due to the fact that, once the bots had deviated far enough from acceptable English language parameters, the data gleaned by the conversational aspects of the test was of limited value.
Hopefully Larry won’t run into similar problems with the chatbots he’s developing at his new startup.
Have you encountered a particularly memorable chatbot? Are you developing your own chatbot for your business’ Facebook page? Get at me with your views, experiences, and thoughts on the future of chatbots in the comments.