Experiments
Experiments are projects that explore aspects of the overall theme.
Our team and collaborators built them in support of the overarching research project.
List of Experiments
The current list of experiments includes:
- Library Sentences
- Parametric Hermeneutics
- Place Schema
- Sentiment Analysis
- Term Explorer
- Text Analysis Overview
Background
These experiments interpret data extracted by text analysis tools. We suggest how these data could serve art, design, and research projects. Our experiments also illustrate the limitations of text analysis.
Can digital tools describe places?
Text analysis can identify parts of speech (e.g., nouns, adjectives, etc.), predict named locations and entities (e.g., Gormenghast Castle, Titus), and quantify word relatedness (e.g., black commonly appears with castle). Experimentation revealed the challenges of defining, quantifying and relating specific 'places' and phenomena.
Many subjectivities contribute to sense of place. Meaningful place representations should capture this complexity, but statistical methods produce 'averages' of rich datasets. As well as automating word extraction, digital tools provide ways for users to explore subjectivities and interrelationships using unprocessed data.
For example, we know 'library' appears times in Peake's novels.
Children
- Bias in Language
- Colour Timeline
- Colour Words
- Library Sentences
- Parametric Hermeneutics
- Place Schema
- Sentiment Analysis
- Term Explorer
- Text Analysis Overview
Backlinks