Master of Science, Miami University, 2024, Computer Science

Causal maps are graphical models that are well-understood in small scales. When created through a participatory modeling process, they become a strong asset in decision making. Furthermore, those who participate in the modeling process may seek to understand the problem from various perspectives. However, as causal maps increase in size, the information they contain becomes clouded, which results in the map being unusable. In this thesis, we transform causal maps into various mediums to improve the usability and accessibility of large causal models; our proposed algorithms can also be applied to small-scale causal maps. In particular, we transform causal maps into meaningful paragraphs using GPT and network traversal algorithms to attain full-coverage of the map. Then, we compare automatic text summarization models with graph reduction algorithms to reduce the amount of text to a more approachable size. Finally, we combine our algorithms into a visual analytics environment to provide details-on-demand for the user by displaying the summarized text, and interacting with summaries to display the detailed text, causal map, and even generate images in an appropriate manner. We hope this research provides more tools for decision-makers and allows modelers to give back to participants the final result of their work.

Committee: Philippe Giabbanelli (Advisor); Daniela Inclezan (Committee Member); Garrett Goodman (Committee Member) Subjects: Computer Science

Doctor of Philosophy, The Ohio State University, 2017, Industrial and Systems Engineering

Many decision problems are set in changing environments. For example, determining the optimal investment in cyber maintenance depends on whether there is evidence of an unusual vulnerability such as “Heartbleed” that is causing an especially high rate of incidents. This gives rise to the need for timely information to update decision models so that the optimal policies can be generated for each decision period. Social media provides a streaming source of relevant information, but that information needs to be efficiently transformed into numbers to enable the needed updates. This dissertation first explores the use of social media as an observation source for timely decision-making. To efficiently generate the observations for Bayesian updates, the dissertation proposes a novel computational method to fit an existing clustering model, called K-means Latent Dirichlet Allocation (KLDA). The method is illustrated using a cyber security problem related to changing maintenance policies during periods of elevated risk. Also, the dissertation studies four text corpora with 100 replications and show that KLDA is associated with significantly reduced computational times and more consistent model accuracy compared with collapsed Gibbs sampling. Because social media is becoming more popular, researchers have begun applying text analytics models and tools to extract information from these social media platforms. Many of the text analytics models are based on Latent Dirichlet Allocation (LDA). But these models are often poor estimators of topic proportions for emerging topics. Therefore, the second part of dissertation proposes a visual summarizing technique based on topic models, a point system, and Twitter feeds to support passive summarizing and sensemaking. The associated “importance score” point system is intended to mitigate the weakness of topic models. The proposed method is called TWitter Importance Score Topic (TWIST) summarizing method. TWIST employs the topic propor (open full item for complete abstract)

Committee: Theodore Allen (Advisor); Steven MacEachern (Committee Member); Cathy Xia (Committee Member); Nena Couch (Other) Subjects: Finance; Industrial Engineering; Operations Research; Statistics; Systems Science

Doctor of Philosophy, The Ohio State University, 2018, Computer Science and Engineering

Digitalized scientific literature, as a special type of text articles, is considered valuable knowledge repository in widespread academic and practical settings. Biomedical literature has specifically played an important role in supporting evidence-based medicine and promoting quality healthcare. Given an information need such as a patient problem, information retrieval towards biomedical literature has been focusing on the identification of high relevant articles to support up-to-date knowledge synthetization and reliable decision making. In particular, high recall, high precision, and human involvement are expected for a rigorous information retrieval in healthcare. Despite the critical information needs requiring high effectiveness and efficiency, the information overload from the large volume and heterogeneous biomedical literature has placed challenges on that. In this dissertation, we propose an integrated and generalizable framework of text and visual analytics to facilitate the significant domain application of biomedical literature retrieval. We focus on the unmet and most challenging aspect of identifying high relevant articles from a text corpus, which is typically an article collection obtained via exhaustive literature search. We convert extensive biomedical articles to effective representations that encode underlying article meanings and indicate article relevancies; and promote advantageous visualizations to exploit and explore article representations so that humans can get involved in not only task accomplishment but also knowledge discovery. We first implement text analytics to generate machine-understandable article features and representations, and promote their effectiveness with multiple knowledge and computational resources. Consider the special format of biomedical literature, we start by investigating the fundamental lexical feature space consisting of diverse article elements and examine their usefulness in predicting article relevan (open full item for complete abstract)

Committee: Alan Ritter Ph.D. (Advisor); Po-Yin Yen Ph.D. (Advisor); Raghu Machiraju Ph.D. (Committee Member) Subjects: Biomedical Research; Computer Science; Information Science

Doctor of Philosophy (PhD), Wright State University, 2016, Computer Science and Engineering PhD

Understanding users' latent intents behind search queries is essential for satisfying a user's search needs. Search intent mining can help search engines to enhance its ranking of search results, enabling new search features like instant answers, personalization, search result diversification, and the recommendation of more relevant ads. Hence, there has been increasing attention on studying how to effectively mine search intents by analyzing search engine query logs. While state-of-the-art techniques can identify the domain of the queries (e.g. sports, movies, health), identifying domain-specific intent is still an open problem. Among all the topics available on the Internet, health is one of the most important in terms of impact on the user and forms one of the most frequently searched areas. This dissertation presents a knowledge-driven approach for domain-specific search intent mining with a focus on health-related search queries. First, we identified 14 consumer-oriented health search intent classes based on inputs from focus group studies and based on analyses of popular health websites, literature surveys, and an empirical study of search queries. We defined the problem of classifying millions of health search queries into zero or more intent classes as a multi-label classification problem. Popular machine learning approaches for multi-label classification tasks (namely, problem transformation and algorithm adaptation methods) were not feasible due to the limitation of label data creations and health domain constraints. Another challenge in solving the search intent identification problem was mapping terms used by laymen to medical terms. To address these challenges, we developed a semantics-driven, rule-based search intent mining approach leveraging rich background knowledge encoded in Unified Medical Language System (UMLS) and a crowd-sourced encyclopedia (Wikipedia). The approach can identify search intent in a disease-agnostic manner and has been eva (open full item for complete abstract)

Committee: Amit Sheth Ph.D. (Advisor); Krishnaprasad Thirunarayan Ph.D. (Committee Member); Michael Raymer Ph.D. (Committee Member); Jyotishman Pathak Ph.D. (Committee Member) Subjects: Computer Science

Master of Science, The Ohio State University, 2013, Computer Science and Engineering

Enterprise social media potentially plays a pivotal role in capturing useful insights about employee behavior. This thesis explores how, with the availability of social media analytics tools and methods, this potential is realized in effective decision making within the business processes of an enterprise. Specifically it proposes a generic analytics framework that provides visibility into employee engagement which is a measure of organizational effectiveness in the enterprise through data extracted from internal enterprise social media and other traditional data sources. This extracted data is called an "Engagement Persona". Here the standard employee profiles (factual information from human resource systems) are enhanced with behavioral insights derived from social media and captured interesting relationships that serve as rich information assets. The thesis shows that the Engagement Persona provides visibility that could ultimately reinforce engagement. Sample Engagement Personas are shown by implementing a working model of the proposed framework within a large insurance company that uses Yammer - a micro blogging system to update colleagues on company events, ask work-related questions, and broadcast problem situations. Further, the implementation showed large classes of messages revealing user intent. These were aggregated into a form reflecting the user's underlying Engagement Persona. This holistic view of each employee was shown to be valuable for business roles like management, communications and the Human Resources. The value is in providing visibility into aspects of employee engagement thus leading to smarter management decision-making. Feedback from these roles shows that they are satisfied with the improved visibility and ability to respond on a timelier basis to engagement changes. Thus the thesis shows the framework helps in boosting engagement activities and also fosters better knowledge sharing across the different business units of the enterprise. (open full item for complete abstract)

Committee: Jayashree Ramanathan Dr. (Advisor); Rajiv Ramnath Dr. (Committee Member) Subjects: Computer Engineering; Computer Science