Dr. Ronak Razavisousan

Ph.D. ,  Information Systems, 2022Ronak

Dr. Ronak Razavisousan was advised by Dr. Karuna Joshi from 2018-2022. Her research interests lie in the broad area of Data Science.

She developed a novel methodology, called Textual Fuzzy Interpretive Structural Modeling (TFISM), that automatically analyses large textual datasets to identify the internal and external relationships between factors in the document. She applied her methodology to analyze documents in various domains like Supply Chain Management, Data Privacy regulations and Student Mobility.

She is currently a Senior Data Scientist at Stonehenge.


Ronak successfully defended her Ph.D. Thesis, Building Textual Fuzzy Interpretive Structural Modeling to Analyze Complex Problems, in September 2022.

Committee: Dr. Karuna P Joshi (Chair), Dr. Zhiyuan Chen, Dr. Vandana Janeja, Dr. George Karabatis, Dr. Anupam Joshi
Organizations regularly make decisions on complex issues with multiple variables or parameters. Hence, there is a strong motivation for the organization’s Management to formalize and adopt a scientific approach to their decision-making process based on their ground truth data. From a scientific point of view, each variable or parameter that influences a complex issue has to be analyzed independently and within the networks of other parameters. This will enable us to understand each parameter’s role and the potential for affecting or changing the whole system. However, at present, with the complexity of issues and the deluge of Big Data to be analyzed, it is not feasible to apply several different approaches before making a timely and informed decision. We have developed a novel methodology, called Textual Fuzzy InterpretiveStructural Modeling (TFISM), that helps us understand the variables related to complex issues and the connection between these variables. TFISM identifies vital terms or influential factors in a textual dataset, prioritizes the power of each factor, and then determines the connections and hierarchies between these factors. This computational social science methodology enhances Interpretive Structural Modeling (ISM) approaches to allow the input to be textual data.  TFISM is multi-disciplinary and integrates ISM with Artificial Intelligence, text extraction, and information retrieval techniques. It is a domain-free methodology that can assist in complex decision-making, and we have applied this methodology to different datasets from social media and academic articles Three separate domains were analyzed and validated with the technique during this research study.


Ronak successfully defended her Ph.D. Proposal in March 2020.

Proposal: Developing Student Mobility Model using Fuzzy Interpretive Structural Modeling (Fuzzy- ISM) for Social Media data
Committee: Dr. Karuna P Joshi (Chair), Dr. Zhiyuan Chen, Dr. Vandana Janeja, Dr. George Karabatis, Dr. Yelena Yesha
Abstract: Economists, sociologists, and general social scientists have attempted to clarify the human migration concept. Their success is influenced by changes in general society because of the internal relationships between pulling, pushing, and emerging new factors. In recent years, technology enhancement and globalization caused a drastic increase in human migration all over the world. At the same time, host countries began focusing on educated immigrants and the benefits they afforded their nations. Modern methods for studying human behavior, such as social media analysis and computational analysis, are not effectively employed in the field of human migration and specifically student mobility. Our research explores student mobility motivations, characteristics, competencies, and approaches through social media data with the help of Natural Language Processing (NLP) techniques. This work tries to identify the factors of student mobility and highlight the role and weight of each one, to model the transition of a student in different situations. The relationship between these factors fills the dearth of knowledge concerning human migration focusing on student mobility.
This research primarily utilizes quantitative methods, but where clarification or detail is needed a qualitative method is implemented. The proposed solution is conducted in two parts. In the first part, the collected data from social media (Twitter) is examined with an established economic migration model. NLP techniques boost the content analysis and find the similarity between datasets. In the second part, I model the factors extracted from the data with the help of the prevailing modeling methodology. A fuzzy extension of Interpretive Structural Modeling (Fuzzy-ISM) is customized for textual data and the process flow designed to run the model automatically.

Ronak was invited to present at the Data Science Consortium organized by Michigan Institute for Data Science (MIDAS) on November 13-15 2019.