Chatbots Are Still Missing the Human Element of Conversation
The development of conversational agents or chatbots that can engage in empathetic conversation with people has long been a goal of AI. But the reality is still different, according to Strategy analytics.
The majority of current mainstream chatbots, used to increase customer engagement and reduce costs, are inflexible, prescriptive and unable to work outside of their scope. The inability to express emotion, attitude, or opinion, especially if the chatbot cannot solve a customer’s problem, leads to user frustration and cessation of use.
“Research has shown that a customer’s emotions have significant influence on their satisfaction with a service chatbot. Consumer reaction to error is significantly influenced by perceived competence and trust. By designing systems that are user-centric and content driven, in addition to preventing recognized non-progress events from occurring, this will provide numerous benefits to the businesses using them," said Diane O'Neill, co-author of the study.
Despite some successes in the development of empathetic chatbots, human-level intelligence is still not fully understood. Building intelligent social chatbots that can understand humans and their surrounding world requires further advances in AI particularly as their use diversifies into critical health related services such as mental health support systems.