scholarly journals Investigating the user experience of customer service chatbot interaction: a framework for qualitative analysis of chatbot dialogues

2021 ◽  
Vol 6 (1) ◽  
Author(s):  
Asbjørn Følstad ◽  
Cameron Taylor

AbstractThe uptake of chatbots for customer service depends on the user experience. For such chatbots, user experience in particular concerns whether the user is provided relevant answers to their queries and the chatbot interaction brings them closer to resolving their problem. Dialogue data from interactions between users and chatbots represents a potentially valuable source of insight into user experience. However, there is a need for knowledge of how to make use of these data. Motivated by this, we present a framework for qualitative analysis of chatbot dialogues in the customer service domain. The framework has been developed across several studies involving two chatbots for customer service, in collaboration with the chatbot hosts. We present the framework and illustrate its application with insights from three case examples. Through the case findings, we show how the framework may provide insight into key drivers of user experience, including response relevance and dialogue helpfulness (Case 1), insight to drive chatbot improvement in practice (Case 2), and insight of theoretical and practical relevance for understanding chatbot user types and interaction patterns (Case 3). On the basis of the findings, we discuss the strengths and limitations of the framework, its theoretical and practical implications, and directions for future work.

2013 ◽  
Vol 27 (2) ◽  
pp. 109-119 ◽  
Author(s):  
Duncan Simpson ◽  
Craig Wrisberg

Given the relatively little attention devoted to the study of combat sports in the sport psychology literature, the aim of this investigation was to obtain additional insight into the life and world of professional boxers, particularly with respect to their experiences of training for fights. Existential phenomenological interviews were conducted with nine professional British boxers ranging in age from 22 to 42 years. Qualitative analysis of the transcripts revealed a total of 341 meaning units, which were further grouped into higher order themes. A final thematic structure revealed six major dimensions that characterized participants’ training experience: Achieving Potential, Preparing, Sacrificing, Finding Support, Fearing, and Loving/Hating. The results offer a number of insights for sport psychology researchers and practical implications for boxers, trainers, and sport psychology consultants.


2016 ◽  
Vol 117 (5/6) ◽  
pp. 321-328 ◽  
Author(s):  
Gricel Dominguez

Purpose The purpose of this paper is to propose a method for the assessment of library space use and user experience by combining seating studies, surveys and observational data. Design/methodology/approach Seating usage studies (called seating sweeps), technology-assisted face-to-face surveys and observational data were used to assess library space usage and identify user behaviors. Findings Results from the study revealed higher library use than expected and provided insight into user behaviors and patterns. Practical implications The methods and study described aid in raising awareness of user experience within library spaces and provide valuable data for space redesign efforts. Originality/value The study builds upon methods described by Linn (2013) and combines traditional user experience methodologies to gain insight into library space use and user needs.


2019 ◽  
Author(s):  
Xuan Zhao ◽  
Juliana Schroeder ◽  
Shirly Bluvstein ◽  
Alixandra Barasch

Today more than ever before, online writing (e.g., emails, texts, and social media posts) has become a primary means of communication. Because written communication lacks human nonverbal cues (e.g., voice), people frequently struggle to distinguish whether they are interacting with a human or chatbot online. The current research suggests a novel way to humanize writers: typographical errors (“typos”). Across four experiments (N = 1,253) that used ambiguous conversational counterparts (e.g., customer service agents that might be bots), communicators who made and subsequently corrected a typo, rather than making no typo or not correcting a typo, appeared more humanlike. Respondents consequently believed that the communicator was warmer and were more likely to disclose personal information to the communicator. These findings provide insight into when people are willing to share their personal data online. We discuss theoretical implications for humanization and practical implications for Internet privacy and building trust in organizations.


2019 ◽  
Vol 19 (1) ◽  
pp. 10-14
Author(s):  
Ryan Scott ◽  
Malcolm Le Lievre

Purpose The purpose of this paper is to explore insights methodology and technology by using behavioral to create a mind-set change in the way people work, especially in the age of artificial intelligence (AI). Design/methodology/approach The approach is to examine how AI is driving workplace change, introduce the idea that most organizations have untapped analytics, add the idea of what we know future work will look like and look at how greater, data-driven human behavioral insights will help prepare future human-to-human work and inform people’s work with and alongside AI. Findings Human (behavioral) intelligence will be an increasingly crucial part of behaviorally smart organizations, from hiring to placement to adaptation to team building, compliance and more. These human capability insights will, among other things, better prepare people and organizations for changing work roles, including working with and alongside AI and similar tech innovation. Research limitations/implications No doubt researchers across the private, public and nonprofit sectors will want to further study the nexus of human capability, behavioral insights technology and AI, but it is clear that such work is already underway and can prove even more valuable if adopted on a broader, deeper level. Practical implications Much “people data” inside organizations is currently not being harvested. Validated, scalable processes exist to mine that data and leverage it to help organizations of all types and sizes be ready for the future, particularly in regard to the marriage of human capability and AI. Social implications In terms of human capability and AI, individuals, teams, organizations, customers and other stakeholders will all benefit. The investment of time and other resources is minimal, but must include C-suite buy in. Originality/value Much exists on the softer aspects of the marriage of human capability and AI and other workplace advancements. What has been lacking – until now – is a 1) practical, 2) validated and 3) scalable behavioral insights tech form that quantifiably informs how people and AI will work in the future, especially side by side.


Sensors ◽  
2021 ◽  
Vol 21 (12) ◽  
pp. 4127
Author(s):  
Will Farlessyost ◽  
Kelsey-Ryan Grant ◽  
Sara R. Davis ◽  
David Feil-Seifer ◽  
Emily M. Hand

First impressions make up an integral part of our interactions with other humans by providing an instantaneous judgment of the trustworthiness, dominance and attractiveness of an individual prior to engaging in any other form of interaction. Unfortunately, this can lead to unintentional bias in situations that have serious consequences, whether it be in judicial proceedings, career advancement, or politics. The ability to automatically recognize social traits presents a number of highly useful applications: from minimizing bias in social interactions to providing insight into how our own facial attributes are interpreted by others. However, while first impressions are well-studied in the field of psychology, automated methods for predicting social traits are largely non-existent. In this work, we demonstrate the feasibility of two automated approaches—multi-label classification (MLC) and multi-output regression (MOR)—for first impression recognition from faces. We demonstrate that both approaches are able to predict social traits with better than chance accuracy, but there is still significant room for improvement. We evaluate ethical concerns and detail application areas for future work in this direction.


2019 ◽  
Vol 8 (4) ◽  
pp. 17-41
Author(s):  
Maria Panagiotopoulou ◽  
Margarita Kokla ◽  
Anastasia Stratigea

Despite the remarkable interest in smart cities, noticed during the last decade, a consistent comprehension of the concept is not yet fully realized. Various definitions, ranging from exclusively technology-oriented perceptions to broader views, have been introduced, establishing a definitional polyphony and causing lack of semantic interoperability. Empirical evidence witnesses the prevalence of technology-pushed smart city initiatives as well as their failure to meet expectations in several urban domains. When planning “smart,” the relevance of ICT and their applications should be in alignment with spatial and other urban peculiarities and sub-systems' interactions, implying the need for getting deep insight into the city's ontology. The paper focuses on the extension/enrichment of an existing smart city ontology, with concepts and relationships stemming from Mediterranean small and medium-sized cities, in an attempt to outline their main key drivers and their interrelationships and fully grasp the smart city concept in the particular spatial context.


Leonardo ◽  
2014 ◽  
Vol 47 (5) ◽  
pp. 500-501 ◽  
Author(s):  
Mónica Mendes ◽  
Pedro Ângelo ◽  
Nuno Correia

Hug@ree is an interactive installation that provides a bond between urban beings and the forest. It is an ARTiVIS (Arts, Real-Time Video and Interactivity for Sustainability) experience that provides interaction with trees and videos of trees in real-time, raising awareness of the natural environment and how individual action can collectively become so relevant. In this paper, the authors present an overview of the Hug@ree concept, related work, implementation, user experience evaluation and future work.


2016 ◽  
Vol 8 (4) ◽  
pp. 504-510
Author(s):  
Gunjan M. Sanjeev ◽  
Richard Teare

Purpose The paper aims to profile the theme issue of Worldwide Hospitality and Tourism Themes titled “How is the need for innovation being addressed by the Indian hospitality industry?” with reference to the experiences of the theme editor, contributors from the industry and academia and the theme issue outcomes. Design/methodology/approach The paper uses structured questions to enable the theme editor to reflect on the rationale for their theme issue question, the starting-point, the selection of the writing team and material and the editorial process. Findings It highlights recent innovations that have taken place in the Indian hospitality industry especially in the areas of customer service, cost competitiveness, culinary management, revenue management and technology. Practical implications As hotel sector investment in India intensifies, this theme issue will be of interest to hoteliers, policy makers, analysts and others interested in the role that innovation can play in helping to facilitate differentiation between competing hotel products and services. Originality/value There is limited literature available on industry innovations in the Indian context. All the papers in this theme issue were written after several cycles of interaction between academics and practitioners and so they incorporate real–time, relevant and contemporary data.


2014 ◽  
Vol 25 (1) ◽  
pp. 21-37 ◽  
Author(s):  
Amira Galin

Purpose – The purpose of this paper is to obtain insight into court-referred mediation in the Israeli Labor Courts, by analyzing its processes and outcomes, as a function of tactics used by both the disputants and the mediator. Design/methodology/approach – Observation of 103 court-referred mediations, for each of which a detailed process and outcome were documented. Data on disputants' refusal to participate in the mediation was also collected. At the end of each mediation case, disputants were given a questionnaire in which they expressed their satisfaction with the outcome and their evaluation of the mediator's contribution. Findings – A low rate of refusal to participate in court-referred mediation was found. Also, the higher the ratio of soft tactics to pressure tactics employed (by all parties involved) during the process, the higher the rate of agreements. Mediators use significantly more soft tactics than disputants, and are more active in using tactics. The two significant variables that predict the mediation's agreement are the ratio between soft tactics to pressure tactics used by all parties, and mediator contribution to the process. Practical implications – The significant role of soft tactics in the process, outcome, and satisfaction of court-referred mediation may serve as a guideline for disputants and mediators. Originality/value – This unique research, which examines the impact of tactics on court-referred mediation, may provide added and significant theoretical insight into its process and outcome, as well as a better understanding of other “hybrid” (compulsory at the beginning, voluntary at the end) mediations.


Sign in / Sign up

Export Citation Format

Share Document