Abstract: Chatbots are one class of intelligent, conversational software agents activated by natural language input (which can be in the form of text, voice, or both). They provide conversational output in response, and if commanded, can sometimes also execute tasks. Although chatbot technologies have existed since the 1960’s and have influenced user interface development in games since the early 1980’s, chatbots are now easier to train and implement. This is due to plentiful open source code, widely available development platforms, and implementation options. Naturally, all this needs to go through a quality check tunnel too before Go-live. Chatbots are indeed revolutionizing the interaction between organizations and individuals, but one thing still lacks, the industry still hasn’t been able to achieve is standardizing the chatbot testing. This blog presents a literature review of quality issues and attributes of Chatbots. First of all I would like to deep-dive in types of chatbots.
Choosing a Chatbot:
Research says that almost 85% of global executives believe that AI will allow their companies to obtain or sustain a competitive advantage and going to a play much larger role in enhancing the organizational work productivity. When it comes to the many applications of AI technologies, chatbots are the most popular and are currently making the biggest noise. I would like to categories Chatbots in mainly 2 big categories. In simple one can say, there are two main ways in which a chatbot can be built — with and without machine learning.
Sequential or Scripted Chatbots:
These bots are pre-defined with a conversational flow and so when a user throws a query, the bot responds with a pre-defined script from the library. These are the kind of chatbots that follow a conversation flow defined by the maker. The chatbot does not and cannot go out of this scope, meaning a user cannot ask questions like ‘how are you?’, ‘what’s the weather like today’. It’s more like a question and answer session, where only the bot will be allowed to ask questions. Sequential chatbots are generally useful where we want to automate tasks like logging feedback, capturing leads etc. It does not have any AI capabilities to understand the user.
Intelligent AI-powered chatbots:
Intelligent bots use Natural Language Processing to answer user queries. The intelligent bots act smart and respond back with most appropriate answer possible. These contain AI technology and Natural Language Processing algorithms, which are able to understand what the user trying to say and understand the intent of it. Having AI, it is smart enough to understand the spelling mistakes of the users, and understand the actual question of the user if poorly written. Such bots need to be trained regularly based on either previous conversations or the questions which are bound to be most frequently asked. Enabling languages other than English can also be done using AI & Machine Learning, although it is a challenge.
Bots can be further subcategorized into the following:
In my next blog-update, I would like to investigate the applications of the Bots. Stay tuned!