With an increase in alternative forms of work, people are no longer limited to traditional office spaces. The aim for a healthier integration of private and work comes with the advantages of experimenting with new technologies. As a result, coworking spaces are spreading through the urban centers. But our way of dealing with work is still marked by our corporate-focused past. This project aims to explore how can co-working spaces occupy a more meaningful role by connecting people with their interests. My interest is to unveil the social rules of the space and turn interactions between coworkers more pleasant and easy. The result is a reflection about the future of collaborative workplaces. The success of the experiments reflect the openness of most co-workers and hosts. On a higher level the project gave me a better understanding of how AI could help to improve the social aspect of our workplaces.

It is projected that by the year 2033, 41% of the population in the United Kingdom will be aged 60 and over, compared to 17% in 2010. However, as people get older, age-related impairments to working memory and cognition, as well as sensory impairments, mean that older adults struggle to adopt new information technology systems, which have become integral to everyday life in recent years. The research presented here investigates, across a series of three large scale experiments, how Embodied Conversational Agents (ECAs) can be used in virtual world applications, addressing three important domains of application space, to understand how ECAs may be used to engage with older users. The Virtual Banking Experiment investigates whether or not ECA gender or age portrayal has an effect on overall usability of virtual world applications for older users. The results of the experiment show that older users do not exhibit a significant preference for a particular ECA gender, however they do exhibit a preference for interacting with younger ECAs when compared with older ECAs in these applications. Results of the Entertainment Experiment show that scripting the interaction, between older users and ECAs in a virtual world quiz game, significantly improved the usability of these virtual world gaming applications employing ECAs as interlocators. The Social Support Experiment investigated three styles of providing advice to older users as part of a virtual advice bureau service. The results of the experiment show that older users prefer to receive advice from ECAs that has not been presented as having been obtained from real-world experiences.

Embodied Conversational Agents (ECAs) potentially represent a way to deliver services to the public that would previously have require human staff. Making an ECA available online allows out-of-hours access to information and services, as well as allowing users to access the information anywhere there is an internet connection. As handheld devices grow in popularity and become the primary source of internet connection for many users, it is necessary to examine whether an ECA is appropriate for use on a handheld device, and what factors affect its usability. Over the course of four experiments this research examines how using a handheld device is different from using a PC, how an ECA should be presented on a handheld device, how using an ECA service in a public space affects the experience, and how an ECA should interact with users. It was determined that the usability of an ECA service is not affected by the device on which it is experienced, that on smaller screens or in demanding environments the ECA should be emphasised, and that text should be included in an ECA service as long as the ECA remains intermittently visible. It was also found that usability results from the laboratory can be generalised to the real world, that ECA services are appropriate for all ages and genders, that incorporating disclosure elements into an ECA service is a beneficial feature, and that while financial topics are appropriate to be discussed with an ECA, they are best kept to general rather than personal information. The following chapters present the necessary literary background to the field, before covering each experiment individually, and finally presenting detailed conclusions about the usability of ECAs on handheld devices.

The purpose of the thesis is to describe usage of Conversational maps in educational process with diabetic patients. Furthermore, the thesis compares standard education and usage of Conversational maps in education in terms of effect in cognitive, psychomotor and effective area. Theoretical part of the thesis describes diabetes mellitus and its distinction. World epidemiologic data and statistics in Czech Republic are described. Education and education using Conversational maps is outlined. Communication between nurse and diabetic patient is another topic the thesis focuses on as well as on theory of taking care of diabetic patients and education of the nurses in this field of medicine. For research qualitative approach was used. Data were collected by interview with nurses and patients. Action research was used to implement group and individual education for patients with diabetes mellitus. Information from the interview were collected on piece of paper with "paper - pencil" method. Transcribed texts were subdued to segmentation, coding and categorization. Categories were made based on similitude of relationships between codes. First group of respondents included five patients and five nurses, both from a diabetic consulting room. Second group of respondents consisted of five nurses from a diabetic consulting room. Action research was used for education of the nurses. Education was provided to groups or individuals, for patients from diabetic clinic and for those who shown interest in it. Concrete aims were taken in consideration of every education plan. The research took place from December 2018 to March 2019. The aim of the thesis is to introduce the problematic of education using Conversational maps and to distinguish between this method and regular methods that are usually used. Health care workers meet diabetic patients every day. Therefore, we wish to make the education more efficient moreover to compere effect in cognitive, psychomotor and effective area. Based on implemented research it can be said that most patients find the usage of Conversational maps in education helpful, understandable and easy to remember. Me as an author of this thesis and interviewed nurses share the same opinion. Most patients in our research were educated in the problematic of diabetes mellitus. Having said that, they still expressed interest in Conversational maps to deepen their knowledge. It would be beneficial to get better access to Conversational maps to provide better education. To make progress in this area we made educational plans which consist of steps and action research that can be used in education. Distinct differences in this area would be made with higher number of educational nurses which would be using this method. The results of this thesis can be used for education´s improvement.

People interact through language and conversation everyday, children learn from an early age to express a variety of intents and responses in an understandable way. But the interaction form most commonly used in systems today is nothing like this. Instead, it is dominated by interactions such as button presses, scrolling, drag and drop, swipe gestures etc. What benefits and drawbacks can be observed when transforming such an application to one where users can use their natural inclination towards conversation to converse directly with the system. This exploratory study compares the usability of a conversational interaction form against the 'de facto'-standard that has a point and click interface. To assess usability differences, a chatbot prototype was designed and implemented. The prototype was developed in partnership with the consulting company Knowit and one of the leading Swedish clothing retailers. This prototype was subsequently tested against the clothing retailer's current application. The two interaction strategies were compared for usability for first and second time use. The results show some self reported usability differences in second time use favouring the chatbot prototype.

<p>The overall aim of this study is to achieve the increased knowledge of the use of the counselling methods in the student counsellors' work and to find the possibilities for development. Two questions are used as guidelines:</p><p>Which counselling methods do student counsellors use in their work in schools?</p><p>How can the current education for the student counsellors be supplemented?</p><p>The analysis of the interviews with six counsellors in Stockholm's administrative province showed that even uneducated counsellors use the same counselling methods as the educated ones. All these methods which are used remind of the known counselling methods that are the part of the current education for the student counsellors.</p><p>In general counsellors experienced that the education for the counsellors should be supplemented within the field children with special needs and that conversation's methodology is the essence of the counselling work.</p>

The overall aim of this study is to achieve the increased knowledge of the use of the counselling methods in the student counsellors' work and to find the possibilities for development. Two questions are used as guidelines: Which counselling methods do student counsellors use in their work in schools? How can the current education for the student counsellors be supplemented? The analysis of the interviews with six counsellors in Stockholm's administrative province showed that even uneducated counsellors use the same counselling methods as the educated ones. All these methods which are used remind of the known counselling methods that are the part of the current education for the student counsellors. In general counsellors experienced that the education for the counsellors should be supplemented within the field children with special needs and that conversation's methodology is the essence of the counselling work.

Thesis (Ph. D.)--University of Hawaii at Manoa, 2003. / Includes bibliographical references (leaves 391-402).

Chatbots are programs that mimic human conversation using Artificial Intelligence (AI). Recent advances in natural language pro- cessing pave the way for chatbots to generate more human-like responses. Therefore, chatbots are finding more complex tasks to perform, such as emotional support which requires both understanding emotions and the ability to properly respond to them. This work presents a chatbot capable of identifying the user's personality and creating responses based on that. During this process, emotion detection is being used to detect and react to users' emotions. The chatbot uses a dynamic knowledge graph to save information as the conversation goes on. A user study confirmed that these additions were both noticeable and improved the user's sense that the chatbot was getting to know them as a person. Long-term, we hope this research will help create chatbots that provide emotional support for caregivers who work with people with dementia.

Communication between the patient and the physician in clinical encounters has traditionally been considered a passive interaction on the side of the patient, whereby the healthcare provider examines the patient's condition and circumstances, evaluates the situation, and prescribes a certain treatment plan or procedural solution that will heal the patient's ailment. However, recent research and fundamental communications understanding strongly emphasizes that effective communication is a two-way endeavor that ideally should involve input and insight from both sides of the conversation. Treating all clinical interactions as a one-way didactic experience where a provider usually goes through a checklist of commonalities would seem to not approach the same level of patient satisfaction and understanding as active mutual participation employing common conversational and argumentative techniques by both sides of the patient-physician dyad. The Conversational Argument Coding Scheme, presented by Canary et al., was implemented in a slightly modified format to code transcripts of clinical encounters in a college setting. It was demonstrated that clinical encounters employing more forms of conversational argumentation did not statistically correlate to increased ratings of patient satisfaction/knowledge, but did not harm these ratings in a significant manner. This could be due to the limitation that the study was conducted with a patient population consisting entirely of enrolled college students on campus, implying a greater degree of health literacy and education level that highlights that a presence or lack of teach-back or other mutual participation would not significantly affect patient satisfaction/knowledge in the clinical encounter. Further research needs to be conducted to prove this correlation, but as of now, it would be in good practice and in good faith for healthcare providers to employ teach-back or to encourage mutual participation and conversation in their clinical encounters.