User experience over time with conversational agents: case study of woebot on supporting subjective well-being

Demirci, Hatice Merve
Technological advancements re-shaped user-product interactions by enabling people to make conversation with interactive systems. This new form of interaction led designers to create a new type of user interface: Conversational User Interface (CUI). Expensive psychological therapy fees and people’s increased awareness related to importance of well-being attracted the interactive system developers to create a domain specific Conversational Agent, which is particularly focusing on psychological terapy and has CUI. In order to maintain user engagement and sustain usage, design of such systems is important. However, existing design guidelines for Conversational Agents are limited and focus on business functions of these agents; however, conversational experience should be the main focus for designers to sustain user engagement and support people’s well-being. The aim of this research is to explore design qualities of Conversational Agent’s that focuses on enhancing people’s subjective well-being, to accomplish sustained usage and engagement with the conversational agent and propose guidance for designing such agents. For this purpose, interviews were conducted with users. Woebot, a Conversational Agent, which is designed for promoting people’s subjective well-being was selected as a case for the study and evaluated by 16 participants. The interpretations of the participants were obtained by semi- structured and in-depth interviews. Through analysing the results of the interviews, improvement suggestions are presented regarding system operations and functionality in terms of its attractiveness, perspicuity, effectiveness, stimulation, dependability, efficiency and novelty. Lastly, the study provides insights that would affect users’ engagement and overall experience


Intelligent student assessment and coaching interface to web-based education-oriented intelligent experimentation on robot supported laboratory set-ups
Motuk, Halil Erdem; Erkmen, Aydan Müşerref; Erkmen, İsmet; Department of Electrical and Electronics Engineering (2003)
This thesis presents a framework for an intelligent interface for the access of robotsupported remote laboratories through the Internet. The framework is composed of the student assessment and coaching system, the experimentation scenario, and the associated graphical user interface. Student assessment and coaching system is the main feature of a successful intelligent interface for use during remote experimentation with a robot-supported laboratory setup. The system has a modular structure employing artifi...
Demonstratives in the context of a collaborative problem solving task
Büyüktekin, Faruk; Çakır, Murat Perit; Temürcü, Ceyhan; Department of Cognitive Sciences (2018)
Multimodal user interfaces have become increasingly important. They are being used in various applications such as computer games, online education, simulations, and assistive technology. Such interfaces now can make use of inputs coming from different modalities such as speech and eye gaze. This multimodality enables situated dialogue between users and artificial agents, encouraging collaborative language use. Naturally, people need to refer to entities in the surrounding environment using demonstratives d...
A usability evaluation framework and a case study on a supplier portal system
Babayiğit, Elif Fatma; Şen, Tayyar; Department of Industrial Engineering (2003)
The goal of this thesis is to provide a usability evaluation framework in the area of e-procurement technologies and a case study on this base. A survey of the concepts of human computer interaction, usability and usability evaluation techniques is carried out. Additionally current e-procurement technologies are explored and specifically a Company̕s Supplier Portal System which was employed in year 2003, as an e-procurement technology for the procurement of direct goods, is taken into consideration. Pointin...
Estimation of the user's cognitive load while interacting with the interface based on bayesian network
Saydam, Aysun; Barbaros, Yet; Department of Cognitive Science (2021-9-10)
The complexity of human machine interfaces is increasing significantly in parallel with the development of technology and excessive data growth, but human cognitive capacity is limited. Therefore, measuring cognitive load is one of the most preferential and common ways to test the usability of user interfaces. There are many different physiological, behavioral and subjective methods to measure human performance and workload. Moreover, there are cognitive predictive models and many related applications based...
Lifelong learning and personalization in long-term human-robot interaction (LEAP-HRI)
Irfan, Bahar; Ramachandran, Aditi; Spaulding, Samuel; Kalkan, Sinan; Parisi, German I.; Gunes, Hatice (2021-03-08)
While most of the research in Human-Robot Interaction (HRI) focuses on short-term interactions, long-term interactions require bolder developments and a substantial amount of resources, especially if the robots are deployed in the wild. Robots need to incrementally learn new concepts or abilities in a lifelong fashion to adapt their behaviors within new situations and personalize their interactions with users to maintain their interest and engagement. The "Lifelong Learning and Personalization in Long-Term ...
Citation Formats
H. M. Demirci, “User experience over time with conversational agents: case study of woebot on supporting subjective well-being,” M.S. - Master of Science, Middle East Technical University, 2018.