Why Would Someone Use A Chatbot?
And What Constitutes A Conversation Between Two People?
Introduction
And why is it so hard to imitate?
Chatbots are machine agents which serve customers via a natural language interface…
This interface can be text or speech. This machine agent needs to be hosted somewhere. Currently the most popular destination is mobile messaging applications.
This is also where we spend most of our time, hence we have become accustomed to asynchronous multi-threaded communication. And in many instances prefer it that way. Hence this is also where we prefer to interact with these conversational interfaces.
Added to this, access to Natural Language Understanding and Processing tools are unprecedented. There are numbers opensource platforms which can be used to create a conversational interface.
Humans Speak Differently To Chatbots
A study comparing human-human conversations to human-chatbot found the following (Hill et al.):
- Human-Chatbot interactions tend to last longer than human-human interactions between strangers.
- Messages are shorter with less complicated vocabulary.
- Increase of Profanity.
This poses a real challenge in instances where designers are studying human-human conversations in designing the conversational interface. Any preparation and design is better than nothing, but prepare for a number of anomalies.
Apart from convenience, what else motivates people to use chatbots? A study found (Corti & Gillespie) that where chatbots were perceived as humans, users made an effort to repair misunderstandings. When users realize the interface is automated, this changed.
A recent study (Xu et al.) found that 40% of chatbot conversations are emotional rather that product or service related. Should a chatbot not be able to related to customer emotionally, a huge opportunity is missed. Small talk must be catered for in the design and implementation.
Productivity Is Important
Users want quick and consistent feedback when in need of information and general assistance. This points to the implementation of chatbots in the customer service domain. Users are more interested in immediate communication domains.
Information is important to customers, but two elements which are paramount are immediacy and interactivity. The quick/instant response of a chatbot is a huge draw card for productivity minded cultures.
The Novelty Factor
Novelty is a big factor, and as you will see in the discussion below regarding sequence expansion, user screening of the chatbot is very relevant.
During the screening phase of the conversation, the user is checking the capability of the chatbot, understanding the unseen conversational landscape of the conversational interface.
The Essence Of Conversation
In a conversation two humans are naturally taking turns in exchanging information while organizing the conversational dialog turns sequentially.
The key elements your chatbot must make provision for are:
- Recognize Common Conversational Actions
- Persist the Sequential Context; Across Previous Turns, Into Future Turns
Sequences
A sequence is the smallest unit of a human conversation. There are two types of sequences:
- Adjacent Pair Sequences
- Storytelling Sequences
Adjacent Pair Sequences refers to social action pairs, which is relatively easy to cater for. These include, Greeting & Greeting, Good Bye & Good Bye, Question & Answer, Offer & Accept/Reject, Request & Grant/Deny, Invite, Accept/Decline etc.
When the first part of the pair is initiated, it creates an expectation for the second part to be fulfilled and often an obligation.
The initiation of an Adjacent Pair Sequence constrains the user in their response, but it should not determine it.
This should be seen as a collaborative effort between the user and the chatbot.
When designing a conversational interface, don’t restrict the user to the expected adjacent pair.
This will most probably lead to fallback proliferation; a snare most chatbot designers step into.
Here is the challenge, Adjacent Pair Sequences should be expandable.
Think of expansion as nested turns.
An expansion can bee seen as a sequence on a sequence. Base adjacent pairs stand on their own; while expansions do not.
They are dependent on the base. Should a chatbot design not allow for expansion, continuity is lost in the conversation.
Have a look at this example of simple expansion:
Here thanks is responsive to something which happened earlier…it actually closes a prior sequence.
Sequence expansion types are screening, repeat, base, elicit and close.
Expansion can be seen as the elasticity of your conversational design, to what extend can the conversation be expanded by the user while context and logic is maintained in the conversation.
The expansion element I find most interesting is screening. That is the common process of initial exploration of the chatbot by the user. It is crucial in engaging the user and ensuring the intent of the user is accurately determined.
Storytelling Sequence is an elongated conversation with a set of numerous instructions. The user is guided along the journey from instruction to instruction. The next instruction can be given by the chatbot after a user pause, or confirmation by the user.
The storytelling sequence must not be too rigid; it should allow for digression, breakout to another journey and navigation upwards and downwards.
Capability Check
During the screening phase of the conversation, the user is checking the capability of the chatbot, understanding the unseen conversational landscape of the conversational interface.
Irrelevance detection is important, and the chatbot must be able to see if user requests are irrelevant to the designed domain and advise the user accordingly.
Conclusion
Much focus is given to entity extraction, intent recognition and natural language processing; but sequential context is an important design consideration.
