Can You be More Social? Injecting Politeness and Positivity into Task-Oriented Conversational Agents
This research addresses the problem of improving user engagement and task completion for goal-oriented conversational agents by making them more socially appropriate.
This paper investigates the impact of social language in goal-oriented conversational agents, finding that politeness and positivity from human agents correlate with increased user responsiveness and task completion. They developed a sequence-to-sequence deep learning model, extended with social language understanding, that can inject social language into agent responses while preserving content.
Goal-oriented conversational agents are becoming prevalent in our daily lives. For these systems to engage users and achieve their goals, they need to exhibit appropriate social behavior as well as provide informative replies that guide users through tasks. The first component of the research in this paper applies statistical modeling techniques to understand conversations between users and human agents for customer service. Analyses show that social language used by human agents is associated with greater users' responsiveness and task completion. The second component of the research is the construction of a conversational agent model capable of injecting social language into an agent's responses while still preserving content. The model uses a sequence-to-sequence deep learning architecture, extended with a social language understanding element. Evaluation in terms of content preservation and social language level using both human judgment and automatic linguistic measures shows that the model can generate responses that enable agents to address users' issues in a more socially appropriate way.