Hi! I’m a Ph.D. candidate at Worcester Polytechnic Institute in the DAISY Lab advised by Elke Rundensteiner and Xiangnan Kong in the Data Science program, a part of the Computer Science department. I am developing deep learning and reinforcement learning methods for time series data mining/machine learning and am interested in applications in healthcare and sustainability. I have published several papers at top data mining and machine learning conferences and have been fortunate to collaborate with some wonderful people on a wide variety of topics including NLP and explainability.

My CV can be found here.



  • Time series modelling
  • Recurrent Neural Networks
  • Early Classification
  • Healthcare applications

I am generally interested in sequential representation learning, or building vector representations that capture relevant temporal dynamics in sequential data such as time series or text. So far, I have studied and published on early classification, clinical note classification, attention mechanisms for RNNs, meta word embeddings, interpretable machine learning, and irregularly-sampled time series. Much of my work involves Recurrent Neural Networks and Reinforcement Learning. On my Publications page I describe some of my representative research in more detail. I am also interested in applications to problems of human health and sustainability (particularly conservation biology).

Please feel free to contact me with questions regarding my research or our program at WPI. I am always looking to chat about research!


  • Learning to Selectively Update State Neurons in Recurrent Networks

    T. Hartvigsen, C. Sen, X. Kong, E. Rundensteiner.
    CIKM, 2020. Research track.
    [pdf] [code]
  • Recurrent Halting Chain for Early Multi-label Classification

    T. Hartvigsen, C. Sen, X. Kong, E. Rundensteiner.
    KDD, 2020. Research track, acceptance rate: 16.9%.
  • Human Attention Maps for Text Classification: Do Humans and Neural Networks Focus on the Same Words?

    C. Sen, T. Hartvigsen, B. Yin, X. Kong, E. Rundensteiner.
    ACL, 2020. Long paper, acceptance rate: 17.6%.
    [pdf] [link] [data]
  • Clinical Performance Evaluation of a Machine Learning System for Predicting Hospital-Acquired Clostridium Difficile Infection

    E. Teeple, T. Hartvigsen, C. Sen, K. Claypool, E. Rundensteiner.
    HEALTHINF, 2020. Best Poster.
  • Patient-Level Classification of Clinical Note Sequences Guided by Attributed Hierarchical Attention

    C. Sen, T. Hartvigsen, X. Kong, E. Rundensteiner.
    IEEE BigData, 2019.
  • Learning Temporal Relevance in Longitudinal Medical Notes

    C. Sen, T. Hartvigsen, X. Kong, E. Rundensteiner.
    IEEE BigData, 2019.
  • Adaptive-Halting Policy Network for Early Classification

    T. Hartvigsen, C. Sen, X. Kong, E. Rundensteiner.
    KDD, 2019. Research track, acceptance rate: 14.2%.
  • Early Diagnosis Prediction with Recurrent Neural Networks

    D. Johnston, L. Klindziuk, L. Nazarov, T. Hartvigsen, E. Rundensteiner.
    IEEE URTC, 2019.
  • Comparing General and Locally-Learned Word Embeddings for Clinical Text Mining

    J. Thadajarassiri, C. Sen, T. Hartvigsen, X. Kong, E. Rundensteiner.
    IEEE BHI, 2019.
  • Handling Missing Values in Multivariate Time Series Classification

    J. Friend, A. Hauck, S. Kurada, C. Sen, T. Hartvigsen, E. Rundensteiner.
    IEEE URTC, 2018.
  • Detecting MRSA Infections by Fusing Structured and Unstructured Electronic Health Record Data

    T. Hartvigsen, C. Sen, E. Rundensteiner.
    Communications in Computer and Information Science, Volume 1024, 2018.
  • Early Prediction of MRSA Infections using Electronic Health Records

    T. Hartvigsen, C. Sen, S. Brownell, E. Teeple, X. Kong, E. Rundensteiner.
    HEALTHINF, 2018. Best student paper short list.
  • CREST - Risk Prediction for Clostridium Difficile Infection Using Multimodal Data Mining

    C. Sen, T. Hartvigsen, K. Claypool, E. Rundensteiner.
    ECML, 2017.


In my spare time, I enjoy rock climbing, cycling, reading (fantasy, science fiction, science fact), and playing guitar.