Web & Text Mining, Natural Language Processing, Privacy, Censorship, Obfuscation, Adversarial Debiasing
- Working with University of Iowa CompEpi group training ML classifiers, Logistic Regression, Naive Bayes, CNN, on doctors’ notes to predict patient readmissions.
- Classifying meme sentiments and type of humour expressed, based on SemEval 2020 Task 8
- Studying content moderation in social media. Exploring moderation with respect to classification and obfuscation. Looking to understand moderation methods being employed and how they may affect promotion of free speech.
Rusert, J., Khalid, O., Hong, D., Shafiq, Z., & Srinivasan, P. No Place to Hide: Inadvertent
Location Privacy Leaks on Twitter, Proceedings on Privacy Enhancing Technologies,
Rusert, J., & Srinivasan, P. NLP@UIOWA at SemEval-2019 Task 6: Classifying the Crass
using Multi-windowed CNNs. In Proceedings of the 13th International Workshop on
Semantic Evaluation (pp. 704-711).
Rusert, J., & Pedersen, T. Umnduluth at semeval-2016 task 14: Wordnet's missing lemmas.
In Proceedings of the 10th International Workshop on Semantic Evaluation (SemEval-2016)
Language Evolves, so should WordNet: Automatically Extending WordNet with the Sense of Out of Vocabulary Lemmas