Text analysis

• Google Ngram Viewer

Text data sources¶

Data¶

• Patent data
• Job postings
• Firm earnings call
• Newspapers
• Syllabus
• Twitter

Libraries¶

TBD

Text representation¶

Tokenization¶

• n-gram - Wikipedia

TF-IDF¶

• tf–idf - Wikipedia

Embeddings¶

Word embeddings¶

• Word embedding - Wikipedia

Document embeddings¶

TBD