Masterarbeit
Conceptualization and Implementation of an Experiment Infrastructure to research on Dark Patterns in Chatbots
Completion
2024/08
Research Area
Students
Firdos Katoon Khan
Advisers
Description
In the dynamic landscape of digital communication, graphical user interfaces (GUIs) sometimes employ deceptive design techniques known as Dark Patterns, potentially guiding users towards actions that may not be in their best interests. This is often the case in the e-commerce sector. In the last years, chatbots have become companions in our daily interactions, acting as the contact point between users and companies. Although users can recognize Dark Patterns within GUIs, the research such practices within the growing domain of chatbots remains largely unexplored. This research is motivated by this gap of the presence and impact of Dark Patterns in chatbots.
The thesis aims to address this gap by conceptualising and implementing an experiment infrastructure which includes a working chatbot with use cases either with or without Dark Patterns. This experiment infrastructure should aid researchers in conducting their experiments by offering user friendly settings and automation. The concept of the experiment setup has to be researched in the existing literature and adapted to the demands of this thesis, but must include typical experiment components like information for the participants on the experiment setup and the use of their personal data, a collection of pseudonymized or anonymized data and integration of appropriate evaluation methods (either qualitative, quantitative or mixed-method).
The objective of this thesis is the creation of a solution or the combination of existing approaches to solve the problem of conceptualizing and implementing an experiment infrastructure to research on Dark Patterns in Chatbots as described above. This comprises the following parts. An analysis of the state of the art of existing Dark Patterns, known Dark Patterns in Chatbots or other Conversational User Interfaces, appropriate experiment settings and other relevant work. A demonstration of the solution by a prototypical implementation of the experiment infrastructure. A suitable evaluation based both on the conceptualized experiment settings and use cases, and the compliance with elicited requirements based on the literature research.
