Date of Award
Fall 11-24-2023
Document Type
Thesis
Degree Name
Master of Science (MS)
Department
Mathematics, Statistics and Computer Science
First Advisor
Sheikh Iqbal Ahamed
Second Advisor
Praveen Madiraju
Third Advisor
Niharika Jain
Abstract
The objective of this master’s thesis is to utilize daily episode notes obtained from users in order to develop a lifestyle indicator through the application of natural language processing (NLP) techniques. The primary objective is to enhance the precision of this indicator by reducing its level of ambiguity. In order to achieve this objective, the present work undertakes a comprehensive examination of conversational agents, specifically focusing on social media data that has been annotated with content pertaining to diabetes. The study uses a variety of NLP methodologies to establish a correlation between the subject matter of these discussions and medical terminologies present in the Unified Medical Language System (UMLS). This mapping ensures compliance with established medical terminology and enhances understanding of linguistic expressions related to the patient’s lifestyle. Moreover, the research acknowledges the significance of minimizing ambiguity in the semantics of written material. Methods for mitigating ambiguity, such as the Viterbi algorithm, are employed to enhance the precision of lifestyle summaries extracted from online textual content. This pivotal phase ensures that the indicator effectively and meaningfully represents the decisions, behaviors, and overall welfare of users. The findings of this study significantly contribute to the domain of lifestyle annotation and provide valuable insights into the development of tailored metrics for individuals with diabetes. This study lays the foundation for enhancing the accuracy and informativeness of casual daily textual analysis or habitant behavior measurements through the integration of Spacy, UMLs, and Viterbi. These indicators not only contribute to improved healthcare decision-making but also enhance the overall quality of life for those with diabetes.