26 Business Professionals in a multinational corporation were asked to assess their search skill prior to undertaking 2 exploratory search goal tasks (not a single right result) using their enterprise search engine. Task #1 could have potentially many results, Task #2 very few. For each task 4 high value documents were hidden in the search... Continue Reading →

I created a vectorspace model using 700 UK license relinquishment reports, comparing companies to risk (x-axis) and uncertainty (y-axis) using word vectors and cosine similarity. Based on patterns in text, those companies in the top right quadrant have a higher 'similarity' to risk and uncertainty; those in the bottom left - the opposite. The companies... Continue Reading →

Word embeddings in Natural Language Processing (NLP) are a representation of words in real valued vectors that encode the meaning of the word. Words closer in vector space are likely to be similar in meaning. From 5,000 reports, the cross plots above shows the word vectors for 1500 minerals to the word vectors for hydrothermal... Continue Reading →

I have been experimenting with text analytics on 500 public Mars Geology documents. Following on from my last post spatialising data on a map, I have also explored multivariate heat map clustering. Recognition to Metsalu and Vilo (2015) for clustering visualisations originally developed for Nucleic Acid research.

#mars #nasa #geology #naturallanguageprocessing

Over 5,000 USGS reports were analysed using Natural Language Processing (NLP) and Machine Learning to detect potential environments for Copper. Over 1.5Million detections were made. The results were coarsely spatialised by country and shown on the map above. The larger the pie-chart the greater the tone of uncertainty / speculation. These data were displayed in... Continue Reading →

Last 5 years Google Searches for Critical Minerals. #google #criticalminerals ..and for oil & gas exploration #petroleumexploration ..and Green and Blue Hydrogen #greenhydrogen #bluehydrogen

There are several Question & Answer OpenSource Language Comprehension models that can be applied to unstructured text. Even without tuning to a domain, they are capable of producing some quite remarkable answers buried in large amounts of text for simple factual questions. The image above is a simple example related to Carbon Capture, Utilisation and Storage... Continue Reading →

Sentence based sentiment analysis was conducted for monthly hydrological summary reports for the UK, covering groundwater, river flows and rainfall over the past 9 years. The hypothesis was whether seasonal changes would be picked out using text based sentiment. Averaging smoothes out the 'edge cases' but nevertheless some consistent patterns may emerge. Further work ongoing.... Continue Reading →