Applied AI & AI in business /

The chatbot dilemma

November 13
  • Liliana Lindberg
    Liliana LindbergSolutions Architect

Do you really need a chatbot? At Peltarion we receive numerous questions regarding chatbots and conversational interfaces. They can be implemented in many different ways depending on what the chatbot should do. Take a look at natural language processing (NLP) tasks as text classification, sentiment analysis, semantic similarity search among others as they may be more suitable for the particular problem you are solving.

Here we have put together a quick checklist to look if your current need for conversational interaction is pointing more towards a more discrete behind-the-scenes AI-based solution or a chatbot. 

Is your challenge either of the following?

  • Coping with the increasing demand for customer support or customer service
  • Answering frequently asked questions in a more efficient way
  • Finding the most human-like bot because your users prefer to talk to people
  • Taking action on some cases but not all of them that concern the business operations 

It is worth considering the following alternatives, as you might be able to solve your challenge without using a bot.

  1. Increasing demand for customer support/service: If your customer service department is constantly growing to cope with demand, you can easily automate the most simple and repetitive tasks. One way is to use text classification on incoming requests. This not only reduces the response times to your customers but also will free-up your agent’s time and allow them to focus on the most complex and difficult inquiries.
  2. Intelligent FAQ answering: Chatbots sometimes are not the answer to overlooking the importance of an effective search. Powerful semantic search, leveraged by the latest natural language processing (NLP) models such as BERT, goes beyond keyword search and finds answers to the query solely based on its meaning. The advantage is that once the model has been created, it can keep improving with minimal effort compared to the effort needed on extending the intends/actions on traditional chatbots frameworks.
  3. The most human-like bots are humans: If I get the option to interact with a real person or a bot I undoubtedly will go for the person. If your users feel the same way, then empower your user-facing staff not only by automating the simple and repetitive tasks—as described in point 1 above—but also by providing them with the tools to help them retrieve information much faster and redirecting to them only those inquiries that are part of their area of expertise. Methods such as text classification, sentiment analysis to prioritize inquiries and similarity search can be used here. In this way, you are not only improving your first and second line support but also maintaining a very close and personalized relationship with your customer base.
  4. Focused on some cases but not all: Once the chatbot is out it becomes an extension of your company and your brand. The range of possible inputs becomes endless, hence making sure you have the correct response to all possible intends expressed by your users is paramount. Minimize the possibility to generate chatbot frustration that can cost you a loyal customer by embedding a solution only in the areas of your organization that need it most. 
  5. A hybrid solution: If a conversational interaction solution fits your needs but lacks some functionality chances are that a hybrid solution may be the most appropriate. For example, NLP could help to make sense of all the domain of the dialog space for chatbot configuration, adding multilingual support missing on some frameworks or guide the customer towards a product or service.  Backend services can provide added functionality while maintaining the existing user interaction. 

In short, it all comes down to the problem you are trying to solve. From an NLP perspective here are the most common ways to apply AI to improve substantially your business discreetly from behind the scenes:

  • Semantic similarity: a very powerful NLP task that has improved extensively in the past couple of years and has revolutionized how systems can interpret text in a semantic way not possible before. Very suitable for smart search, question answering tasks and effective retrieval of information. Read our customer stories speeding up the RFP process using data from past bids and AI + market research as a path to smarter, faster & bolder decisions for some inspiration.
  • Classify text in one or multiple languages simultaneously: Automatically assigned predefined categories to any inbound communication, independent of the language used. For example: tag customers requests by issue type, classify inquiries by importance (critical, urgent, not urgent, etc), identify products or services and redirect to the responsible team. Try out our tutorial classify customer complaints to see it in action.
  • Sentiment analysis Identify the opinion or emotional tone of a given text as negative, neutral or positive as a means to extract brand perception, classify claims urgency or differentiate intent towards a product or service. Our tutorial movie review feelings provides a good example.

Contact us at contact@peltarion.com and we will guide you through. Or why not start exploring the platform right away to see what you think!

  • Liliana Lindberg

    Liliana Lindberg

    Solutions Architect

    Liliana works as a solutions architect at Peltarion guiding customers to solve business challenges by successfully using AI and deep learning. She is passionate about emerging technologies and before joining Peltarion she worked for a number of years at Google as a customer engineer for the Google Cloud Platform team. Her academic background includes BSc. Systems and Computing Engineering; MSc. in Geographical Information Systems from the University of Calgary, Canada; and a Master’s level Business Leadership Specialization from Duke University.

02/ More on data science here