A Satisfaction-based Model for Affect Recognition from Conversational Features in Spoken Dialog Systems

Detecting user affect automatically during real-time conversation is the main challenge towards our greater aim of infusing social intelligence into a natural-language mixed-initiative High-Fidelity (Hi-Fi) audio control spoken dialog agent. In recent years, studies on affect detection from voice have moved on to using realistic, non-acted data, which is subtler. However, it is more challenging to perceive subtler emotions and this is demonstrated in tasks such as labelling and machine prediction. This paper attempts to address part of this challenge by considering the role of user satisfaction ratings and also conversational/dialog features in discriminating contentment and frustration, two types of emotions that are known to be prevalent within spoken human-computer interaction. However, given the laboratory constraints, users might be positively biased when rating the system, indirectly making the reliability of the satisfaction data questionable. Machine learning experiments were conducted on two datasets, users and annotators, which were then compared in order to assess the reliability of these datasets. Our results indicated that standard classifiers were significantly more successful in discriminating the abovementioned emotions and their intensities (reflected by user satisfaction ratings) from annotator data than from user data. These results corroborated that: first, satisfaction data could be used directly as an alternative target variable to model affect, and that they could be predicted exclusively by dialog features. Second, these were only true when trying to predict the abovementioned emotions using annotator?s data, suggesting that user bias does exist in a laboratory-led evaluation.

Justice, emotions and satisfaction in complaint behavior in services

This study proposes a marketing approach to service recovery (SR) models in order to help to explain what factors affect cumulative satisfaction, loyalty and word-of-mouth following complaint behavior. The model has its base on the definition of perceived justice and its influence on satisfaction with service recovery (SSR) and on emotions (positive and negative). Trust acts as a central construct in the model, receiving influence from the affective and cognitive aspect and mediating the relationship between SSR and cumulative satisfaction and between positive/negative emotions and loyalty. The sample for this study consists of 303 Spanish B2C-EC users who made a complaint after an electronic transaction. Results from the analysis show the influence of perceived justice ?mainly interactional justice and procedural justice? on SSR, and the relevance of positive emotions as a key factor in SSR processes, in contrast to the major role which negative emotions have traditionally played in these models. Furthermore, trust mediates the relation between SSR and cumulative satisfaction, and is the factor which has a higher influence on loyalty, whilst cumulative satisfaction becomes the more relevant factor affecting WOM.

Are team personality and climate related to satisfaction and software quality? Aggregating results from a twice replicated experiment

Research into software engineering teams focuses on human and social team factors. Social psychology deals with the study of team formation and has found that personality factors and group processes such as team climate are related to team effectiveness. However, there are only a handful of empirical studies dealing with personality and team climate and their relationship to software development team effectiveness. Objective We present aggregate results of a twice replicated quasi-experiment that evaluates the relationships between personality, team climate, product quality and satisfaction in software development teams. Method Our experimental study measures the personalities of team members based on the Big Five personality traits (openness, conscientiousness, extraversion, agreeableness, neuroticism) and team climate factors (participative safety, support for innovation, team vision and task orientation) preferences and perceptions. We aggregate the results of the three studies through a meta-analysis of correlations. The study was conducted with students. Results The aggregation of results from the baseline experiment and two replications corroborates the following findings. There is a positive relationship between all four climate factors and satisfaction in software development teams. Teams whose members score highest for the agreeableness personality factor have the highest satisfaction levels. The results unveil a significant positive correlation between the extraversion personality factor and software product quality. High participative safety and task orientation climate perceptions are significantly related to quality. Conclusions First, more efficient software development teams can be formed heeding personality factors like agreeableness and extraversion. Second, the team climate generated in software development teams should be monitored for team member satisfaction. Finally, aspects like people feeling safe giving their opinions or encouraging team members to work hard at their job can have an impact on software quality. Software project managers can take advantage of these factors to promote developer satisfaction and improve the resulting product.

La Calidad Técnica de los Proyectos de Ejecución de Viviendas

En el proceso general de la sociedad por la mejora continua hacia la Calidad, el sector de la construcción, y más específicamente la actividad de los Arquitectos con la redacción de los proyectos, no pueden, ni deben, quedar al margen. La presente investigación apunta un procedimiento para el control técnico de los proyectos y demuestra la eficacia y rentabilidad de éste o cualquier otro método de control, avanzando una aproximación a los modelos de costes de calidad de los estudios de arquitectura. El método de trabajo que se ha previsto para el desarrollo de la tesis cuenta con una base principal consistente en definir un procedimiento general de revisión de los proyectos, tipificando los principales errores (sistema de puntos de inspección), analizando las causas que los generan, su repercusión en el plazo, durabilidad y satisfacción del cliente, así como en definir un método de cuantificación que nos aproxime a la "importancia" (económica) que tienen o inducen los errores e indefiniciones detectadas. Para demostrar la validez de la hipótesis inicial sobre la rentabilidad de aplicar un sistema de control técnico del proyecto, se ha aplicado una parte del procedimiento general particularizado para la evaluación sistemática de los problemas, indefiniciones y fallos detectados, al que llamamos de forma simplificada Método Partícula Éste se aplica sobre una muestra de proyectos que se revisan y que, para que los resultados del análisis sean representativos, se seleccionaron de forma aleatoria, respondiendo topológicamente en sus variables definitorias a la población que se pretende estudiar: la totalidad de proyectos de ejecución de viviendas producidos en el ámbito territorial de Madrid (Comunidad) en el plazo comprendido entre los años 1990 y 1995. Pero además esta representatividad está condicionada a la mayor o menor exactitud de la valoración que se haga de los sobrecostos que puedan generar los errores e indefiniciones de los proyectos. Se hace pues imprescindible el tratar de objetivar al máximo los criterios de valoración de los mismos. Con los datos generados en la revisión de cada proyecto se analizan la totalidad de resultados de la muestra objeto de estudio, sacando conclusiones sobre frecuencia e importancia de los errores, incidencia de las variables que influyen, y posibles combinaciones de variables que incrementan el riesgo. Extrapolando el análisis al método general y a la población objeto de estudio, se extraen conclusiones significativas respecto a la eficacia del control técnico de proyectos, así como de las formas de optimizar las inversiones realizadas en el mismo, depurando y optimizando selectivamente el método general definido. Con el análisis de los modelos de coste de calidad se puede constatar cómo las inversiones en desarrollar sistemas de aseguramiento de la calidad de los proyectos, o, de forma más modesta, controlando la calidad técnica de los mismos, los estudios de arquitectura, amén del mejor servicio ofrecido a los clientes, y lo que ésto supone de permanencia en el mercado, mejoran significativamente su competitividad y su margen de beneficio, demostrando que son muy rentables tanto para los propios arquitectos, como para la sociedad en general. ABSTRACT The construction sector as a whole, and especifically architects as project drafters, must fully participate in the general process of society for continuous improvement towards quality. Our research outlines a procedure for the technical control of projects and shows the efficacy and cost-effectiveness of this or any other control method, putting fonvard an approach to quality cost-models in Architecture offices. Our procedure consists mainly in defining a general method of revising projects, typifying main errors (Points of inspection system), analysing their causes, their repercussion in clients' durability and satisfaction. It wHI also define a quantitative method to assess tfie economic importance of detected errors and indefinitions. To prove our initial hypothesis on the cost-effectiveness of applying a system of tecfinical control to projects we have applied part of the general procedure, adjusting it to the systematic evaluation of problems, indefinitions and errors we have found. This will be simply called Particular Method. We will use it on a sample of projects which were randomly selected, for the sake of representativeness, and which, in their defining variables, match the population under study topologically: every housing project in Madrid (Región) between 1.990 and 1.995. Furthermore, this representativeness is related to the accuracy of the assessment of the additional costs due to errors or lack of definition in the projects. We must therefore try to be precise in the evaluation of their costs. With data obtained from the revision of each project, we analyze every result from the sample under study, drawing conclusions about the frequency and importance of each error, their causing variables, and the combination of variables which are risk-increasing. By extrapolating this analysis to the General Method and the population under study, we draw significant conclusions on the effectiveness of the technical control of projects, as well as of the ways to optimise the investment in it, improving and optimising the General Method in a selective way. Analyzing quality cost-models, we can show how the investment in developing systems that will guarantee quality projects, or, more modestly, controlling the technical quality of them, Architecture firms will not only serve their clients best, with its impact on the firm's durability, but also improve their competitivity and their profit margin proving that they are profitable both for architects themselves and for the general public.