CHChristopher G. Healey

Christopher G. Healey

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Christopher G. Healey has a total of 52 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Top Cited Papers

    Abstractive Summarization of Large Document Collections Using GPT

    by Shengjie Liu, Christopher G. Healey

    This paper proposes a method of abstractive summarization designed to scale to document collections instead of individual documents. Our approach combines semantic clustering, document size reduction within topic clusters, semantic chunking of a cluster's documents, GPT-based summarization and concatenation, and a combined sentiment and text visualization of each topic to support exploratory data analysis. A statistical comparison of our results with those of existing state-of-the-art systems, including BART, BRIO, PEGASUS, and MoCa, using ROUGE and METEOR summary scores showed statistically equivalent performance with BART and PEGASUS in the CNN/Daily Mail test dataset and with BART in the Gigaword test dataset. This finding is promising, since we view document collection summarization as more challenging than individual document summarization. We conclude with a discussion of how issues of scale are being addressed in the GPT large language model, then suggest potential areas for future work.


  • Open Access

    Visual Analytics for NASCAR Motorsports

    by Kornelia Bastin, Christopher G. Healey

    The National Association of Stock Car Auto Racing (NASCAR) is ranked among the top ten most popular sports in the United States. NASCAR events are characterized by on-track racing punctuated by pit stops since cars must refuel, replace tires, and modify their setup throughout a race. A well-executed pit stop can allow drivers to gain multiple seconds on their opponents. Strategies around when to pit and what to perform during a pit stop are under constant evaluation. One currently unexplored area is publically available communication between each driver and their pit crew during the race. Due to the many hours of audio, manual analysis of even one driver’s communications is prohibitive. We propose a fully automated approach to analyze driver–pit crew communication. Our work was conducted in collaboration with NASCAR domain experts. Audio communication is converted to text and summarized using cluster-based Latent Dirichlet Analysis to provide an overview of a driver’s race performance. The transcript is then analyzed to extract important events related to pit stops and driving balance: understeer (pushing) or oversteer (over-rotating). Named entity recognition (NER) and relationship extraction provide context to each event. A combination of the race summary, events, and real-time race data provided by NASCAR are presented using Sankey visualizations. Statistical analysis and evaluation by our domain expert collaborators confirmed we can accurately identify important race events and driver interactions, presented in a novel way to provide useful, important, and efficient summaries and event highlights for race preparation and in-race decision-making.


  • Open Access

    Towards a Robust Retrieval-Based Summarization System

    by Shengjie Liu, Jing Wu, Jingyuan Bao, Wenyi Wang, Naira Hovakimyan, Christopher G Healey

    This paper describes an investigation of the robustness of large language models (LLMs) for retrieval augmented generation (RAG)-based summarization tasks. While LLMs provide summarization capabilities, their performance in complex, real-world scenarios remains under-explored. Our first contribution is LogicSumm, an innovative evaluation framework incorporating realistic scenarios to assess LLM robustness during RAG-based summarization. Based on limitations identified by LogiSumm, we then developed SummRAG, a comprehensive system to create training dialogues and fine-tune a model to enhance robustness within LogicSumm's scenarios. SummRAG is an example of our goal of defining structured methods to test the capabilities of an LLM, rather than addressing issues in a one-off fashion. Experimental results confirm the power of SummRAG, showcasing improved logical coherence and summarization quality. Data, corresponding model weights, and Python code are available online.


  • Open Access

    Abstractive Summarization of Large Document Collections Using GPT

    by Sengjie Liu, Christopher G. Healey

    This paper proposes a method of abstractive summarization designed to scale to document collections instead of individual documents. Our approach applies a combination of semantic clustering, document size reduction within topic clusters, semantic chunking of a cluster's documents, GPT-based summarization and concatenation, and a combined sentiment and text visualization of each topic to support exploratory data analysis. Statistical comparison of our results to existing state-of-the-art systems BART, BRIO, PEGASUS, and MoCa using ROGUE summary scores showed statistically equivalent performance with BART and PEGASUS on the CNN/Daily Mail test dataset, and with BART on the Gigaword test dataset. This finding is promising since we view document collection summarization as more challenging than individual document summarization. We conclude with a discussion of how issues of scale are

  • Open Access

    Visual Analytics for NASCAR Motorsports

    by Kornelia Bastin, Christopher Healey

    The National Association of Stock Car Auto Racing (NASCAR) is consistently ranked among the top ten most popular sports in the United State1,2 . It is the most lucrative, generating an estimated $3 billion annually3 . Teams are financially well-supported and competitive in all areas where an advantage might be gained. NASCAR events are characterized by on-track racing punctuated by pit stops since cars must refuel, replace tires, and modify their setup throughout a race. A well-executed pit stop can allow drivers to gain multiple seconds on their opponents. Strategies around when to pit and what to perform during a pit stop are under constant evaluation. One currently unexplored area is publically available communication between each driver and their pit crew during the race. Due to the many hours of audio, manual analysis of even one driver’s communications is prohibitive. We propose a fully automated approach to analyze driver–pit crew communication. Our work was conducted in collaboration with NASCAR domain experts—a simulation manager, a crew chief, and a software engineering manager—to validate our findings. Audio communication is converted to text and summarized using cluster-based Latent Dirichlet Analysis (LDA) to provide an overview of a driver’s race performance. The transcript is then analyzed to extract important events related to pit stops and driving balance: whether a car is understeering (pushing) or oversteering (over-rotating). Named entity recognition (NER) and relationship extraction provide context to each event. A combination of the race summary, events, and real-time race data provided by NASCAR are presented using Sankey visualizations. Statistical analysis and evaluation by our domain expert collaborators confirmed we can accurately identify important race events and driver interactions, presented in a novel way to provide useful, 1 important, and efficient summaries and event highlights for race preparation and in-race decision-making.

  • Visual Analytics for the Coronavirus COVID-19 Pandemic

    by Christopher G. Healey, Susan J. Simmons, Chandra Manivannan, Yoonchul Ro

    The coronavirus disease COVID-19 was first reported in Wuhan, China, on December 31, 2019. The disease has since spread throughout the world, affecting 227.2 million individuals and resulting in 4,672,629 deaths as of September 9, 2021, according to the Johns Hopkins University Center for Systems Science and Engineering. Numerous sources track and report information on the disease, including Johns Hopkins itself, with its well-known Novel Coronavirus Dashboard. We were also interested in providing information on the pandemic. However, rather than duplicating existing resources, we focused on integrating sophisticated data analytics and visualization for region-to-region comparison, trend prediction, and testing and vaccination analysis. Our high-level goal is to provide visualizations of predictive analytics that offer policymakers and the general public insight into the current pandemic state and how it may progress into the future. Data are visualized using a web-based jQuery+Tableau dashboard.† The dashboard allows both novice viewers and domain experts to gain useful insights into COVID-19's current and predicted future state for different countries and regions of interest throughout the world.


  • Visual Analytics of Text Conversation Sentiment and Semantics

    by Christopher G. Healey, Gowtham Dinakaran, Kalpesh Padia, Shaoliang Nie, J. Riley Benson, Dave Caira, Dean Shaw, Gary Catalfu, Ravi Devarajan


  • Open Access

    Dengue Fever Surveillance in India Using Text Mining in Public Media

    by Andrea Villanes, Emily Griffiths, Michael Rappa, Christopher G. Healey

    Despite the improvement in health conditions across the world, communicable diseases remain among the leading mortality causes in many countries. Combating communicable diseases depends on surveillance, preventive measures, outbreak investigation, and the establishment of control mechanisms. Delays in obtaining country-level data of confirmed communicable disease cases, such as dengue fever, are prompting new efforts for short- to medium-term data. News articles highlight dengue infections, and they can reveal how public health messages, expert findings, and uncertainties are communicated to the public. In this article, we analyze dengue news articles in Asian countries, with a focus in India, for each month in 2014. We investigate how the reports cluster together, and uncover how dengue cases, public health messages, and research findings are communicated in the press. Our main contributions are to 1) uncover underlying topics from news articles that discuss dengue in Asian countries in 2014; 2) construct topic evolution graphs through the year; and 3) analyze the life cycle of dengue news articles in India, then relate them to rainfall, monthly reported dengue cases, and the Breteau Index. We show that the five main topics discussed in the newspapers in Asia in 2014 correspond to 1) prevention; 2) reported dengue cases; 3) politics; 4) prevention relative to other diseases; and 5) emergency plans. We identify that rainfall has 0.92 correlation with the reported dengue cases extracted from news articles. Based on our findings, we conclude that the proposed method facilitates the effective discovery of evolutionary dengue themes and patterns.