Download now Free registration required
The authors use quantitative media (blogs, and news as a comparison) data generated by a large-scale Natural Language Processing (NLP) text analysis system to perform a comprehensive and comparative study on how a company's reported media frequency, sentiment polarity and subjectivity anticipates or reflects its stock trading volumes and financial returns. Their analyzes provides concrete evidence that media data is highly informative, as previously suggested in the literature - but never studied on their scale of several large collections of blogs and news for over five years.
- Format: PDF
- Size: 344.2 KB