Welcome!

My name is Reihane Boghrati and I'm currently a final year Ph.D student at the department of Computer Science, University of Southern California. I'm working as a research assistant in the Computational Social Science Laboratory under supervision of Prof. Morteza Dehghani.
Relying on natural language processing methods, a priori hypothesis, and behavioral experiments, we aim to explore cognitive and psychological traces in artifacts of social discourse (such as narratives, social media, political speeches, and news articles) and measure complex psychologically-relevant variables in a manner that enables inferential testing.
My research is particularly focused on designing and developing a tool to measure grammatical structures in language. I applied this tool in various domains to study the language usage of different groups and explore the patterns among people’s verbal interactions.

Conversation Level Syntax Similarity Metric

While semantics and word choice have been extensively used to study human behavior, less emphasis has been put on the role of syntax and whether the way people put their words together can help to convey their intentions.
In this work, we introduce ConversAtion level Syntax SImilarity Metric (CASSIM), a novel method for calculating conversation level syntax similarity. We have developed and provided evidence for the effectiveness of CASSIM for comparing syntax structures between documents.

Decoding the Neural Representation of Story Meanings across Languages

In this project, we used story-level embeddings to examine the neuro-semantic representations of stories in people from three different linguistic-cultural backgrounds, across their three native languages. We demonstrated that story-level vector representations can capture story content across languages, and can be used to localize the neuro-semantic content of stories to specific regions of the brain.

Diagnosis of Coronary Artery Disease Using Data Mining

Coronary Artery Disease (CAD) is the most common fatal heart disease, and is the subject of large body of studies. Our project aimed to examine effects of set of features, including lab data and echo information, on CAD diagnosis which some of them were not considered in previous studies.

Get in touch

Feel free to contact me if you are interested to know more about my research or have any questions.