Notice: Function _load_textdomain_just_in_time was called incorrectly. Translation loading for the all-in-one-seo-pack domain was triggered too early. This is usually an indicator for some code in the plugin or theme running too early. Translations should be loaded at the init action or later. Please see Debugging in WordPress for more information. (This message was added in version 6.7.0.) in /home/planetac/desa.planetachatbot.com/wp-includes/functions.php on line 6114

Notice: Function _load_textdomain_just_in_time was called incorrectly. Translation loading for the wp-user-avatar domain was triggered too early. This is usually an indicator for some code in the plugin or theme running too early. Translations should be loaded at the init action or later. Please see Debugging in WordPress for more information. (This message was added in version 6.7.0.) in /home/planetac/desa.planetachatbot.com/wp-includes/functions.php on line 6114
5 Artículos sobre Inteligencia Artificial Conversacional que he leído en septiembre - Planeta Chatbot

En una entrevista reciente, otra vez me preguntaron sobre qué contenidos leo normalmente sobre Inteligencia Artificial Conversacional para mantenerme al día. Como es una pregunta que he recibido muchas veces, he decidido empezar a compartir las lecturas más relevantes de cada mesy aquellos contenidos que, en general, se han quedado fijados en mi mente entre el denso flujo de información que circula sobre el tema.

Los temas principales de septiembre han sido las perspectivas éticas en las conversaciones humano-máquina, la multimodalidad en la interacción a través de chat, los estilos de comunicación de los usuarios a la hora de interactuar con automatizaciones y las percepciones y las motivacionesde los usuarios para emplear chats y asistentes de voz.

El último artículo de la lista de este mes es mi propia producción para el blog de FlixMobility Tech. Es esta entrada, titulada, Conversational UX Design: Creating Persistent Conversations, reflexiono sobre la necesidad de prestar más atención en el diseño conversacional a los aspectos estructurales e interactivos de la conversación y a la creación de una intersubjetividad entre el usuario y el sistema, para que la experiencia sea beneficiosa para ambas partes.

Espero que los artículos resulten de vuestro interés y espero que octubre sea tan fructífero como septiembre en términos de lectura 🙂

Tabla de contenidos

A conversation-based perspective for shaping ethical human–machine interactions: The particular challenge of chatbots

A conversation-based perspective for shaping ethical human-machine interactions: The particular…

Grazia Murtarelli, Ph.D. is Assistant Professor of Corporate Communication at Università IULM in Milan (Italy), where…

 

Abstract

The use of chatbots to manage online interactions with consumers poses additional ethical challenges linked to the use of artificial intelligence (AI) applications and opens up new ethical avenues for investigation. A literature analysis identifies a research gap regarding the ethical challenges related to chatbots as non-moral and non-independent agents managing non-real conversations with consumers. It raises concerns about the ethical implications related to the progressive automation of online conversational processes and their integration with AI. The conversational approach has been explored in the organisational and management literature, which has analysed the features and roles of conversations in managing interactions ethically. This study aims to discuss conceptually the ethical challenges related to chatbots within the marketplace by integrating the current chatbot-based literature with that on conversation management studies. A new conceptual model is proposed which embraces ethical considerations in the future development of chatbots.

ODO: Design of Multimodal Chatbot for an Experiential Media System

ODO: Design of Multimodal Chatbot for an Experiential Media System

This paper presents the design of a multimodal chatbot for use in an interactive theater performance. This chatbot has…

Abstract

This paper presents the design of a multimodal chatbot for use in an interactive theater performance. This chatbot has an architecture consisting of vision and natural language processing capabilities, as well as embodiment in a non-anthropomorphic movable LED array set in a stage. Designed for interaction with up to five users at a time, the system can perform tasks including face detection and emotion classification, tracking of crowd movement through mobile phones, and real-time conversation to guide users through a nonlinear story and interactive games. The final prototype, named ODO, is a tangible embodiment of a distributed multimedia system that solves several technical challenges to provide users with a unique experience through novel interaction.

A Case Study of User Communication Styles with Customer Service Agents versus Intelligent Virtual Agents

A Case Study of User Communication Styles with Customer Service Agents versus Intelligent Virtual…

Abstract We investigate differences in user communication with live chat agents versus a commercial Intelligent Virtual…

Abstract

We investigate differences in user communication with live chat agents versus a commercial Intelligent Virtual Agent (IVA). This case study compares the two types of interactions in the same domain for the same company filling the same purposes. We compared 16,794 human-to-human conversations and 27,674 conversations with the IVA. Of those IVA conversations, 8,324 escalated to human live chat agents. We then investigated how human-to-human communication strategies change when users first communicate with an IVA in the same conversation thread. We measured quantity, quality, and diversity of language, and analyzed complexity using numerous features.

We find that while the complexity of language did not significantly change between modes, the quantity and some quality metrics did vary significantly. This fair comparison provides unique insight into how humans interact with commercial IVAs and how IVA and chatbot designers might better curate training data when automating customer service tasks.

(Non-)Interacting with conversational agents: perceptions and motivations of using chatbots and voice assistants

(Non-)Interacting with conversational agents | Proceedings of the Conference on Mensch und Computer

Conversational agents (CAs) such as Siri, Alexa, and Google Assistant are increasingly penetrating everyday life. From…

 

Abstract

Conversational agents (CAs) such as Siri, Alexa, and Google Assistant are increasingly penetrating everyday life. From a Human-Computer Interaction (HCI) perspective, designing CAs that appropriately support the way they are used within daily life is still challenging. While initial design guidelines for human-AI interaction exist, we still know little about how users actually perceive CAs within their daily lives and what aspects motivate their usage of such tools. Within our research, we therefore conducted an interview study with 29 participants to uncover daily positive and negative experiences with CAs. By revealing how users currently perceive CAs, we identify quality criteria that could inform their future design. By evaluating these criteria with respect to existing research discourses about user experience (UX) guidelines for CAs, we contribute to the field by extending these guidelines from an end-user’s perspective.

Conversational UX Design: Creating Persistent Conversations

FlixTech Blog – All about FlixBus’ IT journeys

Anyone who interacts on a daily basis with virtual assistants and chatbots will know that one of the main…

FlixTech Blog – All about FlixBus’ IT journeysAnyone who interacts on a daily basis with virtual assistants and chatbots will know that one of the main…flix.tech

Resumen

¿Por qué es tan difícil permitir que los sistemas conversen con nosotros de forma adecuada, especialmente desde que el Procesamiento del Lenguaje Natural ha llevado a tantos avances en la capacidad de las computadoras para procesar, analizar y dar sentido a una gran cantidad de datos de lenguaje natural? La respuesta es que hay algo más allá del lenguaje que debe ser modelado en una conversación para mantener una interacción persistente con una máquina: 1) la naturaleza estructurada de la conversación humana, y 2) la necesidad de establecer y mantener un entendimiento mutuo con el sistema incluso antes de iniciar una conversación con él.

Recibe este contenido directamente por email suscribiéndote a mi lista de correo.

¡Feliz octubre!

Por Carmen Martínez

La Dra. Carmen Martinez es Analista de Conversación y Etnógrafa de Comunicación que trabaja en Inteligencia Artificial Conversacional en FlixBus. Como experta en conversaciones de persona a persona, contribuye a un equipo multidisciplinario automatizando las interacciones de servicio al cliente, modelando conversaciones de persona a máquina basadas en texto y voz, y desarrollando soluciones visuales para agentes conversacionales gráficos y multimodales. Carmen tiene un doctorado en Análisis de Conversaciones y es autora de “Conversar en español: un enfoque desde el Análisis de la Conversación” publicado por Peter Lang Berlin.

Deja una respuesta

Tu dirección de correo electrónico no será publicada. Los campos obligatorios están marcados con *