Amir is an assistant professor at the Khoury College of Computer Sciences. His research develops natural language processing, machine learning, and information retrieval methods for personal and user-generated text, such as social media and clinical notes from electronic health records.

Amir is primarily interested in methods utilized for tasks involving subjective, personalized, or user-level inferences (e.g., opinion mining and digital phenotyping). In particular, his work aims to improve the reliability, interpretability, and fairness of predictive models and analytics derived from personal and user-generated data.

Amir’s research is part of ongoing efforts to develop human-centered AI meant to empower rather than replace humans and AI for Social Good that tackles meaningful social, societal, and humanitarian challenges. He often collaborates with domain experts on multidisciplinary projects that address real-world problems in social sciences, medicine, and epidemiology to achieve these goals.