Date of Award
Santa Clara : Santa Clara University, 2019
Developing a compelling and cohesive thesis for analytical writing can be a daunting task, even for those who have produced many written works, and finding others to engage with in literary discussion can be equally challenging. In this paper, we describe our solution: Questioner, a discussion tool that engages users in conversation about an academic topic of their choosing for the purpose of collecting thoughts on a subject and constructing an argument. This system will ask informed questions that prompt further discussion about the topic and provide a discussion report after the conversation has ended. We found that our system is effective in providing users with unique questions and excerpts that are relevant, significant, and engaging. Such a discussion tool can be used by writers building theses, students looking for study tools, and instructors who want to create individualized in-class discussions. Once more data is gathered, efficient and accurate machine learning models can be used to further improve the quality of question and excerpt recommendations. Co-creative discussion tools like Questioner are useful in assisting users in developing critical analyses of written works, helping to maximize human creativity.
Culkin, Robbie and Shur, Tim, "A Questioning Agent for Literary Discussion" (2019). Computer Science and Engineering Senior Theses. 130.