Evaluation of Abstraction Capabilities and Detection of Discomfort with a Newscaster Chatbot for Entertaining Elderly Users

Abstract

We recently proposed a novel intelligent newscaster chatbot for digital inclusion. Its controlled dialogue stages (consisting of sequences of questions that are generated with hybrid Natural Language Generation techniques based on the content) support entertaining personalisation, where user interest is estimated by analysing the sentiment of his/her answers. A differential feature of our approach is its automatic and transparent monitoring of the abstraction skills of the target users. In this work we improve the chatbot by introducing enhanced monitoring metrics based on the distance of the user responses to an accurate characterisation of the news content. We then evaluate abstraction capabilities depending on user sentiment about the news and propose a Machine Learning model to detect users that experience discomfort with precision, recall, F1 and accuracy levels over 80%.

Interacting with chatbots later in life: A technology acceptance perspective in COVID-19 pandemic situation

“…Studies have revealed that chatbots perform better is they are specifically created for a certain domain or group ( De Arriba-Pérez et al, 2021 ). Chatbots can be used in domains such as e-commerce, business, marketing, communication, education, news, health, food, design, finance, entertainment, travel, or utilities, but not limited to them ( Liu et al, 2018 ; Adamopoulou and Moussiades, 2020 ).…”

“…To avoid mental issues, like depression and anxiety, they need to be engaged into the daily routine, to be stimulated and entertained ( Valtolina and Hu, 2021 ). Social interaction is considered a basic need for aging population in which solitude is one of the biggest issues ( De Arriba-Pérez et al, 2021 ). Like in a vicious circle, social isolation, rejection, or loneliness seems to have a paramount negative effect on the general and mental health of an individual.…”

“…Thus, assistive technology, by its social interaction capabilities and engagement, can help in preventing illnesses ( Gunathilaka et al, 2020 ) and offers a more comfortable and cost-effective medical care ( Mesbah and Pumplun, 2020 ). However, although technology can solve this problem, aging adults are resistant to change ( Vichitvanichphong et al, 2017 ) and the digital divide is a barrier ( De Arriba-Pérez et al, 2021 ). Considering that many devices and applications are created without considering users’ perception and are designed by young people, many aging adults are reluctant to products they do not understand ( Lee and Coughlin, 2014 ; Pelizäus-Hoffmeister, 2016 ).…”

“…Almost all of them are written from a technical point of view by computer science specialists. Although AI developments in assistive technology are advanced, there is still work to be done for achieving a proper chatbot for end aging users ( De Arriba-Pérez et al, 2021 ). Thus, the existing studies refer to presenting, designing, and testing prototypes of conversational agents with meaningful, empathetic emotional, and friendship capabilities ( Yang et al, 2015 ; Bassi et al, 2021 ), with personalized entertainment content access ( De Arriba-Pérez et al, 2021 ), with workplace environment facilities ( Bächle et al, 2018 ), with capabilities to promote healthy habits through a coaching model ( Justo et al, 2021 ), with public administration abilities ( Miliani et al, 2021 ), with virtual caregiving attributions ( Su et al, 2017 ; Ryu et al, 2020 ; Valtolina and Hu, 2021 ; Miura et al, 2022 ).…”

Productivity of incident management with conversational bots-a review

“…Application Reference Conversational agent AI-based multitasking conversational agent [23], [25], [27], [38], [44], [45], [53], [ [34], [39], [48], [52] Chatbot that manages information Chatbot in information management. [53] Chatbots con AI Chatbots with AI and cloud computing.…”