• Corpus ID: 77394426

Building Real-World Chatbot Interviewers: Lessons from a Wizard-of-Oz Field Study

@inproceedings{Zhou2019BuildingRC,
  title={Building Real-World Chatbot Interviewers: Lessons from a Wizard-of-Oz Field Study},
  author={Michelle X. Zhou and Carolyn Wang and Gloria Mark and Huahai Yang and Kevin Xu},
  booktitle={IUI Workshops},
  year={2019}
}
We present a Wizard-of-Oz field study, where a humanassisted chatbot interviewed 53 actual job applicants each in a 30-minute, text-based conversation. A detailed analysis of the chat transcripts and user feedback revealed users’ likes and dislikes of the chatbot, as well as the patterns of their interaction with the chatbot. Our findings yield a set of practical design suggestions for building effective, realworld chatbot interviewers that appear intelligent with even limited NLP or… 

Figures and Tables from this paper

Wizard-of-Oz Testing as an Instrument for Chatbot Development An experimental Pre-study for Setting up a Recruiting Chatbot Prototype

This study investigated chatbots in recruiting, a field within human resource management that is characterized by a high proportion of repetitive and standardized tasks, and applies a Wizard-of-Oz approach in which a basic dialog concept is tested in a very early phase of the project, simulating the chatbot functionality by a human operator.

Preliminary Findings of using Chat-bots as a Course FAQ Tool

The preliminary findings of an admin-updatable Dialogflow-based chat-bot deployed on an instant messaging platform (Telegram) to handle all course queries shows that chat-bots are a viable tool to disseminate information to students and it is possible to build such an agent with a limited set of question.

Conversational Interfaces for Explainable AI: A Human-Centred Approach

Conversational Interfaces are proposed to be the perfect setting to enable the user to enquire information and explanation directly from an intelligent agent, and both requirements of users and obstacles in the implementation of protocols for interacting agents are disclosed.

A Psychologist Chatbot Developing Experience

A quality of experience framework is applied to explore the factors that impact stakeholders and influence design priories and the conclusions regarding the leveraging cloud platforms and the technical customisation required for non-standard chatbot use cases are presented.

Mapping the Design Space of Human-AI Interaction in Text Summarization

This work conducts a systematic literature review of 70 papers, developing a taxonomy of five interactions in AI-assisted text generation and relevant design dimensions, and designed text summarization prototypes for each interaction.

A Paradigm Shift from “Human Writing” to “Machine Generation” in Personality Test Development: an Application of State-of-the-Art Natural Language Processing

Natural language processing (NLP) techniques have become increasingly popular in areas of psychological assessment. Recently, researchers have sought to use NLP techniques for automatic item

Lehtori Moti

Ammattikorkeakoulussa toteutetun opetuskokeilun perusteella opetusbotit saattavat tarjota yhden mahdollisuuden parantaa opetuksen laatua ja vähentää opettajan kokemaa työkuormitusta. Opetusbotti on

How to establish a digital therapeutic alliance between chatbots and users: The role of relational cues

: To address the issue of users’ poor engagement, researchers have recently integrated the therapeutic alliance (TA) concept with Internet-based self-help interventions (ISIs). Digital therapeutic

References

SHOWING 1-10 OF 25 REFERENCES

Embodied Conversational Agent-Based Kiosk for Automated Interviewing

An automated kiosk that uses embodied intelligent agents to interview individuals and detect changes in arousal, behavior, and cognitive effort by using psychophysiological information systems was created and smiling agents were perceived as more likable than neutral demeanor agents.

SimSensei kiosk: a virtual human interviewer for healthcare decision support

SimSensei Kiosk is presented, an implemented virtual human interviewer designed to create an engaging face-to-face interaction where the user feels comfortable talking and sharing information and development of a fully automatic virtual interviewer able to engage users in 15-25 minute interactions.

Active Listening in Peer Interviews: The Influence of Message Paraphrasing on Perceptions of Listening Skill

Perhaps no communication skill is identified as regularly as active listening in training programs across a variety of disciplines and activities. Yet little empirical research has examined specific

Personalization in HRI: A longitudinal field experiment

The results show that, as compared with the social service alone, adding personalized service improved rapport, cooperation, and engagement with the robot during service encounters.

KnowMe and ShareMe: understanding automatically discovered personality traits from social media and user sharing preferences

The findings show there is a potential feasibility of automatically deriving one's personality traits from social media with various factors impacting the accuracy of models, and their implications for designing a new generation of privacy-preserving, hyper-personalized systems.

The effect of interviewer experience, attitudes, personality and skills on respondent co-operation with face-to-face surveys

This paper examines the role of interviewers' experience, attitudes, personality traits and inter-personal skills in determining survey co-operation, conditional on contact. We take the perspective

Multimodal interaction: A review

  • M. Turk
  • Psychology
    Pattern Recognit. Lett.
  • 2014

The qualitative research interview

This work examines less structured interview strategies in which the person interviewed is more a participant in meaning making than a conduit from which information is retrieved.