Sökning: "Conversational Interface"

Visar resultat 1 - 5 av 23 uppsatser innehållade orden Conversational Interface.

  1. 1. Exploring Emely: An exploratory case study on the usability and user experience of a conversational agent for L2 learning

    Kandidat-uppsats, Malmö universitet/Institutionen för datavetenskap och medieteknik (DVMT)

    Författare :Julia Ahrling; Jonna Franzén; [2023]
    Nyckelord :Conversational agents; Second language learning; L2 learning; Usability; User experience;

    Sammanfattning : This study focuses on evaluating and enhancing the user experience of Emely, a conversational agent aimed at improving language skills for second language learners, particularly those who want to increase their chances of securing employment in Sweden. Usability testing was conducted in two test rounds, with the first round providing design implications for the user interface in the second round. LÄS MER

  2. 2. Utilizing GPT for Interactive Dialogue-based Learning Scenarios : A Comparative Analysis with Rasa

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Valdimar Björnsson; [2023]
    Nyckelord :Generative Pretrained Transformer; Rasa; Interactive Tutoring Systems; Conversational AI; Education Technology; Generativ förtränad transformator; Rasa; interaktiva handledningssystem; Conversational AI; Education Technology;

    Sammanfattning : This thesis explores the use of advanced language models, specifically OpenAI’s Generative Pretrained Transformer (GPT), in the context of interactive tutoring systems built within a Unity-based game environment. The central problem addressed is whether the recent advancements in large language models make them feasible and useful to function as tutors specifically in providing meaningful, engaging, and educationally rich user interactions on a dialogue based learning platform developed by Fictive Reality. LÄS MER

  3. 3. Exploring cognitive biases in voice-based virtual assistants

    Master-uppsats, Mälardalens universitet/Akademin för innovation, design och teknik

    Författare :Anna Khofman; [2023]
    Nyckelord :Voice user interface; virtual assistant; natural language processing; cognitive bias;

    Sammanfattning : This paper investigates the conversational capabilities of voice-controlled virtual assistants with respect to biased questions and answers. Three commercial virtual assistants (Google Assistant, Alexa and Siri) are tested for the presence of three cognitive biases (wording, framing and confirmation) in the answers given. LÄS MER

  4. 4. Transforming Education into Chatbot Chats : The implementation of Chat-GPT to prepare educational content into a conversational format to be used for practicing skills

    Kandidat-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Simon Wickman; Philip Zandin; [2023]
    Nyckelord :Artificial intelligence; ChatGPT; Summarization; Educational material; Dialogue format; Automatic evaluation; Prompt creation; Prompt.; Artificiell intelligens; ChatGPT; Sammanfattning; Utbildningsmaterial; Dialog format; Automatisk utvärdering; Instruktion.;

    Sammanfattning : In this study we explore the possibility of using ChatGPT, to summarise large contents of educational content and put it in a template that later can be used for dialogue purposes and will explore the challenges and solutions that occur during the implementation. Today there is a problem for users to create wellmade prompts for learning scenarios that fulfill all the requirements set by the user. LÄS MER

  5. 5. Shaping conversations : Investigating how conversational agents are designed and developed

    Master-uppsats, KTH/Skolan för elektroteknik och datavetenskap (EECS)

    Författare :Annetta Sillard; [2022]
    Nyckelord :Conversational Agent; Voice interface; Chatbot; Interview study; Design methods; Design tools;

    Sammanfattning : Conversational agents are becoming increasingly common in our day to day lives. We can speak to our phones, our cars and our smart home devices. Despite these advances, the current conversational agents are still far from perfect. LÄS MER