Logo des Repositoriums

Auflistung nach Schlagwort "chatbot"

1 - 7 von 7
  • Konferenzbeitrag
    Enhancing Chatbot-Assisted Study Program Orientation
    (Proceedings of DELFI Workshops 2024, 2024) Dieing, Thilo I.; Scheffler, Marc; Cohausz, Lea
    As university dropout rates increase, implementing innovative solutions is crucial to reduce attrition. Aligning students’ interests with their study programs enhances academic success, satisfaction, and retention. This paper presents a novel approach using open-source Large Language Models (LLM) and Retrieval-Augmented Generation (RAG) to develop a semi-open-domain knowledge chatbot. The chatbot generates informed responses and recommendations to diverse student queries by retrieving relevant data while maintaining ethical standards and avoiding biased responses. When testing five model combinations on 70 prompts partially from real study advisors, results demonstrate that the RAG approach with the Mixtral LLM and RoBERTa embedding model offers superior performance. Our method for handling critical user prompts further indicates a significantly improved response quality. These findings advance service-oriented chatbots in education, aiming to reduce student attrition through accurate and helpful program recommendations.
  • Zeitschriftenartikel
    Fridolin: participatory design and evaluation of a nutrition chatbot for older adults
    (i-com: Vol. 22, No. 1, 2023) Weber, Philip; Mahmood, Faisal; Ahmadi, Michael; von Jan, Vanessa; Ludwig, Thomas; Wieching, Rainer
    In recent years, emerging approaches to chatbot-guided food coaching and dietary management, while innovative and promising in nature, have often lacked long-term studies. Therefore, with this work, we pursued a participatory approach within a design case study to the co-design and development of a nutrition chatbot for elderly people. Overall, 15 participants were directly involved in the study, of which 12 participated in the initial co-design phase, seven in the first real-world evaluation study over four weeks, and three in the second evaluation study over seven weeks. We contribute to the fields of Human-Computer Interaction by showing how the long-term use of such a chatbot in the area of nutrition looks like, which design implications arise for the development of nutrition chatbots, and how a participatory design approach can be realized to design, evaluate and develop nutrition chatbots.
  • Workshopbeitrag
    Lenny the bot as a resource for sequential analysis: exploring the treatment of Next Turn Repair Initiation in the beginnings of unsolicited calls
    (Mensch und Computer 2019 - Workshopband, 2019) Relieu, Marc; Sahin, Merve; Francillon, Aurelien
    Based on conversation analysis, this study examines a corpus of naturally produced telemarketing phone calls with a chatbot called Lenny. Initially designed to trick the authors of unsolicited calls, Lenny has a methodological interest for Conversation Analysis and permits a fine understanding of bot/human professional calls. Because the design of its “turns” never changes, Lenny facilitates the comparisons between sequential phenomena. In this paper, we focus on repair sequences initiated with a specific “trouble with hearing” Next Turn Repair Initiator during beginnings and pre- beginnings. We show how the caller preserves the progressivity of the call while trying to solve the repair issue.
  • Konferenzbeitrag
    (Non-)Interacting with conversational agents: perceptions and motivations of using chatbots and voice assistants
    (Mensch und Computer 2020 - Tagungsband, 2020) Weber, Philip; Ludwig, Thomas
    Conversational agents (CAs) such as Siri, Alexa, and Google Assistant are increasingly penetrating everyday life. From a Human¬–Computer Interaction (HCI) perspective, designing CAs that appropriately support the way they are used within daily life is still challenging. While initial design guide¬lines for human–AI interaction exist, we still know little about how users actually perceive CAs within their daily lives and what as¬pects motivate their usage of such tools. Within our research, we therefore conducted an interview study with 29 participants to uncover daily positive and negative experiences with CAs. By revealing how users currently perceive CAs, we identify quality criteria that could inform their future design. By evaluating these criteria with respect to existing research discourses about user experience (UX) guidelines for CAs, we contribute to the field by extending these guidelines from an end-user’s perspective.
  • Zeitschriftenartikel
    PrintAssist—a conversational human-machine interface for 3D printers
    (i-com: Vol. 22, No. 1, 2023) Jasche, Florian; Weber, Philip; Liu, Shi; Ludwig, Thomas
    3D printers are no longer found only in industry, universities or makerspaces but now are increasingly used in domestic settings. Personal fabrication will increase in the coming years, and 3D printing will play an important role in this process. Due to technology and price development, 3D printers are becoming established among casual users at home. However, there are still many hurdles in the use of 3D printers that interfere with their appropriation in everyday life. In this paper, we investigate how chatbots can overcome these hurdles and support onboarding to 3D printing. Furthermore, we explore how chatbots can be used as a human–machine interface and facilitate interaction with 3D printers for both novice and expert users. In a research-through-design approach, we have created a fully functional chatbot that introduces users to 3D printing and helps them perform typical tasks when operating 3D printers.
  • Konferenzbeitrag
    Prototyping a Virtual Tutor with Modular Teaching Styles
    (21. Fachtagung Bildungstechnologien (DELFI), 2023) Linxen, Andrea; Opel, Simone; Ebbing, Stephanie; Beecks, Christian
    Digitization and artificial intelligence (AI) have entered education in several different ways. While the current development of large language models enables students to access vast knowledge, virtual tutors offer a more tailored approach and better support for time-independent and individualized learning. As several AI systems have become more common in higher education, we developed a concept to implement a virtual tutor with different teaching styles, using the conversational AI plat-form Rasa. This tutor teaches students basic Exploratory Data Analysis in linear, free, and modular learning phases. In the future, we will conduct comprehensive studies to determine the ability of the virtual tutor to support successful learning.
  • Konferenzbeitrag
    Usability guidelines and evaluation criteria for conversational user interfaces: a heuristic and linguistic approach
    (Mensch und Computer 2020 - Tagungsband, 2020) Sugisaki, Kyoko; Bleiker, Andreas
    Even though conversational user interfaces (CUI) have been studied since the 1950s, it is not yet fully understood what makes them feel natural, intuitive and usable. As a result, their design and evaluation poses major challenges. In this paper, we discuss how CUIs are different from other forms of human computer interaction, and what challenges and opportunities arise from these differences. We provide an overview of relevant linguistic principles for a natural language conversation and look at established high-level usability heuristics to derive a set of 53 technology-agnostic checkpoints specifically for text-based CUIs (a.k.a chatbots). These checkpoints have been evaluated with 15 professionals and academics from the fields of User Experience, Natural Language Processing, Conversation Analysis and linguistics to examine content validity. The resulting list of checkpoints provides both guidelines for the design and criteria for the evaluation of chatbots.