Karine Megerdoomian's homepage

Sentiment Analysis and Opinion Mining in Social Media

CCT department, Georgetown University (Summer 2015)

    The goal of this course is to explore the core concepts of sentiment analysis and opinion mining in social media, to understand the state-of-the-art in the field, and to investigate the limitations of these approaches. In this course, we will be studying recent publications and studies applying sentiment analysis in the domains of political science, clinical studies, marketing and deception detection.
    The students will get hands-on experience in using some of the tools and technology available for automatically downloading Twitter data and performing sentiment analysis on the text. Automatic tools allow the researcher to go beyond manual analysis of a limited data set to detect emerging trends, automatically identify opinions in public debate or product reviews, and investigate temporal changes. We will also discuss the combination of qualitative and quantitative measures applied to identifying opinions and sarcasm in social media. As part of the final project, the students will have an opportunity to examine sentiment analysis on a topic of their choice.

Narrative Networks: Analysis of Framing and Narratives in Online Media

CCT department, Georgetown University (Fall 2013)

    Narratives are used to convey a certain perspective or to craft an identity by tapping into preexisting beliefs and opinions. Narratives are also the central mechanism through which ideologies are expressed and absorbed in the population. The study of narratives and framing theory is therefore a fundamental component of media studies, strategic communications, organization branding and policy setting. The course focuses on the core concepts of narrative theory in online news and social media, and introduces the students to technology that can be applied for the automatic identification of framing and narrative. We will apply content and corpus analysis to detect important frames and rhetoric, and social network analysis to identify distinct factions and perspectives. Computer skills are not required for this course; technical concepts will be presented through readings and hands-on applications in the classroom.

Social Media Analytics: Culture and ideology in the Middle East

CCT department, Georgetown University (Fall 2012)

    The goal of this course was to discover the socio-cultural issues in the Middle East through the application of Social Media Analysis technologies. The focus of this seminar is on Social Media Analysis technology with emphasis on Twitter and Blogs and its application to several Middle Eastern nations. The goal is to discover the main issues, cultural and religious forces, minority groups, women s roles, and youth interests by automatically investigating the trends and discussions found in new media sources.

    Heritage Language Courses Taught

All classes taught at the University of California San Diego, Linguistics department. Each course consisted of a Culture and Communication session (taught by Elham Sadegholvad) and a language analysis session (taught by me). Full syllabus, exercises and handouts for the courses are available under the Language Analysis site.