Proceedings ArticleDOI
Evaluating and Informing the Design of Chatbots
Mohit Jain,Pratyush Kumar,Ramachandra Kota,Shwetak N. Patel +3 more
- pp 895-906
TLDR
A study with 16 first-time chatbot users interacting with eight chatbots over multiple sessions on the Facebook Messenger platform revealed that users preferred chatbots that provided either a 'human-like' natural language conversation ability, or an engaging experience that exploited the benefits of the familiar turn-based messaging interface.Abstract:
Text messaging-based conversational agents (CAs), popularly called chatbots, received significant attention in the last two years. However, chatbots are still in their nascent stage: They have a low penetration rate as 84% of the Internet users have not used a chatbot yet. Hence, understanding the usage patterns of first-time users can potentially inform and guide the design of future chatbots. In this paper, we report the findings of a study with 16 first-time chatbot users interacting with eight chatbots over multiple sessions on the Facebook Messenger platform. Analysis of chat logs and user interviews revealed that users preferred chatbots that provided either a 'human-like' natural language conversation ability, or an engaging experience that exploited the benefits of the familiar turn-based messaging interface. We conclude with implications to evolve the design of chatbots, such as: clarify chatbot capabilities, sustain conversation context, handle dialog failures, and end conversations gracefully.read more
Citations
More filters
Proceedings ArticleDOI
Understanding the Negative Aspects of User Experience in Human-likeness of Voice-based Conversational Agents
TL;DR: This study explored what influences the negative aspects of user experience in human-like VCAs and discovered that the dialogues of the human-likeness outside of the expressed purpose of a VCA and expressions pretending to come from a human identity could lead to negative experiences with VCAs.
Proceedings ArticleDOI
A chatbot response generation system
TL;DR: In this article, the authors present a system that enables chatbot developers to efficiently engage domain experts in the chatbot response generation process, which is a non-trivial endeavor that often depends on high-quality training data and deep domain knowledge.
Proceedings ArticleDOI
An Exploratory Study of Reactions to Bot Comments on GitHub
TL;DR: An observational study of how users react to bot comments on GitHub suggests that some reaction types are not equally distributed across human and bot comments and that a bot's design and purpose influence the types of reactions it receives.
Proceedings ArticleDOI
'A Modern Up-To-Date Laptop' - Vagueness in Natural Language Queries for Product Search
TL;DR: The vagueness of the formulations and their match to retailer-generated content and user-generated product reviews are examined and the potential of user reviews as a source for supporting users with rather vague search intents is revealed.
References
More filters
Book ChapterDOI
Development of NASA-TLX (Task Load Index): Results of Empirical and Theoretical Research
TL;DR: In this article, the results of a multi-year research program to identify the factors associated with variations in subjective workload within and between different types of tasks are reviewed, including task-, behavior-, and subject-related correlates of subjective workload experiences.
Design of Everyday Things
TL;DR: In this article, the authors reveal how smart design is the new competitive frontier, and why some products satisfy customers while others only frustrate them, and how to choose the ones that satisfy customers.
Book
The Design of Everyday Things
TL;DR: Revealing how smart design is the new competitive frontier, this innovative book is a powerful primer on how--and why--some products satisfy customers while others only frustrate them.
Journal ArticleDOI
ELIZA — a computer program for the study of natural language communication between man and machine
TL;DR: A discussion of some psychological issues relevant to the ELIZA approach as well as of future developments concludes the paper.
Book
Embodied conversational agents
TL;DR: Embodied conversational agents as mentioned in this paper are computer-generated cartoonlike characters that demonstrate many of the same properties as humans in face-to-face conversation, including the ability to produce and respond to verbal and nonverbal communication.
Related Papers (5)
"Like Having a Really Bad PA": The Gulf between User Expectation and Experience of Conversational Agents
Ewa Luger,Abigail Sellen +1 more