Terms that were at least 90% accurate were included in the dictionary for a topic, while words or phrases that were less than 30% accurate were dropped. Terms between those thresholds were fine-tuned until they could be included or dropped. For example, ethical was included in the integrity dictionary.

Google

For each selected topic, researchers built a preliminary dictionary of high-fidelity words and phrases, then had two team members analyze a random sample of at least 20 reviews containing each term. The bootstrapping process generated tens of thousands of terms, which human experts reviewed and refined.

Bootstrapping Process for Culture 500 Dictionary Terms

MIT Sloan Management Review project page on measuring culture in leading companies, including the Culture 500 dataset. https://sloanreview.mit.edu/projects/measuring-culture-in-leading-companies/

Learn Before

Related