Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
41 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
41 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

How should my chatbot interact? A survey on human-chatbot interaction design (1904.02743v2)

Published 4 Apr 2019 in cs.HC
How should my chatbot interact? A survey on human-chatbot interaction design

Abstract: Chatbots' growing popularity has brought new challenges to HCI, having changed the patterns of human interactions with computers. The increasing need to approximate conversational interaction styles raises expectations for chatbots to present social behaviors that are habitual in human-human communication. In this survey, we argue that chatbots should be enriched with social characteristics that cohere with users' expectations, ultimately avoiding frustration and dissatisfaction. We bring together the literature on disembodied, text-based chatbots to derive a conceptual model of social characteristics for chatbots. We analyzed 56 papers from various domains to understand how social characteristics can benefit human-chatbot interactions and identify the challenges and strategies to designing them. Additionally, we discussed how characteristics may influence one another. Our results provide relevant opportunities to both researchers and designers to advance human-chatbot interactions.

Surveying Social Characteristics in Human-Chatbot Interaction Design

The paper "How should my chatbot interact? A survey on social characteristics in human-chatbot interaction design" by Ana Paula Chaves and Marco Aurelio Gerosa provides a comprehensive survey of the various social characteristics that can enhance the interaction between humans and chatbots. The authors synthesize findings from 56 studies, presenting a conceptual model that categorizes social characteristics into three primary domains: conversational intelligence, social intelligence, and personification. This work is pivotal in understanding how chatbots can be designed to meet user expectations for social interaction, thereby minimizing frustration and dissatisfaction.

Key Concepts and Findings

  1. Conversational Intelligence: This domain focuses on characteristics that enhance a chatbot's role in efficiently managing conversations. The key features include:
    • Proactivity: A proactive chatbot can engage users by initiating exchanges, suggesting new topics, or providing additional information. The literature identifies proactivity as beneficial for maintaining user interest and enhancing conversation productivity.
    • Conscientiousness: This reflects a chatbot's ability to demonstrate attentiveness to user inputs and the conversational context. Conscientiousness ensures coherence and relevance in responses, reducing user frustration.
    • Communicability: Effective communicability allows chatbots to convey their capabilities and limitations to users, addressing discrepancies in user expectations and reducing abandonment.
  2. Social Intelligence: Social intelligence encompasses chatbots' ability to adhere to social norms and exhibit empathetic behaviors.
    • Damage Control: This characteristic is crucial in handling conflicts and failures gracefully, preventing negative escalation in interactions due to user testing or harassment.
    • Emotional Intelligence: Though chatbots do not experience emotions, simulating emotional intelligence increases user engagement and satisfaction by fostering a sense of understanding and belonging.
    • Manners and Moral Agency: Chatbots should demonstrate politeness and adhere to social ethics to avoid reinforcing negative stereotypes and to create a positive user experience.
  3. Personification: Personification involves attributing human-like characteristics to chatbots, which can enhance interaction by introducing elements of identity and personality.
    • Identity and Personality: These attributes make chatbots relatable and consistent in their interactions. They can enhance user engagement by providing a predictable and enjoyable interaction experience.

Implications and Future Directions

The survey underscores the importance of integrating social characteristics into chatbot design to create more natural and satisfying human-chatbot interactions. By drawing parallels with human social interaction components, the paper provides a framework that aids researchers and designers in identifying relevant characteristics for specific contexts. The findings suggest several areas for further research, including:

  • The development of more sophisticated strategies for manifesting emotional intelligence and moral agency in chatbots.
  • Evaluating the effectiveness of various social characteristics in different domains and interaction contexts.
  • Exploring the intersections of social characteristics, such as how manners can facilitate conscientious communication or how emotional intelligence can enhance communicability.

The prescribed characteristics and their interrelationships provide a foundation for creating chatbots that are not only functionally proficient but also socially adept. This survey acts as a valuable resource for designing chatbots that can meet the nuanced demands of human-social interaction, ultimately impacting the broader field of Human-Computer Interaction (HCI) and paving the way for more sophisticated and user-aligned conversational agents.

User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (2)
  1. Ana Paula Chaves (11 papers)
  2. Marco Aurelio Gerosa (7 papers)
Citations (332)