Esin Durmus


Contact me: ed459@cornell.edu

Welcome! I am Esin Durmus. I am a third year PhD student in Cornell University advised by Claire Cardie.

Research Interests

  • Natural Language Processing
  • Social Media Analysis
  • Computational Social Science
  • Argumentation Mining
  • Argument Generation


My research

My primary research focuses on understanding and modeling user behaviour (things like how users interact with each other, how they express their opinions, how their activity changes over time) on social media. I focus on modeling user-related characteristics and language jointly to understand how the language and interaction style varies across different groups of people. I use techniques from Machine Learning, NLP and combine these with the literature from Social Science, Pyschology, and Communications with the hope of contributing to many of these fields.

Recently, I am also interested in argument generation. I aim to understand and model the important subtasks to generate arguments at the right level of coherence and specificity at a given discourse.


News

  • Our paper 'Modeling the Factors of User Success in Online Debate' got accepted to WWW (The Web Conference) 2019.
  • Our work on "Exploring the Role of Prior Beliefs for Argument Persuasion" got accepted to NAACL for oral presentation.
  • Our work on 'Understanding the Effect of Gender and Stance on Opinion Expression in Debates on "Abortion"' got accepted to PEOPLES workshop co-organized with NAACL.
  • Debate.org dataset is now publicly available.

Publications

  • Modeling the Factors of User Success in Online Debate. Esin Durmus and Claire Cardie.
    To appear in WWW (The Web Conference) 2019.
  • Exploring the Role of Prior Beliefs for Argument Persuasion. Esin Durmus and Claire Cardie.
    In Proceedings of the Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL), 2018.
    Bibtex
  • Understanding the Effect of Gender and Stance on Opinion Expression in Debates on "Abortion”. Esin Durmus and Claire Cardie.
    In Proceedings of PEOPLES2018 workshop (co-organized with NAACL) on computational modeling of peoples opinions, personality, and emotions in social media.
    Bibtex
  • Vlad Niculae, Kai Sun, Xilun Chen, Yao Cheng, Xinya Du, Esin Durmus, Arzoo Katiyar and Claire Cardie.
    Cornell Belief and Sentiment System at TAC 2016. Text Analysis Conference (TAC). 2016.

Datasets

  • Debate.org dataset : Contains a collection of 77,595 debates from October of 2007 until November of 2017 drawn from debate.org along with comprehensive user profile information for 35,684 users.

Teaching

  • Introduction to Natural Language Processing, Cornell University. Fall 2016, Fall 2017, Fall 2018.
  • Machine Learning for Data Science, Cornell University. Spring 2016.
  • Introduction to Web Design, Cornell University. Fall 2015.

Work Experience

  • Applied Scientist Intern in Amazon Inc. Summer 2017.

Contact

You can contact me at ed459@cornell.edu.

Design: HTML5 UP.