Print Email Facebook Twitter An Exploratory Study on Conversational Agents Using Dynamic Conversation Styles Title An Exploratory Study on Conversational Agents Using Dynamic Conversation Styles Author Lerer, Bar (TU Delft Electrical Engineering, Mathematics and Computer Science) Contributor Qiu, S. (mentor) Gadiraju, Ujwal (mentor) Yang, J. (mentor) Bohmer, Wendelin (graduation committee) Degree granting institution Delft University of Technology Programme Computer Science and Engineering Project CSE3000 Research Project Date 2021-07-02 Abstract This study aims to examine the effect of dynamically aligning the conversation style to the user’s preference in a conversational agent environment. We suggest a technique to identify the user’s preferred conversation style, by scoring statements based on their writing style. We designed a within-subject experiment intended to measure the user engagement and satisfaction (with style alignment × without style alignment). We found an increase in self reported satisfaction ratings and reflect on how familiarity with the entity behind the chatbot may affect the preference of the conversational style. We finish this study with concrete suggestions to designers and developers of future chatbots and how should the alignment of conversation style be assigned and adapted Subject HCIConversational AgentChatbotConversation Style To reference this document use: http://resolver.tudelft.nl/uuid:710f265b-113d-4b72-ba4b-b89be44e360f Part of collection Student theses Document type bachelor thesis Rights © 2021 Bar Lerer Files PDF An_Exploratory_Study_on_C ... Styles.pdf 847.79 KB Close viewer /islandora/object/uuid:710f265b-113d-4b72-ba4b-b89be44e360f/datastream/OBJ/view