John Bollenbacher

John Bollenbacher

Auto-generated profile, based on publicly available information

John Bollenbacher

RTI International 27709 Durham NC United States

Research Focus & Metrics

Academic Career Length

6Years (2021-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
26 August 2024 in Journal of Data Science
Verified
Journal Article
Open access
PDF file
APAlexander J. Preiss
Alexander J. Preiss
CACaren A. Arbeit
Caren A. Arbeit
ABAnthony Berghammer
Anthony Berghammer
JBJohn Bollenbacher
John Bollenbacher
JMJohn V. McCarthy
John V. McCarthy
SSShaquavia Straughn
Shaquavia Straughn
Text clustering can streamline many labor-intensive tasks, but it creates a new challenge: efficiently labeling and interpreting the clusters. Generative large language models (LLMs) are a promising option to automate the process of naming text clusters, which could significantly streamline workflows, especially in domains with large datasets and esoteric language. In this study, we assessed the ability of GPT-3.5-turbo to generate names for clusters of texts and compared these to human-generated text cluster names. We clustered two benchmark datasets, each from a specialized domain: research abstracts and clinical patient notes. We generated names for each cluster using four prompting strategies (different ways of including information about the cluster in the prompt used to get LLM responses). For both datasets, the best prompting strategy beat the manual approach across all quality domains. However, name quality varied by prompting strategy and dataset. We conclude that practitioners should consider trying automated cluster naming to avoid bottlenecks or when the scale of the effort is enough to take advantage of the cost savings offered by automation, as detailed in our supplemental blueprint for using LLM cluster naming. However, to get the best performance, it is vital to test a variety of prompting strategies and perform a small test to identify which one performs best on each project’s unique data.

20 April 2021 in arXiv
Verified
Preprint
Open access
PDF file
MDMatthew R. DeVerna
Matthew R. DeVerna
FPFrancesco Pierri
Francesco Pierri
BTBao Tran Truong
Bao Tran Truong
JBJohn Bollenbacher
John Bollenbacher
DADavid Axelrod
David Axelrod
JBJohn Bryden
John Bryden
With a substantial proportion of the population currently hesitant to take the COVID-19 vaccine, it is important that people have access to accurate information. However, there is a large amount of low-credibility information about vaccines spreading on social media. In this paper, we present the CoVaxxy dataset, a growing collection of English-language Twitter posts about COVID-19 vaccines. Using one week of data, we provide statistics regarding the numbers of tweets over time, the hashtags used, and the websites shared. We also illustrate how these data might be utilized by performing an analysis of the prevalence over time of high- and low-credibility sources, topic groups of hashtags, and geographical distributions. Additionally, we develop and present the CoVaxxy dashboard, allowing people to visualize the relationship between COVID-19 vaccine adoption and U.S. geo-located posts in our dataset. This dataset can be used to study the impact of online information on COVID-19 health outcomes (e.g., vaccine uptake) and our dashboard can help with exploration of the data.