Juliana Miehle

When communicating, people use strategies while choosing the words and the non-verbal signs in order to achieve their purpose. Hence, they do not only focus on what they say, but also on how they formulate it. The aim of this thesis is to examine the role of communication styles in human-computer interaction. This is approached from two angles: it is investigated how varying communication styles are perceived by the user and how communication styles can be integrated into spoken dialogue systems. In order to answer the first question, system requirements are analysed in a series of complex prototypes and various user evaluations are conducted to examine different user groups in diverse scenarios. The second aspect is addressed through the implementation of two new components for spoken dialogue systems. There are numerous parameters that influence an interaction between two participants and the appropriate or preferred communication style, like the speakers’ roles, their cultures, their personalities or the aim of the interaction. In order to enable adaptation through communication styles, these different aspects need to be set into relation. Therefore, the Communication Style Perception Model is presented within the scope of this thesis. It covers elements that are relevant for the selection of the system communication style as well as aspects that are influenced by the system communication style. It is based on numerous user evaluations, examining various user groups in different scenarios. Three experiments investigate the influence of numerous variables on the user's preference in the system communication style. The results …

With the aim of designing a spoken dialogue system which has the ability to adapt to the user's communication idiosyncrasies, we investigate whether it is possible to carry over insights from the usage of communication styles in human-human interaction to human-computer interaction. In an extensive literature review, it is demonstrated that communication styles play an important role in human communication. Using a multi-lingual data set, we show that there is a significant correlation between the communication style of the system and the preceding communication style of the user. This is why two components that extend the standard architecture of spoken dialogue systems are presented: 1) a communication style classifier that automatically identifies the user communication style and 2) a communication style selection module that selects an appropriate system communication style. We consider the communication styles elaborateness and indirectness as it has been shown that they influence the user's satisfaction and the user's perception of a dialogue. We present a neural classification approach based on supervised learning for each task. Neural networks are trained and evaluated with features that can be automatically derived during an ongoing interaction in every spoken dialogue system. It is shown that both components yield solid results and outperform the baseline in form of a majority-class classifier.

We present a study addressing the question how script knowledge based conversational assistants should act in situations of inconclusive information. Such situations occur for example in case of alternative or optional events that lead to multiple correct paths through the script. We have conducted a user study with four typical everyday activities (Making Coffee, Baking Cake, Finding the route to main station, Finding the route to camping ground) that may be represented in scripts. In this study, we have compared and evaluated four different presentation styles to handle situations of conflicting script information. A total of 182 persons participated in our study. The evaluation results show that, in case of a conflicting script state, users find the assistant most useful and are most satisfied if the assistant guesses the next correct event and provides a direct instruction instead of disclosing his incompetence. Alternatives in …

Nowadays, intelligent agents are omnipresent and used by almost all generations. Furthermore, we live in a globally mobile society in which populations of widely different cultural backgrounds live and work together. The number of people who leave their ancestral cultural environment and move to countries with different culture and language is increasing. This is not free of challenges. Especially in the case of care, migrants often face two issues:(i) not being able to speak the language and not being acquainted with the culture of the resident country, and (ii) being unfamiliar with the care and health administrations of the country. As a consequence, eg elderly migrants in care homes suffer from social exclusion, with their relatives also struggling with getting the right information and interacting with the administration, migrants at home are often reluctant to go to see the doctor in case of health issues, a tendency that …

Contemporary societies are comprised of individuals very diverse in terms of culture, status, gender and age. In this context, there is no single system behaviour that fits all users, not even considering the traditional “personalization” efforts of adaptable systems, in which individual users can explicitly tailor some system features to their needs. Multicultural and ageing societies demand adaptive interactive systems with the ability to learn about and from their users and adjust their behaviour accordingly. This chapter presents a vision of an intelligent reminder agent to illustrate the current challenges for the design and development of adaptive systems, which are analysed following the what-which-how-then model to cover all aspects of which features to adapt, what to adapt to, when to adapt and how to adapt, with special emphasis on multimodal conversational interaction.

The cultural background has a great influence on the people’s behaviour and perception. With the aim of designing a culturally sensitive conversational assistant, we have investigated whether culture-specific parameters may be trained by use of a supervised learning approach. We have used a dialogue management framework based on the concept of probabilistic rules and a multicultural data set to generate a culture-aware dialogue manager which allows communication in accordance with the user’s cultural idiosyncrasies. Hence, the system response to a user action varies depending on the user’s culture. Our data set contains 258 spoken dialogues from four different European cultures: German, Polish, Spanish and Turkish. For our evaluation, we have trained a culture-specific dialogue domain for each culture. Afterwards, we have compared the probability distributions of the parameters which are …

The collection of spatiotemporal tourism information is important in smart tourism and user-generated contents are perceived as reliable information. Participatory sensing is a useful method for collecting such data, and the active contribution of users is an important aspect for continuous and efficient data collection. This study has focused on the impact of task allocation interface design and individual personality on data collection efficiency and their contribution in gamified participatory sensing for tourism. We have designed two types of interfaces: a map-based with active selection and a chat-based with passive selection. Moreover, different levels of elaborateness and indirectness have been introduced into the chat-based interface. We have employed the Gamification User Types Hexad framework to identify the differences in the contributions and interface preferences of different user types. The results of our tourism experiment with 108 participants show that the map-based interface collects more data, while the chat-based interface collects data for spots with higher information demand. We also found that the contribution to sensing behavior and interface preference differed depending on the individual user type.

We present an indoor navigation system that is based on natural spoken interaction. The system navigates the user through the University of Ulm based on scripts, supporting three different routes and varying communication styles for the system descriptions. Furthermore, the system is able to cope with incomplete scripts and inconclusive situations by passing the dialogue initiative to the user. In order to create the scripts, a data collection has been carried out in which 97 native speakers described the routes with the help of videos. In the end, the system has been evaluated in a user study with 30 participants. The work is part of the research project “MUNGO—Multi-User Indoor Navigation Using Natural Spoken Dialog and Self-learning Ontologies”, co-funded by the 2018 Google Faculty Research Award.