Text Mining from Free Unstructured Text: An Experiment of Time Series Retrieval for Volcano Monitoring

Abstract

Volcanic activity may influence climate parameters and impact people safety, and hence monitoring its characteristic indicators and their temporal evolution is crucial. Several databases, communications and literature providing data, information and updates on active volcanoes worldwide are available, and will likely increase in the future. Consequently, information extraction and text mining techniques aiming to efficiently analyze such databases and gather data and parameters of interest on a specific volcano can play an important role in this applied science field. This work presents a natural language processing (NLP) system that we developed to extract geochemical and geophysical data from free unstructured text included in monitoring reports and operational bulletins issued by volcanological observatories in HTML, PDF and MS Word formats. The NLP system enables the extraction of relevant gas parameters (e.g., SO2 and CO2 flux) from the text, and was tested on a series of 2839 daily and weekly bulletins published online between 2015 and 2021 for the Stromboli volcano (Italy). The experiment shows that the system proves capable in the extraction of the time series of a set of user-defined parameters that can be later analyzed and interpreted by specialists in relation with other monitoring and geospatial data. The text mining system can potentially be tuned to extract other target parameters from this and other databases.