Can You be More Social? Injecting Politeness and Positivity into Task-Oriented Conversational Agents

TL;DR

This paper explores how incorporating social language like politeness and positivity into task-oriented conversational agents can improve user engagement and task success, using statistical analysis and deep learning models.

Contribution

It introduces a novel deep learning model that injects social language into agent responses while maintaining task content, enhancing social appropriateness.

Findings

Social language correlates with higher user responsiveness and task completion.

The proposed model effectively generates socially appropriate responses without losing content accuracy.

Human and automatic evaluations confirm improved social behavior in generated responses.

Abstract

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.