Category: Chatbot

Why chatbots suck (and why natural languages are hard)

Why chatbots suck (and why natural languages are hard)

We have previously touched on how to make your chatbot a success, top chatbots and  how many chatbots fail (a list that is constantly growing). Today, we will show you why it is hard for chatbots to hold human-like conversations, and why dealing with natural languages is hard.

Natural Languages are old and quite irregular

It is important to define the natural language concept as we begin. Natural languages are the product of thousands of years of speech patterns, evolved to fit the needs of a particular community at a particular time. They are very fluid, as there can be a lot of change over time (think Victorian English). Although we may attempt to catalogue the different rules of natural languages, they eventually get replaced by new rules, and in some cases, they diverge so much that the new set of rules essentially become a new language. Read more

Why publicly trained chatbots are not always a good idea

Why publicly trained chatbots are not always a good idea

We have previously touched on how to make your chatbot a success, and also, how many chatbots fail (a list that is constantly growing). Today, we will show you how seemingly harmless chatbots learn to make racist and sexist comments, and what you can do to avoid that.

Background

Chatbots used to be, as described by our previous posts, handcoded FAQ services, presented in a conversational way. They were highly rigid in terms of what they could understand and what they could achieve. However, due to their simplicity, they would only say what you deemed appropriate. They would not learn inappropriate responses, because they could not learn. Read more

Top chatbot success stories

Top chatbot success stories

Though hype about chatbots is increasing, chatbot failure stories continue to get more visibility as well. From Microsoft to Communist Party of China, we have listed examples showing that no one is immune to suffering from chatbot failures. However, success stories are rare and ambitious designers of conversational interfaces need to study them because for every hundreds of failures, there is only a few success stories.

Here we cover all text based bots. While some bots like, XiaoIce, respond to your commands, other bots like Facebook M listen in to your conversations and offer suggestions. Bots are a relatively new user interface and success is elusive so we wanted to be broad in our scope. Read more

All 22 chatbot applications areas for brands

All 22 chatbot applications areas for brands

Chatbots have become the buzzword du jour but brands with successful chatbots are rare. We are more likely to find pages full of chatbot failure stories. Here we outline the successful areas of chatbot application.

First of all, we are talking about chatbots in a platform-agnostic manner. Whether they are on your website or on Facebook Messenger or on some other platform, chatbots are essentially conversational interfaces. We can divide up use cases for conversational interfaces into two categories: reactive and proactive. Read more

Chatbots will change the world, do not get left behind

Chatbots will change the world, do not get left behind

Humans are good at talking and listening. They are one of the first things we learn and the sophistication of language sets us apart from other animals. Therefore it is no surprise that people are excited about chatbots as they offer a language interface to the digital world.

Benefits

Chatbots have numerous possible benefits in diverse areas:

  • Marketing: Messaging has a larger social base than all other areas of social media. Brands have been experimenting heavily with chatbots since the launch of Facebook Messenger Platform and discovered numerous use cases engaging their customers daily. We compiled all chatbot applications brands can build.
  • Customer service: Customer service wages in the US is $100+ Billion p.a. Even small savings in wages can create massive benefits for B2C enterprises where customer reps spend a significant portion of their time answering simple questions.
  • Inside sales: Conversion rate is 10x more for leads that are contacted within 5 minutes according to an insidesales.com study. Achieving that with a human team takes a large team and low utilization. Bots can achieve such speeds at low cost.
  • Healthcare: Chatbots have significant potential in healthcare but regulatory challenges are likely to delay their adoption
    • Prescription reminders: Bots like Florence provide reminders for prescriptions set by patients. This could be quite a suitable service for hospitals or pharmacies.
    • Diagnostic-aid: Users tell Baidu Melody about their symptoms after which Melody asks several questions to produce a preliminary diagnostic.
    • Theraphy: There are already numerous chatbot companies such as X2AI, Therachat or Woebot helping people manage their mental health

    Risks

    Chatbots have significant potential but that does not make them easy to implement. We explained in our detailed blog post on chatbot failure how discoverability, customer expectations and technological limitations have limited traction for numerous bots. And even those who achieved traction experienced a number of issues: Read more