TEXT: Content Attention and Engagement
Projects in the Text theme aim to develop a deeper understanding of how users engage with media content, what content factors may predict content success, and how to create content summaries.
We use controlled lab experiments and other social science methods, as well as machine learning, natural language processing, and statistical modeling to analyze human attention and interaction as it occurs in the real world.
Text Theme News
Text Theme Publications
Using BERT Performance in Propaganda Analysis
Presented at the 2nd Workshop on NLP for Internet Freedom
Understanding Reader Backtracking Behavior in Online News Articles
Uzi Smajda, Max Grusky, Yoav Artzi, and Mor Naaman
The Role of Source, Headline, and Expressive Responding in Political News Evaluation
Maurice Jakesch, Moran Koran, Anna Evtushenko, and Mor Naaman
Presented at Computation & Journalism 2019, Feb 1-2, Miami, FL
Newsroom: A Dataset of 1.3 Million Summaries with Diverse Extractive Strategies
Max Grusky, Mor Naaman, and Yoav Artzi
Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics.
Modeling Sub-Document Attention Using Viewport Time
Max Grusky, Jeiran Jahani, Josh Schwartz, Dan Valente, Yoav Artzi, and Mor Naaman
Proceedings of the 2017 CHI Conference on Human Factors in Comput Systems, p 6475.
A Data-Driven Study of View Duration on YouTube
Minsu Park, Mor Naaman, Jonah Berger
Proceedings of the International Conference on Weblogs and Social Media (ICWSM) 2016.
