Master of Education (MEd), Bowling Green State University, 2011, Career and Technology Education/Technology

As the need for educating traditional and non-traditional students increases and budgets decrease, the demand for higher education institutions to implement creative ways to provide effective customer service to students has never been more critical. This research studied the potential implementation of an Agent for Interactive Student Assistance (AISA) application in Bowling Green State University's (BGSU's) College of Technology and its impact on student engagement and recruitment. AISA is defined as an interactive, human-like, avatar-based online student assistance application with voice and text recognition that provides answers to students' administrative-related most frequently asked questions. The avatar-based application would provide cognitive responses using voice and non-verbal communication with a 90% accuracy rate. BGSU College of Technology undergraduate and graduate students during the 2009/2010 and 2010/2011 academic years were the population of this study consisting of 940 students. The approach of this study was quantitative, post positivist with an expected outcome in the form of an alternate hypothesis tested against a null hypothesis. One survey was administered to the population with a response rate of 9%. Favorable results were found with 91% of students indicating they would or may use an AISA application if provided the opportunity. One proportion z tests showed that, overall, students would not experience a negative impact on engagement and BGSU's College of Technology would not experience a decrease in new students.

Committee: Terry Herman PhD (Committee Chair); Gary Benjamin PhD (Committee Member); Anthony Fontana (Committee Member) Subjects: Education; Educational Technology

Doctor of Philosophy, The Ohio State University, 2020, Computer Science and Engineering

We introduce a virtual patient question-answering dialogue system, used for training medical students to interview real patients, which presents many unique opportunities for research in linguistics, speech, and dialogue. Among the most challenging research topics at this point in the system's development are issues relating to scarcity of training data. We address three main problems. The first challenge is that many questions are very rarely asked of the virtual patient, which leaves little data to learn adequate models of these questions. We validate one approach to this problem, which is to combine a statistical question classification model with a rule-based system, by deploying it in an experiment with live users. Additional work further improves rare question performance by utilizing a recurrent neural network model with a multi-headed self-attention mechanism. We contribute an analysis of the reasons for this improved performance, highlighting specialization and overlapping concerns in independent components of the model. Another data scarcity problem for the virtual patient project is the challenge of adequately characterizing questions that are deemed out-of-scope. By definition, these types of questions are infinite, so this problem is particularly challenging. We contribute a characterization of the problem as it manifests in our domain, as well as a baseline approach to handling the issue, and an analysis of the corresponding improvement in performance. Finally, we contribute a method for improving performance of domain-specific tasks such as ours, which use off-the-shelf speech recognition as inputs, when no in-domain speech data is available. This method augments text training data for the downstream task with inferred phonetic representations, to make the downstream task tolerant of speech recognition errors. We also see performance improvements from sampling simulated errors to replace the text inputs during training. Future enhancements to (open full item for complete abstract)

Committee: Eric Fosler-Lussier PhD (Advisor); Michael White PhD (Committee Member); Yu Su PhD (Committee Member) Subjects: Artificial Intelligence; Computer Science; Educational Software; Linguistics

Master of Science (MS), Wright State University, 2019, Computer Science

Asthma, chronic pulmonary disease, is one of the major health issues in the United States. Given its chronic nature, the demand for continuous monitoring of patient's adherence to the medication care plan, assessment of their environment triggers, and management of asthma control level can be challenging in traditional clinical settings and taxing on clinical professionals. A shift from a reactive to a proactive asthma care can improve health outcomes and reduce expenses. On the technology spectrum, smart conversational systems and Internet-of-Things (IoTs) are rapidly gaining popularity in the healthcare industry. By leveraging such technological prevalence, it is feasible to design a system that is capable of monitoring asthmatic patients for a prolonged period and empowering them to manage their health better. In this thesis, we describe kBot, a knowledge-driven personalized chatbot system designed to continuously track medication adherence of pediatric asthmatic patients (age 8 to 15) and monitor relevant health and environmental data. The outcome is to help asthma patients self manage their asthma progression by generating trigger alerts and educate them with various self-management strategies. kBOT takes the form of an Android application with a frontend chat interface capable of conversing both text and voice-based conversations and a backend cloud-based server application that handles data collection, processing, and dialogue management. The domain knowledge component is pieced together from the Asthma and Allergy Foundation of America, Mayoclinic, and Verywell Health as well as our clinical collaborator. Whereas, the personalization aspect is derived from the patient's history of asthma collected from the questionnaires and day-to-day conversations. The system has been evaluated by eight asthma clinicians and eight computer science researchers for chatbot quality, technology acceptance, and system usability. kBOT achieved an overall technology acceptance (open full item for complete abstract)

Committee: Amit Sheth Ph.D. (Advisor); Krishnaprasad Thirunarayan Ph.D. (Committee Member); Valerie Shalin Ph.D. (Committee Member); Maninder Kalra M.D., Ph.D. (Committee Member) Subjects: Computer Science; Health Care Management; Information Technology