Implementación de un cuestionario estandarizado de evaluación de experiencia de usuario a través de asistentes inteligentes por voz

Estado: 
Número de proyecto: 
834-C1-013
Vigencia:
De 01/Mar/2021 hasta 31/Jul/2023

Objetivo:

Implementar un cuestionario estandarizado de evaluación de experiencia de usuario, a través de un asistente inteligente por voz.


Descripción:

La evaluación de la experiencia de usuario en el contexto de HCI (interacción humano-computador) se realiza mediante diferentes métodos y herramientas. Los cuestionarios estandarizados son una de las herramientas más utilizadas debido a las ventajas que presenta respecto de fiabilidad y aplicación.

Por otro lado, en las últimas décadas se han desarrollado interfaces que buscan explotar diferentes maneras no tradicionales de interacción entre las personas y los computadores. Entre éstas se encuentran las interfaces de lenguaje natural, implementadas por medio de asistentes inteligentes por voz. La interacción que presentan estas interfaces de voz es muy apreciada por los usuarios, motivo por el cual, los asistentes inteligentes por voz han crecido en popularidad y uso en los últimos años.

En este proyecto se desea explorar la implementación de uno de estos cuestionarios estandarizados de evaluación de experiencia de usuario, utilizando interfaces de voz, uniendo las fortalezas del instrumento de evaluación con las virtudes que presentan las interfaces de voz en el contexto de la interacción humano-computador.

Investigador principal
Dr. Ignacio Díaz Oreiro

Colaboradores
Dr. Luis Alberto Guerrero Blanco
Dr. Ignacio Díaz Oreiro

Unidad académica base
Centro de Investigaciones en Tecnologías de la Información y Comunicación (CITIC)

Unidades académicas colaboradoras
Escuela de Ciencias de la Computación e Informática (ECCI)

Publicaciones asociadas

Supporting UX Evaluation with Open Text Word Clustering

Descripción:

This research work proposes using word clustering to identify concepts associated with the user experience (UX) evaluation of a version of the standardized User Experience Questionnaire (UEQ), where the usual written of responses is replaced by input through a voice interface. The clusters were made from a Word2vec model of word embeddings that was built based on sentences contributed by participants who evaluated the implementation of the voice interface, using traditional quantitative questionnaires and which they complemented with open text comments. The results show clusters around keywords such as ’assistant’, ’understand’, ’response’ and ’survey’, which allow the identification of words associated with both the voice implementation and the UEQ questionnaire itself, and provide information about attitudes researchers could investigate in more detail about the assistant implemented, for example in a subsequent evaluation to be carried out through a focus group or semi-structured interviews.

Tipo de publicación: Conference Paper

Publicado en: 2024 IEEE VII Congreso Internacional en Inteligencia Ambiental, Ingeniería de Software y Salud Electrónica y Móvil (AmITIC)

Beyond Written Surveys: Validating Voice-Based Implementations of the User Experience Questionnaire

Descripción:

User Experience (UX) evaluation is fundamental for digital product improvement, yet traditional written questionnaires face limitations in engagement, accessibility, and response consistency. To address this, we present the design, development, and validation of voice-based adaptations of the User Experience Questionnaire, or UEQ, using natural conversational interfaces. This research introduces two distinct implementations: direct scale mapping approach called Voice1-7, and a novel branched-dialog approach called Voice2Q, which uses sequential questions to capture attitude direction and intensity. Further,we propose Voice2Q+VC, a voice-first variant with minimal visual cues to enhance clarity while preserving voice interaction primacy. Multi-stage validation was conducted through multiple case studies involving 345 participants in the design and evaluation phases. These studies compared voice implementations against the standard written version of UEQ. Statistical analyses across diverse participant groups confirmed that both Voice2Q and Voice1-7 produced similar results to the written UEQ in core UX dimensions —Attractiveness, Perspicuity, Efficiency, Dependability, Stimulation, Novelty—establishing their measurement validity. A Usability, UX and cognitive workload comparison was conducted. Results revealed thatVoice2Q significantly reduced response inconsistencies and excelled in UX hedonic stimulation, while the written UEQ retained advantages in UX pragmatic efficiency. Voice2Q+VC mitigated workload challenges inherent in voice-only interactions, outperforming the written UEQ in Usability and UX hedonic dimensions while approaching its UX pragmatic performance levels. These results suggest that supplemental visuals can optimize voice-driven evaluation without sacrificing conversational engagement. This work confirms voice-based UEQ as a statistically valid, accessible alternative to written formats, with benefits in response reliability and user engagement. The Voice2Q+VC implementation presents a promising paradigm for balancing natural interaction with cognitive efficiency in UX evaluation.

Tipo de publicación: Journal Article

Publicado en: Journal of Engineering Research and Sciences