Text-based Trend Analysis Tool

This tool helps domain experts analyze temporal shifts in healthcare architectural design priorities using text-based trend analysis. It uses vector space models to uncover trends across decades. Key features include CADE alignment for comparable vector spaces ¹², interactive visualizations (cosine similarity and PPMI graphs), and flexible preprocessing options for tailored analysis. The tool combines quantitative methods with qualitative insights for a comprehensive understanding of trends.

References

Footnotes

1. Bianchi, F., Di Carlo, V., Nicoli, P., & Palmonari, M. (2020). Compass-aligned distributional embeddings for studying semantic differences across corpora. arXiv:2004.06519. ↩

2. Di Carlo, V., Bianchi, F., & Palmonari, M. (2019). Training temporal word embeddings with a compass. Proceedings of the AAAI Conference on Artificial Intelligence, 33(01), 6326–6334. https://doi.org/10.1609/aaai.v33i01.33016326. ↩